Merge branch 'main' into minimapcontrol

docs/contributing/LOCAL_DEVELOPMENT.md

@@ -125,7 +125,7 @@ To make a workspace:
 
 Should look something like this:
 
-```json
+```jsonc
 {
   // I like to have all InvokeAI-related folders in my workspace
   "folders": [
@@ -164,7 +164,7 @@ to set up your `launch.json` and try it out.
 
 Now we can create the InvokeAI debugging configs:
 
-```json
+```jsonc
 {
   // Use IntelliSense to learn about possible attributes.
   // Hover to view descriptions of existing attributes.

invokeai/app/api/routers/models.py

@@ -14,6 +14,7 @@ from invokeai.backend.model_management.models import (
     OPENAPI_MODEL_CONFIGS,
     SchedulerPredictionType,
     ModelNotFoundException,
+    InvalidModelException,
 )
 from invokeai.backend.model_management import MergeInterpolationMethod
 
@@ -36,11 +37,16 @@ class ModelsList(BaseModel):
     responses={200: {"model": ModelsList }},
 )
 async def list_models(
-    base_model: Optional[BaseModelType] = Query(default=None, description="Base model"),
+    base_models: Optional[List[BaseModelType]] = Query(default=None, description="Base models to include"),
     model_type: Optional[ModelType] = Query(default=None, description="The type of model to get"),
 ) -> ModelsList:
     """Gets a list of models"""
-    models_raw = ApiDependencies.invoker.services.model_manager.list_models(base_model, model_type)
+    if base_models and len(base_models)>0:
+        models_raw = list()
+        for base_model in base_models:
+            models_raw.extend(ApiDependencies.invoker.services.model_manager.list_models(base_model, model_type))
+    else:
+        models_raw = ApiDependencies.invoker.services.model_manager.list_models(None, model_type)
     models = parse_obj_as(ModelsList, { "models": models_raw })
     return models
 
@@ -123,6 +129,7 @@ async def update_model(
     responses= {
         201: {"description" : "The model imported successfully"},
         404: {"description" : "The model could not be found"},
+        415: {"description" : "Unrecognized file/folder format"},
         424: {"description" : "The model appeared to import successfully, but could not be found in the model manager"},
         409: {"description" : "There is already a model corresponding to this path or repo_id"},
     },
@@ -149,7 +156,7 @@ async def import_model(
 
         if not info:
             logger.error("Import failed")
-            raise HTTPException(status_code=424)
+            raise HTTPException(status_code=415)
         
         logger.info(f'Successfully imported {location}, got {info}')
         model_raw = ApiDependencies.invoker.services.model_manager.list_model(
@@ -162,6 +169,9 @@ async def import_model(
     except ModelNotFoundException as e:
         logger.error(str(e))
         raise HTTPException(status_code=404, detail=str(e))
+    except InvalidModelException as e:
+        logger.error(str(e))
+        raise HTTPException(status_code=415)
     except ValueError as e:
         logger.error(str(e))
         raise HTTPException(status_code=409, detail=str(e))

invokeai/app/invocations/compel.py

@@ -1,8 +1,8 @@
-from typing import Literal, Optional, Union, List
+from typing import Literal, Optional, Union, List, Annotated
 from pydantic import BaseModel, Field
 import re
 import torch
-from compel import Compel
+from compel import Compel, ReturnedEmbeddingsType
 from compel.prompt_parser import (Blend, Conjunction,
                                   CrossAttentionControlSubstitute,
                                   FlattenedPrompt, Fragment)
@@ -14,6 +14,7 @@ from ...backend.stable_diffusion.diffusion import InvokeAIDiffuserComponent
 from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
                              InvocationConfig, InvocationContext)
 from .model import ClipField
+from dataclasses import dataclass
 
 
 class ConditioningField(BaseModel):
@@ -23,6 +24,34 @@ class ConditioningField(BaseModel):
     class Config:
         schema_extra = {"required": ["conditioning_name"]}
 
+@dataclass
+class BasicConditioningInfo:
+    #type: Literal["basic_conditioning"] = "basic_conditioning"
+    embeds: torch.Tensor
+    extra_conditioning: Optional[InvokeAIDiffuserComponent.ExtraConditioningInfo]
+    # weight: float
+    # mode: ConditioningAlgo
+
+@dataclass
+class SDXLConditioningInfo(BasicConditioningInfo):
+    #type: Literal["sdxl_conditioning"] = "sdxl_conditioning"
+    pooled_embeds: torch.Tensor
+    add_time_ids: torch.Tensor
+
+ConditioningInfoType = Annotated[
+    Union[BasicConditioningInfo, SDXLConditioningInfo],
+    Field(discriminator="type")
+]
+
+@dataclass
+class ConditioningFieldData:
+    conditionings: List[Union[BasicConditioningInfo, SDXLConditioningInfo]]
+    #unconditioned: Optional[torch.Tensor]
+
+#class ConditioningAlgo(str, Enum):
+#    Compose = "compose"
+#    ComposeEx = "compose_ex"
+#    PerpNeg = "perp_neg"
 
 class CompelOutput(BaseInvocationOutput):
     """Compel parser output"""
@@ -119,10 +148,17 @@ class CompelInvocation(BaseInvocation):
                 cross_attention_control_args=options.get(
                     "cross_attention_control", None),)
 
-        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
+        conditioning_data = ConditioningFieldData(
+            conditionings=[
+                BasicConditioningInfo(
+                    embeds=c,
+                    extra_conditioning=ec,
+                )
+            ]
+        )
 
-        # TODO: hacky but works ;D maybe rename latents somehow?
-        context.services.latents.save(conditioning_name, (c, ec))
+        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
+        context.services.latents.save(conditioning_name, conditioning_data)
 
         return CompelOutput(
             conditioning=ConditioningField(
@@ -130,6 +166,389 @@ class CompelInvocation(BaseInvocation):
             ),
         )
 
+class SDXLPromptInvocationBase:
+    def run_clip_raw(self, context, clip_field, prompt, get_pooled):
+        tokenizer_info = context.services.model_manager.get_model(
+            **clip_field.tokenizer.dict(),
+        )
+        text_encoder_info = context.services.model_manager.get_model(
+            **clip_field.text_encoder.dict(),
+        )
+
+        def _lora_loader():
+            for lora in clip_field.loras:
+                lora_info = context.services.model_manager.get_model(
+                    **lora.dict(exclude={"weight"}))
+                yield (lora_info.context.model, lora.weight)
+                del lora_info
+            return
+
+        #loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
+
+        ti_list = []
+        for trigger in re.findall(r"<[a-zA-Z0-9., _-]+>", prompt):
+            name = trigger[1:-1]
+            try:
+                ti_list.append(
+                    context.services.model_manager.get_model(
+                        model_name=name,
+                        base_model=clip_field.text_encoder.base_model,
+                        model_type=ModelType.TextualInversion,
+                    ).context.model
+                )
+            except ModelNotFoundException:
+                # print(e)
+                #import traceback
+                #print(traceback.format_exc())
+                print(f"Warn: trigger: \"{trigger}\" not found")
+
+        with ModelPatcher.apply_lora_text_encoder(text_encoder_info.context.model, _lora_loader()),\
+                ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (tokenizer, ti_manager),\
+                ModelPatcher.apply_clip_skip(text_encoder_info.context.model, clip_field.skipped_layers),\
+                text_encoder_info as text_encoder:
+
+            text_inputs = tokenizer(
+                prompt,
+                padding="max_length",
+                max_length=tokenizer.model_max_length,
+                truncation=True,
+                return_tensors="pt",
+            )
+            text_input_ids = text_inputs.input_ids
+            prompt_embeds = text_encoder(
+                text_input_ids.to(text_encoder.device),
+                output_hidden_states=True,
+            )
+            if get_pooled:
+                c_pooled = prompt_embeds[0]
+            else:
+                c_pooled = None
+            c = prompt_embeds.hidden_states[-2]
+
+        del tokenizer
+        del text_encoder
+        del tokenizer_info
+        del text_encoder_info
+
+        return c, c_pooled, None
+
+    def run_clip_compel(self, context, clip_field, prompt, get_pooled):
+        tokenizer_info = context.services.model_manager.get_model(
+            **clip_field.tokenizer.dict(),
+        )
+        text_encoder_info = context.services.model_manager.get_model(
+            **clip_field.text_encoder.dict(),
+        )
+
+        def _lora_loader():
+            for lora in clip_field.loras:
+                lora_info = context.services.model_manager.get_model(
+                    **lora.dict(exclude={"weight"}))
+                yield (lora_info.context.model, lora.weight)
+                del lora_info
+            return
+
+        #loras = [(context.services.model_manager.get_model(**lora.dict(exclude={"weight"})).context.model, lora.weight) for lora in self.clip.loras]
+
+        ti_list = []
+        for trigger in re.findall(r"<[a-zA-Z0-9., _-]+>", prompt):
+            name = trigger[1:-1]
+            try:
+                ti_list.append(
+                    context.services.model_manager.get_model(
+                        model_name=name,
+                        base_model=clip_field.text_encoder.base_model,
+                        model_type=ModelType.TextualInversion,
+                    ).context.model
+                )
+            except ModelNotFoundException:
+                # print(e)
+                #import traceback
+                #print(traceback.format_exc())
+                print(f"Warn: trigger: \"{trigger}\" not found")
+
+        with ModelPatcher.apply_lora_text_encoder(text_encoder_info.context.model, _lora_loader()),\
+                ModelPatcher.apply_ti(tokenizer_info.context.model, text_encoder_info.context.model, ti_list) as (tokenizer, ti_manager),\
+                ModelPatcher.apply_clip_skip(text_encoder_info.context.model, clip_field.skipped_layers),\
+                text_encoder_info as text_encoder:
+
+            compel = Compel(
+                tokenizer=tokenizer,
+                text_encoder=text_encoder,
+                textual_inversion_manager=ti_manager,
+                dtype_for_device_getter=torch_dtype,
+                truncate_long_prompts=True,  # TODO:
+                returned_embeddings_type=ReturnedEmbeddingsType.PENULTIMATE_HIDDEN_STATES_NON_NORMALIZED, # TODO: clip skip
+                requires_pooled=True,
+            )
+
+            conjunction = Compel.parse_prompt_string(prompt)
+
+            if context.services.configuration.log_tokenization:
+                # TODO: better logging for and syntax
+                for prompt_obj in conjunction.prompts:
+                    log_tokenization_for_prompt_object(prompt_obj, tokenizer)
+
+            # TODO: ask for optimizations? to not run text_encoder twice
+            c, options = compel.build_conditioning_tensor_for_conjunction(conjunction)
+            if get_pooled:
+                c_pooled = compel.conditioning_provider.get_pooled_embeddings([prompt])
+            else:
+                c_pooled = None
+
+            ec = InvokeAIDiffuserComponent.ExtraConditioningInfo(
+                tokens_count_including_eos_bos=get_max_token_count(tokenizer, conjunction),
+                cross_attention_control_args=options.get("cross_attention_control", None),
+            )
+
+        del tokenizer
+        del text_encoder
+        del tokenizer_info
+        del text_encoder_info
+
+        return c, c_pooled, ec
+
+class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
+    """Parse prompt using compel package to conditioning."""
+
+    type: Literal["sdxl_compel_prompt"] = "sdxl_compel_prompt"
+
+    prompt: str = Field(default="", description="Prompt")
+    style: str = Field(default="", description="Style prompt")
+    original_width: int = Field(1024, description="")
+    original_height: int = Field(1024, description="")
+    crop_top: int = Field(0, description="")
+    crop_left: int = Field(0, description="")
+    target_width: int = Field(1024, description="")
+    target_height: int = Field(1024, description="")
+    clip1: ClipField = Field(None, description="Clip to use")
+    clip2: ClipField = Field(None, description="Clip to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "title": "SDXL Prompt (Compel)",
+                "tags": ["prompt", "compel"],
+                "type_hints": {
+                    "model": "model"
+                }
+            },
+        }
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> CompelOutput:
+        c1, c1_pooled, ec1 = self.run_clip_compel(context, self.clip1, self.prompt, False)
+        if self.style.strip() == "":
+            c2, c2_pooled, ec2 = self.run_clip_compel(context, self.clip2, self.prompt, True)
+        else:
+            c2, c2_pooled, ec2 = self.run_clip_compel(context, self.clip2, self.style, True)
+
+        original_size = (self.original_height, self.original_width)
+        crop_coords = (self.crop_top, self.crop_left)
+        target_size = (self.target_height, self.target_width)
+
+        add_time_ids = torch.tensor([
+            original_size + crop_coords + target_size
+        ])
+
+        conditioning_data = ConditioningFieldData(
+            conditionings=[
+                SDXLConditioningInfo(
+                    embeds=torch.cat([c1, c2], dim=-1),
+                    pooled_embeds=c2_pooled,
+                    add_time_ids=add_time_ids,
+                    extra_conditioning=ec1,
+                )
+            ]
+        )
+
+        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
+        context.services.latents.save(conditioning_name, conditioning_data)
+
+        return CompelOutput(
+            conditioning=ConditioningField(
+                conditioning_name=conditioning_name,
+            ),
+        )
+
+class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
+    """Parse prompt using compel package to conditioning."""
+
+    type: Literal["sdxl_refiner_compel_prompt"] = "sdxl_refiner_compel_prompt"
+
+    style: str = Field(default="", description="Style prompt") # TODO: ?
+    original_width: int = Field(1024, description="")
+    original_height: int = Field(1024, description="")
+    crop_top: int = Field(0, description="")
+    crop_left: int = Field(0, description="")
+    aesthetic_score: float = Field(6.0, description="")
+    clip2: ClipField = Field(None, description="Clip to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "title": "SDXL Refiner Prompt (Compel)",
+                "tags": ["prompt", "compel"],
+                "type_hints": {
+                    "model": "model"
+                }
+            },
+        }
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> CompelOutput:
+        c2, c2_pooled, ec2 = self.run_clip_compel(context, self.clip2, self.style, True)
+
+        original_size = (self.original_height, self.original_width)
+        crop_coords = (self.crop_top, self.crop_left)
+
+        add_time_ids = torch.tensor([
+            original_size + crop_coords + (self.aesthetic_score,)
+        ])
+
+        conditioning_data = ConditioningFieldData(
+            conditionings=[
+                SDXLConditioningInfo(
+                    embeds=c2,
+                    pooled_embeds=c2_pooled,
+                    add_time_ids=add_time_ids,
+                    extra_conditioning=ec2, # or None
+                )
+            ]
+        )
+
+        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
+        context.services.latents.save(conditioning_name, conditioning_data)
+
+        return CompelOutput(
+            conditioning=ConditioningField(
+                conditioning_name=conditioning_name,
+            ),
+        )
+
+class SDXLRawPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
+    """Pass unmodified prompt to conditioning without compel processing."""
+
+    type: Literal["sdxl_raw_prompt"] = "sdxl_raw_prompt"
+
+    prompt: str = Field(default="", description="Prompt")
+    style: str = Field(default="", description="Style prompt")
+    original_width: int = Field(1024, description="")
+    original_height: int = Field(1024, description="")
+    crop_top: int = Field(0, description="")
+    crop_left: int = Field(0, description="")
+    target_width: int = Field(1024, description="")
+    target_height: int = Field(1024, description="")
+    clip1: ClipField = Field(None, description="Clip to use")
+    clip2: ClipField = Field(None, description="Clip to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "title": "SDXL Prompt (Raw)",
+                "tags": ["prompt", "compel"],
+                "type_hints": {
+                    "model": "model"
+                }
+            },
+        }
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> CompelOutput:
+        c1, c1_pooled, ec1 = self.run_clip_raw(context, self.clip1, self.prompt, False)
+        if self.style.strip() == "":
+            c2, c2_pooled, ec2 = self.run_clip_raw(context, self.clip2, self.prompt, True)
+        else:
+            c2, c2_pooled, ec2 = self.run_clip_raw(context, self.clip2, self.style, True)
+
+        original_size = (self.original_height, self.original_width)
+        crop_coords = (self.crop_top, self.crop_left)
+        target_size = (self.target_height, self.target_width)
+
+        add_time_ids = torch.tensor([
+            original_size + crop_coords + target_size
+        ])
+
+        conditioning_data = ConditioningFieldData(
+            conditionings=[
+                SDXLConditioningInfo(
+                    embeds=torch.cat([c1, c2], dim=-1),
+                    pooled_embeds=c2_pooled,
+                    add_time_ids=add_time_ids,
+                    extra_conditioning=ec1,
+                )
+            ]
+        )
+
+        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
+        context.services.latents.save(conditioning_name, conditioning_data)
+
+        return CompelOutput(
+            conditioning=ConditioningField(
+                conditioning_name=conditioning_name,
+            ),
+        )
+
+class SDXLRefinerRawPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
+    """Parse prompt using compel package to conditioning."""
+
+    type: Literal["sdxl_refiner_raw_prompt"] = "sdxl_refiner_raw_prompt"
+
+    style: str = Field(default="", description="Style prompt") # TODO: ?
+    original_width: int = Field(1024, description="")
+    original_height: int = Field(1024, description="")
+    crop_top: int = Field(0, description="")
+    crop_left: int = Field(0, description="")
+    aesthetic_score: float = Field(6.0, description="")
+    clip2: ClipField = Field(None, description="Clip to use")
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "title": "SDXL Refiner Prompt (Raw)",
+                "tags": ["prompt", "compel"],
+                "type_hints": {
+                    "model": "model"
+                }
+            },
+        }
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> CompelOutput:
+        c2, c2_pooled, ec2 = self.run_clip_raw(context, self.clip2, self.style, True)
+
+        original_size = (self.original_height, self.original_width)
+        crop_coords = (self.crop_top, self.crop_left)
+
+        add_time_ids = torch.tensor([
+            original_size + crop_coords + (self.aesthetic_score,)
+        ])
+
+        conditioning_data = ConditioningFieldData(
+            conditionings=[
+                SDXLConditioningInfo(
+                    embeds=c2,
+                    pooled_embeds=c2_pooled,
+                    add_time_ids=add_time_ids,
+                    extra_conditioning=ec2, # or None
+                )
+            ]
+        )
+
+        conditioning_name = f"{context.graph_execution_state_id}_{self.id}_conditioning"
+        context.services.latents.save(conditioning_name, conditioning_data)
+
+        return CompelOutput(
+            conditioning=ConditioningField(
+                conditioning_name=conditioning_name,
+            ),
+        )
+
+
 class ClipSkipInvocationOutput(BaseInvocationOutput):
     """Clip skip node output"""
     type: Literal["clip_skip_output"] = "clip_skip_output"

invokeai/app/invocations/latent.py

@@ -31,6 +31,13 @@ from .controlnet_image_processors import ControlField
 from .image import ImageOutput
 from .model import ModelInfo, UNetField, VaeField
 
+from diffusers.models.attention_processor import (
+    AttnProcessor2_0,
+    LoRAAttnProcessor2_0,
+    LoRAXFormersAttnProcessor,
+    XFormersAttnProcessor,
+)
+
 
 class LatentsField(BaseModel):
     """A latents field used for passing latents between invocations"""
@@ -161,12 +168,12 @@ class TextToLatentsInvocation(BaseInvocation):
         context: InvocationContext,
         scheduler,
     ) -> ConditioningData:
-        c, extra_conditioning_info = context.services.latents.get(
-            self.positive_conditioning.conditioning_name
-        )
-        uc, _ = context.services.latents.get(
-            self.negative_conditioning.conditioning_name
-        )
+        positive_cond_data = context.services.latents.get(self.positive_conditioning.conditioning_name)
+        c = positive_cond_data.conditionings[0].embeds
+        extra_conditioning_info = positive_cond_data.conditionings[0].extra_conditioning
+
+        negative_cond_data = context.services.latents.get(self.negative_conditioning.conditioning_name)
+        uc = negative_cond_data.conditionings[0].embeds
 
         conditioning_data = ConditioningData(
             unconditioned_embeddings=uc,
@@ -476,8 +483,8 @@ class LatentsToImageInvocation(BaseInvocation):
     tiled: bool = Field(
         default=False,
         description="Decode latents by overlaping tiles(less memory consumption)")
+    fp32: bool = Field(False, description="Decode in full precision")
     metadata: Optional[CoreMetadata] = Field(default=None, description="Optional core metadata to be written to the image")
-    
 
     # Schema customisation
     class Config(InvocationConfig):
@@ -496,6 +503,31 @@ class LatentsToImageInvocation(BaseInvocation):
         )
 
         with vae_info as vae:
+            if self.fp32:
+                vae.to(dtype=torch.float32)
+
+                use_torch_2_0_or_xformers = isinstance(
+                    vae.decoder.mid_block.attentions[0].processor,
+                    (
+                        AttnProcessor2_0,
+                        XFormersAttnProcessor,
+                        LoRAXFormersAttnProcessor,
+                        LoRAAttnProcessor2_0,
+                    ),
+                )
+                # if xformers or torch_2_0 is used attention block does not need
+                # to be in float32 which can save lots of memory
+                if use_torch_2_0_or_xformers:
+                    vae.post_quant_conv.to(latents.dtype)
+                    vae.decoder.conv_in.to(latents.dtype)
+                    vae.decoder.mid_block.to(latents.dtype)
+                else:
+                    latents = latents.float()
+
+            else:
+                vae.to(dtype=torch.float16)
+                latents = latents.half()
+
             if self.tiled or context.services.configuration.tiled_decode:
                 vae.enable_tiling()
             else:
@@ -619,6 +651,8 @@ class ImageToLatentsInvocation(BaseInvocation):
     tiled: bool = Field(
         default=False,
         description="Encode latents by overlaping tiles(less memory consumption)")
+    fp32: bool = Field(False, description="Decode in full precision")
+
 
     # Schema customisation
     class Config(InvocationConfig):
@@ -645,6 +679,32 @@ class ImageToLatentsInvocation(BaseInvocation):
             image_tensor = einops.rearrange(image_tensor, "c h w -> 1 c h w")
 
         with vae_info as vae:
+            orig_dtype = vae.dtype
+            if self.fp32:
+                vae.to(dtype=torch.float32)
+
+                use_torch_2_0_or_xformers = isinstance(
+                    vae.decoder.mid_block.attentions[0].processor,
+                    (
+                        AttnProcessor2_0,
+                        XFormersAttnProcessor,
+                        LoRAXFormersAttnProcessor,
+                        LoRAAttnProcessor2_0,
+                    ),
+                )
+                # if xformers or torch_2_0 is used attention block does not need
+                # to be in float32 which can save lots of memory
+                if use_torch_2_0_or_xformers:
+                    vae.post_quant_conv.to(orig_dtype)
+                    vae.decoder.conv_in.to(orig_dtype)
+                    vae.decoder.mid_block.to(orig_dtype)
+                #else:
+                #    latents = latents.float()
+
+            else:
+                vae.to(dtype=torch.float16)
+                #latents = latents.half()
+
             if self.tiled:
                 vae.enable_tiling()
             else:
@@ -659,6 +719,7 @@ class ImageToLatentsInvocation(BaseInvocation):
                 )  # FIXME: uses torch.randn. make reproducible!
 
             latents = 0.18215 * latents
+            latents = latents.to(dtype=orig_dtype)
 
         name = f"{context.graph_execution_state_id}__{self.id}"
         # context.services.latents.set(name, latents)

invokeai/app/invocations/model.py

@@ -33,7 +33,6 @@ class ClipField(BaseModel):
     skipped_layers: int = Field(description="Number of skipped layers in text_encoder")
     loras: List[LoraInfo] = Field(description="Loras to apply on model loading")
 
-
 class VaeField(BaseModel):
     # TODO: better naming?
     vae: ModelInfo = Field(description="Info to load vae submodel")
@@ -50,7 +49,6 @@ class ModelLoaderOutput(BaseInvocationOutput):
     vae: VaeField = Field(default=None, description="Vae submodel")
     # fmt: on
 
-
 class MainModelField(BaseModel):
     """Main model field"""
 
@@ -64,7 +62,6 @@ class LoRAModelField(BaseModel):
     model_name: str = Field(description="Name of the LoRA model")
     base_model: BaseModelType = Field(description="Base model")
 
-
 class MainModelLoaderInvocation(BaseInvocation):
     """Loads a main model, outputting its submodels."""
 
@@ -157,6 +154,22 @@ class MainModelLoaderInvocation(BaseInvocation):
                 loras=[],
                 skipped_layers=0,
             ),
+            clip2=ClipField(
+                tokenizer=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Tokenizer2,
+                ),
+                text_encoder=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.TextEncoder2,
+                ),
+                loras=[],
+                skipped_layers=0,
+            ),
             vae=VaeField(
                 vae=ModelInfo(
                     model_name=model_name,
@@ -167,7 +180,7 @@ class MainModelLoaderInvocation(BaseInvocation):
             ),
         )
 
-
+    
 class LoraLoaderOutput(BaseInvocationOutput):
     """Model loader output"""
 

invokeai/app/invocations/sdxl.py

@@ -0,0 +1,658 @@
+import torch
+import inspect
+from tqdm import tqdm
+from typing import List, Literal, Optional, Union
+
+from pydantic import Field, validator
+
+from ...backend.model_management import ModelType, SubModelType
+from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
+                             InvocationConfig, InvocationContext)
+
+from .model import UNetField, ClipField, VaeField, MainModelField, ModelInfo
+from .compel import ConditioningField
+from .latent import LatentsField, SAMPLER_NAME_VALUES, LatentsOutput, get_scheduler, build_latents_output
+
+class SDXLModelLoaderOutput(BaseInvocationOutput):
+    """SDXL base model loader output"""
+
+    # fmt: off
+    type: Literal["sdxl_model_loader_output"] = "sdxl_model_loader_output"
+
+    unet: UNetField = Field(default=None, description="UNet submodel")
+    clip: ClipField = Field(default=None, description="Tokenizer and text_encoder submodels")
+    clip2: ClipField = Field(default=None, description="Tokenizer and text_encoder submodels")
+    vae: VaeField = Field(default=None, description="Vae submodel")
+    # fmt: on
+
+class SDXLRefinerModelLoaderOutput(BaseInvocationOutput):
+    """SDXL refiner model loader output"""
+    # fmt: off
+    type: Literal["sdxl_refiner_model_loader_output"] = "sdxl_refiner_model_loader_output"
+    unet: UNetField = Field(default=None, description="UNet submodel")
+    clip2: ClipField = Field(default=None, description="Tokenizer and text_encoder submodels")
+    vae: VaeField = Field(default=None, description="Vae submodel")
+    # fmt: on
+    #fmt: on
+    
+class SDXLModelLoaderInvocation(BaseInvocation):
+    """Loads an sdxl base model, outputting its submodels."""
+
+    type: Literal["sdxl_model_loader"] = "sdxl_model_loader"
+
+    model: MainModelField = Field(description="The model to load")
+    # TODO: precision?
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "title": "SDXL Model Loader",
+                "tags": ["model", "loader", "sdxl"],
+                "type_hints": {"model": "model"},
+            },
+        }
+
+    def invoke(self, context: InvocationContext) -> SDXLModelLoaderOutput:
+        base_model = self.model.base_model
+        model_name = self.model.model_name
+        model_type = ModelType.Main
+
+        # TODO: not found exceptions
+        if not context.services.model_manager.model_exists(
+            model_name=model_name,
+            base_model=base_model,
+            model_type=model_type,
+        ):
+            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
+
+        return SDXLModelLoaderOutput(
+            unet=UNetField(
+                unet=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.UNet,
+                ),
+                scheduler=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Scheduler,
+                ),
+                loras=[],
+            ),
+            clip=ClipField(
+                tokenizer=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Tokenizer,
+                ),
+                text_encoder=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.TextEncoder,
+                ),
+                loras=[],
+                skipped_layers=0,
+            ),
+            clip2=ClipField(
+                tokenizer=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Tokenizer2,
+                ),
+                text_encoder=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.TextEncoder2,
+                ),
+                loras=[],
+                skipped_layers=0,
+            ),
+            vae=VaeField(
+                vae=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Vae,
+                ),
+            ),
+        )
+
+class SDXLRefinerModelLoaderInvocation(BaseInvocation):
+    """Loads an sdxl refiner model, outputting its submodels."""
+    type: Literal["sdxl_refiner_model_loader"] = "sdxl_refiner_model_loader"
+
+    model: MainModelField = Field(description="The model to load")
+    # TODO: precision?
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "title": "SDXL Refiner Model Loader",
+                "tags": ["model", "loader", "sdxl_refiner"],
+                "type_hints": {"model": "model"},
+            },
+        }
+
+    def invoke(self, context: InvocationContext) -> SDXLRefinerModelLoaderOutput:
+        base_model = self.model.base_model
+        model_name = self.model.model_name
+        model_type = ModelType.Main
+
+        # TODO: not found exceptions
+        if not context.services.model_manager.model_exists(
+            model_name=model_name,
+            base_model=base_model,
+            model_type=model_type,
+        ):
+            raise Exception(f"Unknown {base_model} {model_type} model: {model_name}")
+
+        return SDXLRefinerModelLoaderOutput(
+            unet=UNetField(
+                unet=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.UNet,
+                ),
+                scheduler=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Scheduler,
+                ),
+                loras=[],
+            ),
+            clip2=ClipField(
+                tokenizer=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Tokenizer2,
+                ),
+                text_encoder=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.TextEncoder2,
+                ),
+                loras=[],
+                skipped_layers=0,
+            ),
+            vae=VaeField(
+                vae=ModelInfo(
+                    model_name=model_name,
+                    base_model=base_model,
+                    model_type=model_type,
+                    submodel=SubModelType.Vae,
+                ),
+            ),
+        )
+    
+# Text to image
+class SDXLTextToLatentsInvocation(BaseInvocation):
+    """Generates latents from conditionings."""
+
+    type: Literal["t2l_sdxl"] = "t2l_sdxl"
+
+    # Inputs
+    # fmt: off
+    positive_conditioning: Optional[ConditioningField] = Field(description="Positive conditioning for generation")
+    negative_conditioning: Optional[ConditioningField] = Field(description="Negative conditioning for generation")
+    noise: Optional[LatentsField] = Field(description="The noise to use")
+    steps:       int = Field(default=10, gt=0, description="The number of steps to use to generate the image")
+    cfg_scale: Union[float, List[float]] = Field(default=7.5, ge=1, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
+    scheduler: SAMPLER_NAME_VALUES = Field(default="euler", description="The scheduler to use" )
+    unet: UNetField = Field(default=None, description="UNet submodel")
+    denoising_end: float = Field(default=1.0, gt=0, le=1, description="")
+    #control: Union[ControlField, list[ControlField]] = Field(default=None, description="The control to use")
+    #seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
+    #seamless_axes: str = Field(default="", description="The axes to tile the image on, 'x' and/or 'y'")
+    # fmt: on
+
+    @validator("cfg_scale")
+    def ge_one(cls, v):
+        """validate that all cfg_scale values are >= 1"""
+        if isinstance(v, list):
+            for i in v:
+                if i < 1:
+                    raise ValueError('cfg_scale must be greater than 1')
+        else:
+            if v < 1:
+                raise ValueError('cfg_scale must be greater than 1')
+        return v
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents"],
+                "type_hints": {
+                  "model": "model",
+                  # "cfg_scale": "float",
+                  "cfg_scale": "number"
+                }
+            },
+        }
+
+    # based on
+    # https://github.com/huggingface/diffusers/blob/3ebbaf7c96801271f9e6c21400033b6aa5ffcf29/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion.py#L375
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        latents = context.services.latents.get(self.noise.latents_name)
+
+        positive_cond_data = context.services.latents.get(self.positive_conditioning.conditioning_name)
+        prompt_embeds = positive_cond_data.conditionings[0].embeds
+        pooled_prompt_embeds = positive_cond_data.conditionings[0].pooled_embeds
+        add_time_ids = positive_cond_data.conditionings[0].add_time_ids
+
+        negative_cond_data = context.services.latents.get(self.negative_conditioning.conditioning_name)
+        negative_prompt_embeds = negative_cond_data.conditionings[0].embeds
+        negative_pooled_prompt_embeds = negative_cond_data.conditionings[0].pooled_embeds
+        add_neg_time_ids = negative_cond_data.conditionings[0].add_time_ids
+
+        scheduler = get_scheduler(
+            context=context,
+            scheduler_info=self.unet.scheduler,
+            scheduler_name=self.scheduler,
+        )
+
+        num_inference_steps = self.steps
+        scheduler.set_timesteps(num_inference_steps)
+        timesteps = scheduler.timesteps
+
+        latents = latents * scheduler.init_noise_sigma
+
+
+        unet_info = context.services.model_manager.get_model(
+            **self.unet.unet.dict()
+        )
+        do_classifier_free_guidance = True
+        cross_attention_kwargs = None
+        with unet_info as unet:
+
+            extra_step_kwargs = dict()
+            if "eta" in set(inspect.signature(scheduler.step).parameters.keys()):
+                extra_step_kwargs.update(
+                    eta=0.0,
+                )
+            if "generator" in set(inspect.signature(scheduler.step).parameters.keys()):
+                extra_step_kwargs.update(
+                    generator=torch.Generator(device=unet.device).manual_seed(0),
+                )
+
+            num_warmup_steps = len(timesteps) - self.steps * scheduler.order
+
+            # apply denoising_end
+            skipped_final_steps = int(round((1 - self.denoising_end) * self.steps))
+            num_inference_steps = num_inference_steps - skipped_final_steps
+            timesteps = timesteps[: num_warmup_steps + scheduler.order * num_inference_steps]
+
+            if not context.services.configuration.sequential_guidance:
+                prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds], dim=0)
+                add_text_embeds = torch.cat([negative_pooled_prompt_embeds, pooled_prompt_embeds], dim=0)
+                add_time_ids = torch.cat([add_neg_time_ids, add_time_ids], dim=0)
+
+                prompt_embeds = prompt_embeds.to(device=unet.device, dtype=unet.dtype)
+                add_text_embeds = add_text_embeds.to(device=unet.device, dtype=unet.dtype)
+                add_time_ids = add_time_ids.to(device=unet.device, dtype=unet.dtype)
+                latents = latents.to(device=unet.device, dtype=unet.dtype)
+
+                with tqdm(total=self.steps) as progress_bar:
+                    for i, t in enumerate(timesteps):
+                        # expand the latents if we are doing classifier free guidance
+                        latent_model_input = torch.cat([latents] * 2) if do_classifier_free_guidance else latents
+
+                        latent_model_input = scheduler.scale_model_input(latent_model_input, t)
+
+                        # predict the noise residual
+                        added_cond_kwargs = {"text_embeds": add_text_embeds, "time_ids": add_time_ids}
+                        noise_pred = unet(
+                            latent_model_input,
+                            t,
+                            encoder_hidden_states=prompt_embeds,
+                            cross_attention_kwargs=cross_attention_kwargs,
+                            added_cond_kwargs=added_cond_kwargs,
+                            return_dict=False,
+                        )[0]
+
+                        # perform guidance
+                        if do_classifier_free_guidance:
+                            noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
+                            noise_pred = noise_pred_uncond + self.cfg_scale * (noise_pred_text - noise_pred_uncond)
+                            #del noise_pred_uncond
+                            #del noise_pred_text
+
+                        #if do_classifier_free_guidance and guidance_rescale > 0.0:
+                        #    # Based on 3.4. in https://arxiv.org/pdf/2305.08891.pdf
+                        #    noise_pred = rescale_noise_cfg(noise_pred, noise_pred_text, guidance_rescale=guidance_rescale)
+
+                        # compute the previous noisy sample x_t -> x_t-1
+                        latents = scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
+
+                        # call the callback, if provided
+                        if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % scheduler.order == 0):
+                            progress_bar.update()
+                            #if callback is not None and i % callback_steps == 0:
+                            #    callback(i, t, latents)
+            else:
+                negative_pooled_prompt_embeds = negative_pooled_prompt_embeds.to(device=unet.device, dtype=unet.dtype)
+                negative_prompt_embeds = negative_prompt_embeds.to(device=unet.device, dtype=unet.dtype)
+                add_neg_time_ids = add_neg_time_ids.to(device=unet.device, dtype=unet.dtype)
+                pooled_prompt_embeds = pooled_prompt_embeds.to(device=unet.device, dtype=unet.dtype)
+                prompt_embeds = prompt_embeds.to(device=unet.device, dtype=unet.dtype)
+                add_time_ids = add_time_ids.to(device=unet.device, dtype=unet.dtype)
+                latents = latents.to(device=unet.device, dtype=unet.dtype)
+
+                with tqdm(total=self.steps) as progress_bar:
+                    for i, t in enumerate(timesteps):
+                        # expand the latents if we are doing classifier free guidance
+                        #latent_model_input = torch.cat([latents] * 2) if do_classifier_free_guidance else latents
+
+                        latent_model_input = scheduler.scale_model_input(latents, t)
+
+                        #import gc
+                        #gc.collect()
+                        #torch.cuda.empty_cache()
+
+                        # predict the noise residual
+
+                        added_cond_kwargs = {"text_embeds": negative_pooled_prompt_embeds, "time_ids": add_neg_time_ids}
+                        noise_pred_uncond = unet(
+                            latent_model_input,
+                            t,
+                            encoder_hidden_states=negative_prompt_embeds,
+                            cross_attention_kwargs=cross_attention_kwargs,
+                            added_cond_kwargs=added_cond_kwargs,
+                            return_dict=False,
+                        )[0]
+
+                        added_cond_kwargs = {"text_embeds": pooled_prompt_embeds, "time_ids": add_time_ids}
+                        noise_pred_text = unet(
+                            latent_model_input,
+                            t,
+                            encoder_hidden_states=prompt_embeds,
+                            cross_attention_kwargs=cross_attention_kwargs,
+                            added_cond_kwargs=added_cond_kwargs,
+                            return_dict=False,
+                        )[0]
+
+                        # perform guidance
+                        noise_pred = noise_pred_uncond + self.cfg_scale * (noise_pred_text - noise_pred_uncond)
+
+                        #del noise_pred_text
+                        #del noise_pred_uncond
+                        #import gc
+                        #gc.collect()
+                        #torch.cuda.empty_cache()
+
+                        #if do_classifier_free_guidance and guidance_rescale > 0.0:
+                        #    # Based on 3.4. in https://arxiv.org/pdf/2305.08891.pdf
+                        #    noise_pred = rescale_noise_cfg(noise_pred, noise_pred_text, guidance_rescale=guidance_rescale)
+
+                        # compute the previous noisy sample x_t -> x_t-1
+                        latents = scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
+
+                        #del noise_pred
+                        #import gc
+                        #gc.collect()
+                        #torch.cuda.empty_cache()
+
+                        # call the callback, if provided
+                        if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % scheduler.order == 0):
+                            progress_bar.update()
+                            #if callback is not None and i % callback_steps == 0:
+                            #    callback(i, t, latents)
+
+
+
+        #################
+
+        torch.cuda.empty_cache()
+
+        name = f'{context.graph_execution_state_id}__{self.id}'
+        context.services.latents.save(name, latents)
+        return build_latents_output(latents_name=name, latents=latents)
+
+class SDXLLatentsToLatentsInvocation(BaseInvocation):
+    """Generates latents from conditionings."""
+
+    type: Literal["l2l_sdxl"] = "l2l_sdxl"
+
+    # Inputs
+    # fmt: off
+    positive_conditioning: Optional[ConditioningField] = Field(description="Positive conditioning for generation")
+    negative_conditioning: Optional[ConditioningField] = Field(description="Negative conditioning for generation")
+    noise: Optional[LatentsField] = Field(description="The noise to use")
+    steps:       int = Field(default=10, gt=0, description="The number of steps to use to generate the image")
+    cfg_scale: Union[float, List[float]] = Field(default=7.5, ge=1, description="The Classifier-Free Guidance, higher values may result in a result closer to the prompt", )
+    scheduler: SAMPLER_NAME_VALUES = Field(default="euler", description="The scheduler to use" )
+    unet: UNetField = Field(default=None, description="UNet submodel")
+    latents: Optional[LatentsField] = Field(description="Initial latents")
+
+    denoising_start: float = Field(default=0.0, ge=0, lt=1, description="")
+    denoising_end: float = Field(default=1.0, gt=0, le=1, description="")
+
+    #control: Union[ControlField, list[ControlField]] = Field(default=None, description="The control to use")
+    #seamless:   bool = Field(default=False, description="Whether or not to generate an image that can tile without seams", )
+    #seamless_axes: str = Field(default="", description="The axes to tile the image on, 'x' and/or 'y'")
+    # fmt: on
+
+    @validator("cfg_scale")
+    def ge_one(cls, v):
+        """validate that all cfg_scale values are >= 1"""
+        if isinstance(v, list):
+            for i in v:
+                if i < 1:
+                    raise ValueError('cfg_scale must be greater than 1')
+        else:
+            if v < 1:
+                raise ValueError('cfg_scale must be greater than 1')
+        return v
+
+    # Schema customisation
+    class Config(InvocationConfig):
+        schema_extra = {
+            "ui": {
+                "tags": ["latents"],
+                "type_hints": {
+                  "model": "model",
+                  # "cfg_scale": "float",
+                  "cfg_scale": "number"
+                }
+            },
+        }
+
+    # based on
+    # https://github.com/huggingface/diffusers/blob/3ebbaf7c96801271f9e6c21400033b6aa5ffcf29/src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion.py#L375
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        latents = context.services.latents.get(self.latents.latents_name)
+
+        positive_cond_data = context.services.latents.get(self.positive_conditioning.conditioning_name)
+        prompt_embeds = positive_cond_data.conditionings[0].embeds
+        pooled_prompt_embeds = positive_cond_data.conditionings[0].pooled_embeds
+        add_time_ids = positive_cond_data.conditionings[0].add_time_ids
+
+        negative_cond_data = context.services.latents.get(self.negative_conditioning.conditioning_name)
+        negative_prompt_embeds = negative_cond_data.conditionings[0].embeds
+        negative_pooled_prompt_embeds = negative_cond_data.conditionings[0].pooled_embeds
+        add_neg_time_ids = negative_cond_data.conditionings[0].add_time_ids
+
+        scheduler = get_scheduler(
+            context=context,
+            scheduler_info=self.unet.scheduler,
+            scheduler_name=self.scheduler,
+        )
+
+        # apply denoising_start
+        num_inference_steps = self.steps
+        scheduler.set_timesteps(num_inference_steps)
+
+        t_start = int(round(self.denoising_start * num_inference_steps))
+        timesteps = scheduler.timesteps[t_start * scheduler.order:]
+        num_inference_steps = num_inference_steps - t_start
+
+        # apply noise(if provided)
+        if self.noise is not None:
+            noise = context.services.latents.get(self.noise.latents_name)
+            latents = scheduler.add_noise(latents, noise, timesteps[:1])
+            del noise
+
+        unet_info = context.services.model_manager.get_model(
+            **self.unet.unet.dict()
+        )
+        do_classifier_free_guidance = True
+        cross_attention_kwargs = None
+        with unet_info as unet:
+
+            # apply scheduler extra args
+            extra_step_kwargs = dict()
+            if "eta" in set(inspect.signature(scheduler.step).parameters.keys()):
+                extra_step_kwargs.update(
+                    eta=0.0,
+                )
+            if "generator" in set(inspect.signature(scheduler.step).parameters.keys()):
+                extra_step_kwargs.update(
+                    generator=torch.Generator(device=unet.device).manual_seed(0),
+                )
+
+            num_warmup_steps = max(len(timesteps) - num_inference_steps * scheduler.order, 0)
+
+            # apply denoising_end
+            skipped_final_steps = int(round((1 - self.denoising_end) * self.steps))
+            num_inference_steps = num_inference_steps - skipped_final_steps
+            timesteps = timesteps[: num_warmup_steps + scheduler.order * num_inference_steps]
+
+            if not context.services.configuration.sequential_guidance:
+                prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds], dim=0)
+                add_text_embeds = torch.cat([negative_pooled_prompt_embeds, pooled_prompt_embeds], dim=0)
+                add_time_ids = torch.cat([add_neg_time_ids, add_time_ids], dim=0)
+
+                prompt_embeds = prompt_embeds.to(device=unet.device, dtype=unet.dtype)
+                add_text_embeds = add_text_embeds.to(device=unet.device, dtype=unet.dtype)
+                add_time_ids = add_time_ids.to(device=unet.device, dtype=unet.dtype)
+                latents = latents.to(device=unet.device, dtype=unet.dtype)
+
+                with tqdm(total=num_inference_steps) as progress_bar:
+                    for i, t in enumerate(timesteps):
+                        # expand the latents if we are doing classifier free guidance
+                        latent_model_input = torch.cat([latents] * 2) if do_classifier_free_guidance else latents
+
+                        latent_model_input = scheduler.scale_model_input(latent_model_input, t)
+
+                        # predict the noise residual
+                        added_cond_kwargs = {"text_embeds": add_text_embeds, "time_ids": add_time_ids}
+                        noise_pred = unet(
+                            latent_model_input,
+                            t,
+                            encoder_hidden_states=prompt_embeds,
+                            cross_attention_kwargs=cross_attention_kwargs,
+                            added_cond_kwargs=added_cond_kwargs,
+                            return_dict=False,
+                        )[0]
+
+                        # perform guidance
+                        if do_classifier_free_guidance:
+                            noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
+                            noise_pred = noise_pred_uncond + self.cfg_scale * (noise_pred_text - noise_pred_uncond)
+                            #del noise_pred_uncond
+                            #del noise_pred_text
+
+                        #if do_classifier_free_guidance and guidance_rescale > 0.0:
+                        #    # Based on 3.4. in https://arxiv.org/pdf/2305.08891.pdf
+                        #    noise_pred = rescale_noise_cfg(noise_pred, noise_pred_text, guidance_rescale=guidance_rescale)
+
+                        # compute the previous noisy sample x_t -> x_t-1
+                        latents = scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
+
+                        # call the callback, if provided
+                        if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % scheduler.order == 0):
+                            progress_bar.update()
+                            #if callback is not None and i % callback_steps == 0:
+                            #    callback(i, t, latents)
+            else:
+                negative_pooled_prompt_embeds = negative_pooled_prompt_embeds.to(device=unet.device, dtype=unet.dtype)
+                negative_prompt_embeds = negative_prompt_embeds.to(device=unet.device, dtype=unet.dtype)
+                add_neg_time_ids = add_neg_time_ids.to(device=unet.device, dtype=unet.dtype)
+                pooled_prompt_embeds = pooled_prompt_embeds.to(device=unet.device, dtype=unet.dtype)
+                prompt_embeds = prompt_embeds.to(device=unet.device, dtype=unet.dtype)
+                add_time_ids = add_time_ids.to(device=unet.device, dtype=unet.dtype)
+                latents = latents.to(device=unet.device, dtype=unet.dtype)
+
+                with tqdm(total=num_inference_steps) as progress_bar:
+                    for i, t in enumerate(timesteps):
+                        # expand the latents if we are doing classifier free guidance
+                        #latent_model_input = torch.cat([latents] * 2) if do_classifier_free_guidance else latents
+
+                        latent_model_input = scheduler.scale_model_input(latents, t)
+
+                        #import gc
+                        #gc.collect()
+                        #torch.cuda.empty_cache()
+
+                        # predict the noise residual
+
+                        added_cond_kwargs = {"text_embeds": negative_pooled_prompt_embeds, "time_ids": add_time_ids}
+                        noise_pred_uncond = unet(
+                            latent_model_input,
+                            t,
+                            encoder_hidden_states=negative_prompt_embeds,
+                            cross_attention_kwargs=cross_attention_kwargs,
+                            added_cond_kwargs=added_cond_kwargs,
+                            return_dict=False,
+                        )[0]
+
+                        added_cond_kwargs = {"text_embeds": pooled_prompt_embeds, "time_ids": add_time_ids}
+                        noise_pred_text = unet(
+                            latent_model_input,
+                            t,
+                            encoder_hidden_states=prompt_embeds,
+                            cross_attention_kwargs=cross_attention_kwargs,
+                            added_cond_kwargs=added_cond_kwargs,
+                            return_dict=False,
+                        )[0]
+
+                        # perform guidance
+                        noise_pred = noise_pred_uncond + self.cfg_scale * (noise_pred_text - noise_pred_uncond)
+
+                        #del noise_pred_text
+                        #del noise_pred_uncond
+                        #import gc
+                        #gc.collect()
+                        #torch.cuda.empty_cache()
+
+                        #if do_classifier_free_guidance and guidance_rescale > 0.0:
+                        #    # Based on 3.4. in https://arxiv.org/pdf/2305.08891.pdf
+                        #    noise_pred = rescale_noise_cfg(noise_pred, noise_pred_text, guidance_rescale=guidance_rescale)
+
+                        # compute the previous noisy sample x_t -> x_t-1
+                        latents = scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0]
+
+                        #del noise_pred
+                        #import gc
+                        #gc.collect()
+                        #torch.cuda.empty_cache()
+
+                        # call the callback, if provided
+                        if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % scheduler.order == 0):
+                            progress_bar.update()
+                            #if callback is not None and i % callback_steps == 0:
+                            #    callback(i, t, latents)
+
+
+
+        #################
+
+        torch.cuda.empty_cache()
+
+        name = f'{context.graph_execution_state_id}__{self.id}'
+        context.services.latents.save(name, latents)
+        return build_latents_output(latents_name=name, latents=latents)

invokeai/backend/install/model_install_backend.py

@@ -212,7 +212,7 @@ class ModelInstall(object):
                                     {'config.json','model_index.json','learned_embeds.bin','pytorch_lora_weights.bin'}
                                     ]
                                    ):
-            models_installed.update(self._install_path(path))
+            models_installed.update({str(model_path_id_or_url): self._install_path(path)})
 
         # recursive scan
         elif path.is_dir():

invokeai/backend/model_management/model_probe.py

@@ -12,6 +12,7 @@ from picklescan.scanner import scan_file_path
 from .models import (
     BaseModelType, ModelType, ModelVariantType,
     SchedulerPredictionType, SilenceWarnings,
+    InvalidModelException
 )
 from .models.base import read_checkpoint_meta
 
@@ -38,6 +39,8 @@ class ModelProbe(object):
 
     CLASS2TYPE = {
         'StableDiffusionPipeline' : ModelType.Main,
+        'StableDiffusionXLPipeline' : ModelType.Main,
+        'StableDiffusionXLImg2ImgPipeline' : ModelType.Main,
         'AutoencoderKL' : ModelType.Vae,
         'ControlNetModel' : ModelType.ControlNet,
     }
@@ -59,7 +62,7 @@ class ModelProbe(object):
         elif isinstance(model,(dict,ModelMixin,ConfigMixin)):
             return cls.probe(model_path=None, model=model, prediction_type_helper=prediction_type_helper)
         else:
-            raise ValueError("model parameter {model} is neither a Path, nor a model")
+            raise InvalidModelException("model parameter {model} is neither a Path, nor a model")
 
     @classmethod
     def probe(cls,
@@ -99,9 +102,10 @@ class ModelProbe(object):
                 upcast_attention = (base_type==BaseModelType.StableDiffusion2 \
                                      and prediction_type==SchedulerPredictionType.VPrediction),
                 format = format,
-                image_size = 768 if (base_type==BaseModelType.StableDiffusion2 \
-                                     and prediction_type==SchedulerPredictionType.VPrediction \
-                                     ) else 512,
+                image_size = 1024 if (base_type in {BaseModelType.StableDiffusionXL,BaseModelType.StableDiffusionXLRefiner}) else \
+                              768 if (base_type==BaseModelType.StableDiffusion2 \
+                                     and prediction_type==SchedulerPredictionType.VPrediction ) else \
+                              512
             )
         except Exception:
             raise
@@ -138,7 +142,7 @@ class ModelProbe(object):
             if len(ckpt) < 10 and all(isinstance(v, torch.Tensor) for v in ckpt.values()):
                 return ModelType.TextualInversion
         
-        raise ValueError(f"Unable to determine model type for {model_path}")
+        raise InvalidModelException(f"Unable to determine model type for {model_path}")
 
     @classmethod
     def get_model_type_from_folder(cls, folder_path: Path, model: ModelMixin)->ModelType:
@@ -168,7 +172,7 @@ class ModelProbe(object):
             return type
 
         # give up
-        raise ValueError(f"Unable to determine model type for {folder_path}")
+        raise InvalidModelException(f"Unable to determine model type for {folder_path}")
 
     @classmethod
     def _scan_and_load_checkpoint(cls,model_path: Path)->dict:
@@ -237,7 +241,7 @@ class CheckpointProbeBase(ProbeBase):
         elif in_channels == 4:
             return ModelVariantType.Normal
         else:
-            raise ValueError(f"Cannot determine variant type (in_channels={in_channels}) at {self.checkpoint_path}")
+            raise InvalidModelException(f"Cannot determine variant type (in_channels={in_channels}) at {self.checkpoint_path}")
 
 class PipelineCheckpointProbe(CheckpointProbeBase):
     def get_base_type(self)->BaseModelType:
@@ -248,7 +252,10 @@ class PipelineCheckpointProbe(CheckpointProbeBase):
             return BaseModelType.StableDiffusion1
         if key_name in state_dict and state_dict[key_name].shape[-1] == 1024:
             return BaseModelType.StableDiffusion2
-        raise ValueError("Cannot determine base type")
+        # TODO: Verify that this is correct! Need an XL checkpoint file for this.
+        if key_name in state_dict and state_dict[key_name].shape[-1] == 2048:
+            return BaseModelType.StableDiffusionXL
+        raise InvalidModelException("Cannot determine base type")
 
     def get_scheduler_prediction_type(self)->SchedulerPredictionType:
         type = self.get_base_type()
@@ -329,7 +336,7 @@ class ControlNetCheckpointProbe(CheckpointProbeBase):
                 return BaseModelType.StableDiffusion2
             elif self.checkpoint_path and self.helper:
                 return self.helper(self.checkpoint_path)
-        raise ValueError("Unable to determine base type for {self.checkpoint_path}")
+        raise InvalidModelException("Unable to determine base type for {self.checkpoint_path}")
 
 ########################################################
 # classes for probing folders
@@ -360,8 +367,12 @@ class PipelineFolderProbe(FolderProbeBase):
             return BaseModelType.StableDiffusion1  
         elif unet_conf['cross_attention_dim'] == 1024:
             return BaseModelType.StableDiffusion2
+        elif unet_conf['cross_attention_dim'] == 1280:
+            return BaseModelType.StableDiffusionXLRefiner
+        elif unet_conf['cross_attention_dim'] == 2048:
+            return BaseModelType.StableDiffusionXL
         else:
-            raise ValueError(f'Unknown base model for {self.folder_path}')
+            raise InvalidModelException(f'Unknown base model for {self.folder_path}')
 
     def get_scheduler_prediction_type(self)->SchedulerPredictionType:
         if self.model:
@@ -418,7 +429,7 @@ class ControlNetFolderProbe(FolderProbeBase):
     def get_base_type(self)->BaseModelType:
         config_file = self.folder_path / 'config.json'
         if not config_file.exists():
-            raise ValueError(f"Cannot determine base type for {self.folder_path}")
+            raise InvalidModelException(f"Cannot determine base type for {self.folder_path}")
         with open(config_file,'r') as file:
             config = json.load(file)
         # no obvious way to distinguish between sd2-base and sd2-768
@@ -435,7 +446,7 @@ class LoRAFolderProbe(FolderProbeBase):
                 model_file = base_file
                 break
         if not model_file:
-            raise ValueError('Unknown LoRA format encountered')
+            raise InvalidModelException('Unknown LoRA format encountered')
         return LoRACheckpointProbe(model_file,None).get_base_type()
 
 ############## register probe classes ######

invokeai/backend/model_management/models/__init__.py

@@ -4,6 +4,7 @@ from pydantic import BaseModel
 from typing import Literal, get_origin
 from .base import BaseModelType, ModelType, SubModelType, ModelBase, ModelConfigBase, ModelVariantType, SchedulerPredictionType, ModelError, SilenceWarnings, ModelNotFoundException, InvalidModelException
 from .stable_diffusion import StableDiffusion1Model, StableDiffusion2Model
+from .sdxl import StableDiffusionXLModel
 from .vae import VaeModel
 from .lora import LoRAModel
 from .controlnet import ControlNetModel # TODO:
@@ -24,6 +25,22 @@ MODEL_CLASSES = {
         ModelType.ControlNet: ControlNetModel,
         ModelType.TextualInversion: TextualInversionModel,
     },
+    BaseModelType.StableDiffusionXL: {
+        ModelType.Main: StableDiffusionXLModel,
+        ModelType.Vae: VaeModel,
+        # will not work until support written
+        ModelType.Lora: LoRAModel,
+        ModelType.ControlNet: ControlNetModel,
+        ModelType.TextualInversion: TextualInversionModel,
+    },
+    BaseModelType.StableDiffusionXLRefiner: {
+        ModelType.Main: StableDiffusionXLModel,
+        ModelType.Vae: VaeModel,
+        # will not work until support written
+        ModelType.Lora: LoRAModel,
+        ModelType.ControlNet: ControlNetModel,
+        ModelType.TextualInversion: TextualInversionModel,
+    },
     #BaseModelType.Kandinsky2_1: {
     #    ModelType.Main: Kandinsky2_1Model,
     #    ModelType.MoVQ: MoVQModel,

invokeai/backend/model_management/models/base.py

@@ -24,6 +24,8 @@ class ModelNotFoundException(Exception):
 class BaseModelType(str, Enum):
     StableDiffusion1 = "sd-1"
     StableDiffusion2 = "sd-2"
+    StableDiffusionXL = "sdxl"
+    StableDiffusionXLRefiner = "sdxl-refiner"
     #Kandinsky2_1 = "kandinsky-2.1"
 
 class ModelType(str, Enum):
@@ -36,7 +38,9 @@ class ModelType(str, Enum):
 class SubModelType(str, Enum):
     UNet = "unet"
     TextEncoder = "text_encoder"
+    TextEncoder2 = "text_encoder_2"
     Tokenizer = "tokenizer"
+    Tokenizer2 = "tokenizer_2"
     Vae = "vae"
     Scheduler = "scheduler"
     SafetyChecker = "safety_checker"

invokeai/backend/model_management/models/sdxl.py

@@ -0,0 +1,114 @@
+import os
+import json
+from enum import Enum
+from pydantic import Field
+from typing import Literal, Optional
+from .base import (
+    ModelConfigBase,
+    BaseModelType,
+    ModelType,
+    ModelVariantType,
+    DiffusersModel,
+    read_checkpoint_meta,
+    classproperty,
+)
+from omegaconf import OmegaConf
+
+class StableDiffusionXLModelFormat(str, Enum):
+    Checkpoint = "checkpoint"
+    Diffusers = "diffusers"
+    
+class StableDiffusionXLModel(DiffusersModel):
+
+    # TODO: check that configs overwriten properly
+    class DiffusersConfig(ModelConfigBase):
+        model_format: Literal[StableDiffusionXLModelFormat.Diffusers]
+        vae: Optional[str] = Field(None)
+        variant: ModelVariantType
+
+    class CheckpointConfig(ModelConfigBase):
+        model_format: Literal[StableDiffusionXLModelFormat.Checkpoint]
+        vae: Optional[str] = Field(None)
+        config: str
+        variant: ModelVariantType
+
+    def __init__(self, model_path: str, base_model: BaseModelType, model_type: ModelType):
+        assert base_model in {BaseModelType.StableDiffusionXL, BaseModelType.StableDiffusionXLRefiner}
+        assert model_type == ModelType.Main
+        super().__init__(
+            model_path=model_path,
+            base_model=BaseModelType.StableDiffusionXL,
+            model_type=ModelType.Main,
+        )
+
+    @classmethod
+    def probe_config(cls, path: str, **kwargs):
+        model_format = cls.detect_format(path)
+        ckpt_config_path = kwargs.get("config", None)
+        if model_format == StableDiffusionXLModelFormat.Checkpoint:
+            if ckpt_config_path:
+                ckpt_config = OmegaConf.load(ckpt_config_path)
+                ckpt_config["model"]["params"]["unet_config"]["params"]["in_channels"]
+
+            else:
+                checkpoint = read_checkpoint_meta(path)
+                checkpoint = checkpoint.get('state_dict', checkpoint)
+                in_channels = checkpoint["model.diffusion_model.input_blocks.0.0.weight"].shape[1]
+
+        elif model_format == StableDiffusionXLModelFormat.Diffusers:
+            unet_config_path = os.path.join(path, "unet", "config.json")
+            if os.path.exists(unet_config_path):
+                with open(unet_config_path, "r") as f:
+                    unet_config = json.loads(f.read())
+                in_channels = unet_config['in_channels']
+
+            else:
+                raise Exception("Not supported stable diffusion diffusers format(possibly onnx?)")
+
+        else:
+            raise NotImplementedError(f"Unknown stable diffusion 2.* format: {model_format}")
+
+        if in_channels == 9:
+            variant = ModelVariantType.Inpaint
+        elif in_channels == 5:
+            variant = ModelVariantType.Depth
+        elif in_channels == 4:
+            variant = ModelVariantType.Normal
+        else:
+            raise Exception("Unkown stable diffusion 2.* model format")
+
+        if ckpt_config_path is None:
+            # TO DO: implement picking
+            pass
+        
+        return cls.create_config(
+            path=path,
+            model_format=model_format,
+
+            config=ckpt_config_path,
+            variant=variant,
+        )
+
+    @classproperty
+    def save_to_config(cls) -> bool:
+        return True
+
+    @classmethod
+    def detect_format(cls, model_path: str):
+        if os.path.isdir(model_path):
+            return StableDiffusionXLModelFormat.Diffusers
+        else:
+            return StableDiffusionXLModelFormat.Checkpoint
+
+    @classmethod
+    def convert_if_required(
+        cls,
+        model_path: str,
+        output_path: str,
+        config: ModelConfigBase,
+        base_model: BaseModelType,
+    ) -> str:
+        if isinstance(config, cls.CheckpointConfig):
+            raise NotImplementedError('conversion of SDXL checkpoint models to diffusers format is not yet supported')
+        else:
+            return model_path

invokeai/backend/model_management/models/stable_diffusion.py

@@ -5,14 +5,11 @@ from pydantic import Field
 from pathlib import Path
 from typing import Literal, Optional, Union
 from .base import (
-    ModelBase,
     ModelConfigBase,
     BaseModelType,
     ModelType,
-    SubModelType,
     ModelVariantType,
     DiffusersModel,
-    SchedulerPredictionType,
     SilenceWarnings,
     read_checkpoint_meta,
     classproperty,
@@ -248,6 +245,12 @@ def _select_ckpt_config(version: BaseModelType, variant: ModelVariantType):
             ModelVariantType.Normal: "v2-inference-v.yaml", # best guess, as we can't differentiate with base(512)
             ModelVariantType.Inpaint: "v2-inpainting-inference.yaml",
             ModelVariantType.Depth: "v2-midas-inference.yaml",
+        },
+        # note that these .yaml files don't yet exist!
+        BaseModelType.StableDiffusionXL: {
+            ModelVariantType.Normal: "xl-inference-v.yaml",
+            ModelVariantType.Inpaint: "xl-inpainting-inference.yaml",
+            ModelVariantType.Depth: "xl-midas-inference.yaml",
         }
     }
 
@@ -263,6 +266,7 @@ def _select_ckpt_config(version: BaseModelType, variant: ModelVariantType):
 
 
 # TODO: rework
+# Note that convert_ckpt_to_diffuses does not currently support conversion of SDXL models
 def _convert_ckpt_and_cache(
     version: BaseModelType,
     model_config: Union[StableDiffusion1Model.CheckpointConfig, StableDiffusion2Model.CheckpointConfig],

invokeai/configs/INITIAL_MODELS.yaml

@@ -1,4 +1,10 @@
 # This file predefines a few models that the user may want to install.
+sd-1/main/stable-diffusion-xdl-base:
+   description: Stable Diffusion XL base model - NOT YET RELEASED!! (70 GB)
+   repo_id: stabilityai/stable-diffusion-xl-base
+sd-1/main/stable-diffusion-xdl-refiner:
+   description: Stable Diffusion XL refiner model - NOT YET RELEASED!! (60 GB)
+   repo_id: stabilityai/stable-diffusion-xl-refiner
 sd-1/main/stable-diffusion-v1-5:
    description: Stable Diffusion version 1.5 diffusers model (4.27 GB)
    repo_id: runwayml/stable-diffusion-v1-5

invokeai/frontend/web/src/features/parameters/components/Parameters/Advanced/ParamClipSkip.tsx

@@ -14,6 +14,14 @@ export const clipSkipMap = {
     maxClip: 24,
     markers: [0, 1, 2, 3, 5, 10, 15, 20, 24],
   },
+  sdxl: {
+    maxClip: 24,
+    markers: [0, 1, 2, 3, 5, 10, 15, 20, 24],
+  },
+  'sdxl-refiner': {
+    maxClip: 24,
+    markers: [0, 1, 2, 3, 5, 10, 15, 20, 24],
+  },
 };
 
 export default function ParamClipSkip() {

invokeai/frontend/web/src/features/parameters/types/constants.ts

@@ -1,4 +1,6 @@
 export const MODEL_TYPE_MAP = {
   'sd-1': 'Stable Diffusion 1.x',
   'sd-2': 'Stable Diffusion 2.x',
+  sdxl: 'Stable Diffusion XL',
+  'sdxl-refiner': 'Stable Diffusion XL Refiner',
 };

invokeai/frontend/web/src/features/parameters/types/parameterSchemas.ts

@@ -126,7 +126,7 @@ export type HeightParam = z.infer<typeof zHeight>;
 export const isValidHeight = (val: unknown): val is HeightParam =>
   zHeight.safeParse(val).success;
 
-const zBaseModel = z.enum(['sd-1', 'sd-2']);
+const zBaseModel = z.enum(['sd-1', 'sd-2', 'sdxl', 'sdxl-refiner']);
 
 export type BaseModelParam = z.infer<typeof zBaseModel>;
 

invokeai/frontend/web/src/features/ui/components/tabs/ModelManager/subpanels/AddModelsPanel/ScanAdvancedAddModels.tsx

@@ -19,18 +19,16 @@ export default function ScanAdvancedAddModels() {
   const [advancedAddMode, setAdvancedAddMode] =
     useState<ManualAddMode>('diffusers');
 
-  const [isCheckpoint, setIsCheckpoint] = useState(
-    advancedAddScanModel &&
-      ['.ckpt', '.safetensors', '.pth', '.pt'].some((ext) =>
-        advancedAddScanModel.endsWith(ext)
-      )
-  );
+  const [isCheckpoint, setIsCheckpoint] = useState<boolean>(true);
 
   useEffect(() => {
-    isCheckpoint
+    advancedAddScanModel &&
+    ['.ckpt', '.safetensors', '.pth', '.pt'].some((ext) =>
+      advancedAddScanModel.endsWith(ext)
+    )
       ? setAdvancedAddMode('checkpoint')
       : setAdvancedAddMode('diffusers');
-  }, [setAdvancedAddMode, isCheckpoint]);
+  }, [advancedAddScanModel, setAdvancedAddMode, isCheckpoint]);
 
   const dispatch = useAppDispatch();
 

invokeai/frontend/web/src/features/ui/components/tabs/ModelManager/subpanels/MergeModelsPanel.tsx

@@ -58,10 +58,10 @@ export default function MergeModelsPanel() {
   }, [sd1DiffusersModels, sd2DiffusersModels]);
 
   const [modelOne, setModelOne] = useState<string | null>(
-    Object.keys(modelsMap[baseModel])[0]
+    Object.keys(modelsMap[baseModel as keyof typeof modelsMap])[0]
   );
   const [modelTwo, setModelTwo] = useState<string | null>(
-    Object.keys(modelsMap[baseModel])[1]
+    Object.keys(modelsMap[baseModel as keyof typeof modelsMap])[1]
   );
 
   const [modelThree, setModelThree] = useState<string | null>(null);
@@ -89,9 +89,9 @@ export default function MergeModelsPanel() {
     modelsMap[baseModel as keyof typeof modelsMap]
   ).filter((model) => model !== modelOne && model !== modelThree);
 
-  const modelThreeList = Object.keys(modelsMap[baseModel]).filter(
-    (model) => model !== modelOne && model !== modelTwo
-  );
+  const modelThreeList = Object.keys(
+    modelsMap[baseModel as keyof typeof modelsMap]
+  ).filter((model) => model !== modelOne && model !== modelTwo);
 
   const handleBaseModelChange = (v: string) => {
     setBaseModel(v as BaseModelType);

invokeai/frontend/web/src/features/ui/components/tabs/ModelManager/subpanels/ModelManagerPanel/CheckpointModelEdit.tsx

@@ -1,4 +1,4 @@
-import { Divider, Flex, Text } from '@chakra-ui/react';
+import { Badge, Divider, Flex, Text } from '@chakra-ui/react';
 import { useForm } from '@mantine/form';
 import { makeToast } from 'app/components/Toaster';
 import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
@@ -115,7 +115,20 @@ export default function CheckpointModelEdit(props: CheckpointModelEditProps) {
             {MODEL_TYPE_MAP[model.base_model]} Model
           </Text>
         </Flex>
-        <ModelConvert model={model} />
+        {!['sdxl', 'sdxl-refiner'].includes(model.base_model) ? (
+          <ModelConvert model={model} />
+        ) : (
+          <Badge
+            sx={{
+              p: 2,
+              borderRadius: 4,
+              bg: 'error.200',
+              _dark: { bg: 'error.400' },
+            }}
+          >
+            Conversion Not Supported
+          </Badge>
+        )}
       </Flex>
       <Divider />
 

invokeai/frontend/web/src/features/ui/components/tabs/ModelManager/subpanels/shared/BaseModelSelect.tsx

@@ -8,6 +8,8 @@ import { useTranslation } from 'react-i18next';
 const baseModelSelectData: IAISelectDataType[] = [
   { value: 'sd-1', label: MODEL_TYPE_MAP['sd-1'] },
   { value: 'sd-2', label: MODEL_TYPE_MAP['sd-2'] },
+  { value: 'sdxl', label: MODEL_TYPE_MAP['sdxl'] },
+  { value: 'sdxl-refiner', label: MODEL_TYPE_MAP['sdxl-refiner'] },
 ];
 
 type BaseModelSelectProps = Omit<IAISelectProps, 'data'>;

invokeai/frontend/web/src/services/api/schema.d.ts

@@ -316,7 +316,7 @@ export type components = {
      * @description An enumeration. 
      * @enum {string}
      */
-    BaseModelType: "sd-1" | "sd-2";
+    BaseModelType: "sd-1" | "sd-2" | "sdxl" | "sdxl-refiner";
     /** BoardChanges */
     BoardChanges: {
       /**
@@ -1219,7 +1219,7 @@ export type components = {
        * @description The nodes in this graph
        */
       nodes?: {
-        [key: string]: (components["schemas"]["LoadImageInvocation"] | components["schemas"]["ShowImageInvocation"] | components["schemas"]["ImageCropInvocation"] | components["schemas"]["ImagePasteInvocation"] | components["schemas"]["MaskFromAlphaInvocation"] | components["schemas"]["ImageMultiplyInvocation"] | components["schemas"]["ImageChannelInvocation"] | components["schemas"]["ImageConvertInvocation"] | components["schemas"]["ImageBlurInvocation"] | components["schemas"]["ImageResizeInvocation"] | components["schemas"]["ImageScaleInvocation"] | components["schemas"]["ImageLerpInvocation"] | components["schemas"]["ImageInverseLerpInvocation"] | components["schemas"]["ControlNetInvocation"] | components["schemas"]["ImageProcessorInvocation"] | components["schemas"]["MainModelLoaderInvocation"] | components["schemas"]["LoraLoaderInvocation"] | components["schemas"]["VaeLoaderInvocation"] | components["schemas"]["MetadataAccumulatorInvocation"] | components["schemas"]["RangeInvocation"] | components["schemas"]["RangeOfSizeInvocation"] | components["schemas"]["RandomRangeInvocation"] | components["schemas"]["ImageCollectionInvocation"] | components["schemas"]["CompelInvocation"] | components["schemas"]["ClipSkipInvocation"] | components["schemas"]["CvInpaintInvocation"] | components["schemas"]["TextToLatentsInvocation"] | components["schemas"]["LatentsToImageInvocation"] | components["schemas"]["ResizeLatentsInvocation"] | components["schemas"]["ScaleLatentsInvocation"] | components["schemas"]["ImageToLatentsInvocation"] | components["schemas"]["InpaintInvocation"] | components["schemas"]["InfillColorInvocation"] | components["schemas"]["InfillTileInvocation"] | components["schemas"]["InfillPatchMatchInvocation"] | components["schemas"]["AddInvocation"] | components["schemas"]["SubtractInvocation"] | components["schemas"]["MultiplyInvocation"] | components["schemas"]["DivideInvocation"] | components["schemas"]["RandomIntInvocation"] | components["schemas"]["NoiseInvocation"] | components["schemas"]["ParamIntInvocation"] | components["schemas"]["ParamFloatInvocation"] | components["schemas"]["FloatLinearRangeInvocation"] | components["schemas"]["StepParamEasingInvocation"] | components["schemas"]["DynamicPromptInvocation"] | components["schemas"]["RealESRGANInvocation"] | components["schemas"]["GraphInvocation"] | components["schemas"]["IterateInvocation"] | components["schemas"]["CollectInvocation"] | components["schemas"]["CannyImageProcessorInvocation"] | components["schemas"]["HedImageProcessorInvocation"] | components["schemas"]["LineartImageProcessorInvocation"] | components["schemas"]["LineartAnimeImageProcessorInvocation"] | components["schemas"]["OpenposeImageProcessorInvocation"] | components["schemas"]["MidasDepthImageProcessorInvocation"] | components["schemas"]["NormalbaeImageProcessorInvocation"] | components["schemas"]["MlsdImageProcessorInvocation"] | components["schemas"]["PidiImageProcessorInvocation"] | components["schemas"]["ContentShuffleImageProcessorInvocation"] | components["schemas"]["ZoeDepthImageProcessorInvocation"] | components["schemas"]["MediapipeFaceProcessorInvocation"] | components["schemas"]["LeresImageProcessorInvocation"] | components["schemas"]["TileResamplerProcessorInvocation"] | components["schemas"]["SegmentAnythingProcessorInvocation"] | components["schemas"]["LatentsToLatentsInvocation"]) | undefined;
+        [key: string]: (components["schemas"]["LoadImageInvocation"] | components["schemas"]["ShowImageInvocation"] | components["schemas"]["ImageCropInvocation"] | components["schemas"]["ImagePasteInvocation"] | components["schemas"]["MaskFromAlphaInvocation"] | components["schemas"]["ImageMultiplyInvocation"] | components["schemas"]["ImageChannelInvocation"] | components["schemas"]["ImageConvertInvocation"] | components["schemas"]["ImageBlurInvocation"] | components["schemas"]["ImageResizeInvocation"] | components["schemas"]["ImageScaleInvocation"] | components["schemas"]["ImageLerpInvocation"] | components["schemas"]["ImageInverseLerpInvocation"] | components["schemas"]["ControlNetInvocation"] | components["schemas"]["ImageProcessorInvocation"] | components["schemas"]["MainModelLoaderInvocation"] | components["schemas"]["LoraLoaderInvocation"] | components["schemas"]["VaeLoaderInvocation"] | components["schemas"]["MetadataAccumulatorInvocation"] | components["schemas"]["RangeInvocation"] | components["schemas"]["RangeOfSizeInvocation"] | components["schemas"]["RandomRangeInvocation"] | components["schemas"]["ImageCollectionInvocation"] | components["schemas"]["CompelInvocation"] | components["schemas"]["SDXLCompelPromptInvocation"] | components["schemas"]["SDXLRefinerCompelPromptInvocation"] | components["schemas"]["SDXLRawPromptInvocation"] | components["schemas"]["SDXLRefinerRawPromptInvocation"] | components["schemas"]["ClipSkipInvocation"] | components["schemas"]["CvInpaintInvocation"] | components["schemas"]["TextToLatentsInvocation"] | components["schemas"]["LatentsToImageInvocation"] | components["schemas"]["ResizeLatentsInvocation"] | components["schemas"]["ScaleLatentsInvocation"] | components["schemas"]["ImageToLatentsInvocation"] | components["schemas"]["InpaintInvocation"] | components["schemas"]["InfillColorInvocation"] | components["schemas"]["InfillTileInvocation"] | components["schemas"]["InfillPatchMatchInvocation"] | components["schemas"]["AddInvocation"] | components["schemas"]["SubtractInvocation"] | components["schemas"]["MultiplyInvocation"] | components["schemas"]["DivideInvocation"] | components["schemas"]["RandomIntInvocation"] | components["schemas"]["NoiseInvocation"] | components["schemas"]["ParamIntInvocation"] | components["schemas"]["ParamFloatInvocation"] | components["schemas"]["FloatLinearRangeInvocation"] | components["schemas"]["StepParamEasingInvocation"] | components["schemas"]["DynamicPromptInvocation"] | components["schemas"]["PromptsFromFileInvocation"] | components["schemas"]["SDXLModelLoaderInvocation"] | components["schemas"]["SDXLRefinerModelLoaderInvocation"] | components["schemas"]["SDXLTextToLatentsInvocation"] | components["schemas"]["SDXLLatentsToLatentsInvocation"] | components["schemas"]["RealESRGANInvocation"] | components["schemas"]["GraphInvocation"] | components["schemas"]["IterateInvocation"] | components["schemas"]["CollectInvocation"] | components["schemas"]["CannyImageProcessorInvocation"] | components["schemas"]["HedImageProcessorInvocation"] | components["schemas"]["LineartImageProcessorInvocation"] | components["schemas"]["LineartAnimeImageProcessorInvocation"] | components["schemas"]["OpenposeImageProcessorInvocation"] | components["schemas"]["MidasDepthImageProcessorInvocation"] | components["schemas"]["NormalbaeImageProcessorInvocation"] | components["schemas"]["MlsdImageProcessorInvocation"] | components["schemas"]["PidiImageProcessorInvocation"] | components["schemas"]["ContentShuffleImageProcessorInvocation"] | components["schemas"]["ZoeDepthImageProcessorInvocation"] | components["schemas"]["MediapipeFaceProcessorInvocation"] | components["schemas"]["LeresImageProcessorInvocation"] | components["schemas"]["TileResamplerProcessorInvocation"] | components["schemas"]["SegmentAnythingProcessorInvocation"] | components["schemas"]["LatentsToLatentsInvocation"]) | undefined;
       };
       /**
        * Edges 
@@ -1262,7 +1262,7 @@ export type components = {
        * @description The results of node executions
        */
       results: {
-        [key: string]: (components["schemas"]["ImageOutput"] | components["schemas"]["MaskOutput"] | components["schemas"]["ControlOutput"] | components["schemas"]["ModelLoaderOutput"] | components["schemas"]["LoraLoaderOutput"] | components["schemas"]["VaeLoaderOutput"] | components["schemas"]["MetadataAccumulatorOutput"] | components["schemas"]["IntCollectionOutput"] | components["schemas"]["FloatCollectionOutput"] | components["schemas"]["ImageCollectionOutput"] | components["schemas"]["CompelOutput"] | components["schemas"]["ClipSkipInvocationOutput"] | components["schemas"]["LatentsOutput"] | components["schemas"]["IntOutput"] | components["schemas"]["FloatOutput"] | components["schemas"]["NoiseOutput"] | components["schemas"]["PromptOutput"] | components["schemas"]["PromptCollectionOutput"] | components["schemas"]["GraphInvocationOutput"] | components["schemas"]["IterateInvocationOutput"] | components["schemas"]["CollectInvocationOutput"]) | undefined;
+        [key: string]: (components["schemas"]["ImageOutput"] | components["schemas"]["MaskOutput"] | components["schemas"]["ControlOutput"] | components["schemas"]["ModelLoaderOutput"] | components["schemas"]["LoraLoaderOutput"] | components["schemas"]["VaeLoaderOutput"] | components["schemas"]["MetadataAccumulatorOutput"] | components["schemas"]["IntCollectionOutput"] | components["schemas"]["FloatCollectionOutput"] | components["schemas"]["ImageCollectionOutput"] | components["schemas"]["CompelOutput"] | components["schemas"]["ClipSkipInvocationOutput"] | components["schemas"]["LatentsOutput"] | components["schemas"]["IntOutput"] | components["schemas"]["FloatOutput"] | components["schemas"]["NoiseOutput"] | components["schemas"]["PromptOutput"] | components["schemas"]["PromptCollectionOutput"] | components["schemas"]["SDXLModelLoaderOutput"] | components["schemas"]["SDXLRefinerModelLoaderOutput"] | components["schemas"]["GraphInvocationOutput"] | components["schemas"]["IterateInvocationOutput"] | components["schemas"]["CollectInvocationOutput"]) | undefined;
       };
       /**
        * Errors 
@@ -2060,6 +2060,12 @@ export type components = {
        * @default false
        */
       tiled?: boolean;
+      /**
+       * Fp32 
+       * @description Decode in full precision 
+       * @default false
+       */
+      fp32?: boolean;
     };
     /**
      * ImageUrlsDTO 
@@ -2515,6 +2521,12 @@ export type components = {
        * @default false
        */
       tiled?: boolean;
+      /**
+       * Fp32 
+       * @description Decode in full precision 
+       * @default false
+       */
+      fp32?: boolean;
       /**
        * Metadata 
        * @description Optional core metadata to be written to the image
@@ -3335,7 +3347,7 @@ export type components = {
     /** ModelsList */
     ModelsList: {
       /** Models */
-      models: (components["schemas"]["StableDiffusion1ModelCheckpointConfig"] | components["schemas"]["StableDiffusion1ModelDiffusersConfig"] | components["schemas"]["VaeModelConfig"] | components["schemas"]["LoRAModelConfig"] | components["schemas"]["ControlNetModelConfig"] | components["schemas"]["TextualInversionModelConfig"] | components["schemas"]["StableDiffusion2ModelCheckpointConfig"] | components["schemas"]["StableDiffusion2ModelDiffusersConfig"])[];
+      models: (components["schemas"]["StableDiffusion1ModelCheckpointConfig"] | components["schemas"]["StableDiffusion1ModelDiffusersConfig"] | components["schemas"]["VaeModelConfig"] | components["schemas"]["LoRAModelConfig"] | components["schemas"]["ControlNetModelConfig"] | components["schemas"]["TextualInversionModelConfig"] | components["schemas"]["StableDiffusion2ModelCheckpointConfig"] | components["schemas"]["StableDiffusion2ModelDiffusersConfig"] | components["schemas"]["StableDiffusionXLModelCheckpointConfig"] | components["schemas"]["StableDiffusionXLModelDiffusersConfig"])[];
     };
     /**
      * MultiplyInvocation 
@@ -3763,6 +3775,56 @@ export type components = {
        */
       prompt: string;
     };
+    /**
+     * PromptsFromFileInvocation 
+     * @description Loads prompts from a text file
+     */
+    PromptsFromFileInvocation: {
+      /**
+       * Id 
+       * @description The id of this node. Must be unique among all nodes.
+       */
+      id: string;
+      /**
+       * Is Intermediate 
+       * @description Whether or not this node is an intermediate node. 
+       * @default false
+       */
+      is_intermediate?: boolean;
+      /**
+       * Type 
+       * @default prompt_from_file 
+       * @enum {string}
+       */
+      type?: "prompt_from_file";
+      /**
+       * File Path 
+       * @description Path to prompt text file
+       */
+      file_path: string;
+      /**
+       * Pre Prompt 
+       * @description String to prepend to each prompt
+       */
+      pre_prompt?: string;
+      /**
+       * Post Prompt 
+       * @description String to append to each prompt
+       */
+      post_prompt?: string;
+      /**
+       * Start Line 
+       * @description Line in the file to start start from 
+       * @default 1
+       */
+      start_line?: number;
+      /**
+       * Max Prompts 
+       * @description Max lines to read from file (0=all) 
+       * @default 1
+       */
+      max_prompts?: number;
+    };
     /**
      * RandomIntInvocation 
      * @description Outputs a single random integer.
@@ -4024,6 +4086,533 @@ export type components = {
      * @enum {string}
      */
     ResourceOrigin: "internal" | "external";
+    /**
+     * SDXLCompelPromptInvocation 
+     * @description Parse prompt using compel package to conditioning.
+     */
+    SDXLCompelPromptInvocation: {
+      /**
+       * Id 
+       * @description The id of this node. Must be unique among all nodes.
+       */
+      id: string;
+      /**
+       * Is Intermediate 
+       * @description Whether or not this node is an intermediate node. 
+       * @default false
+       */
+      is_intermediate?: boolean;
+      /**
+       * Type 
+       * @default sdxl_compel_prompt 
+       * @enum {string}
+       */
+      type?: "sdxl_compel_prompt";
+      /**
+       * Prompt 
+       * @description Prompt 
+       * @default
+       */
+      prompt?: string;
+      /**
+       * Style 
+       * @description Style prompt 
+       * @default
+       */
+      style?: string;
+      /**
+       * Original Width 
+       * @default 1024
+       */
+      original_width?: number;
+      /**
+       * Original Height 
+       * @default 1024
+       */
+      original_height?: number;
+      /**
+       * Crop Top 
+       * @default 0
+       */
+      crop_top?: number;
+      /**
+       * Crop Left 
+       * @default 0
+       */
+      crop_left?: number;
+      /**
+       * Target Width 
+       * @default 1024
+       */
+      target_width?: number;
+      /**
+       * Target Height 
+       * @default 1024
+       */
+      target_height?: number;
+      /**
+       * Clip1 
+       * @description Clip to use
+       */
+      clip1?: components["schemas"]["ClipField"];
+      /**
+       * Clip2 
+       * @description Clip to use
+       */
+      clip2?: components["schemas"]["ClipField"];
+    };
+    /**
+     * SDXLLatentsToLatentsInvocation 
+     * @description Generates latents from conditionings.
+     */
+    SDXLLatentsToLatentsInvocation: {
+      /**
+       * Id 
+       * @description The id of this node. Must be unique among all nodes.
+       */
+      id: string;
+      /**
+       * Is Intermediate 
+       * @description Whether or not this node is an intermediate node. 
+       * @default false
+       */
+      is_intermediate?: boolean;
+      /**
+       * Type 
+       * @default l2l_sdxl 
+       * @enum {string}
+       */
+      type?: "l2l_sdxl";
+      /**
+       * Positive Conditioning 
+       * @description Positive conditioning for generation
+       */
+      positive_conditioning?: components["schemas"]["ConditioningField"];
+      /**
+       * Negative Conditioning 
+       * @description Negative conditioning for generation
+       */
+      negative_conditioning?: components["schemas"]["ConditioningField"];
+      /**
+       * Noise 
+       * @description The noise to use
+       */
+      noise?: components["schemas"]["LatentsField"];
+      /**
+       * Steps 
+       * @description The number of steps to use to generate the image 
+       * @default 10
+       */
+      steps?: number;
+      /**
+       * Cfg Scale 
+       * @description The Classifier-Free Guidance, higher values may result in a result closer to the prompt 
+       * @default 7.5
+       */
+      cfg_scale?: number | (number)[];
+      /**
+       * Scheduler 
+       * @description The scheduler to use 
+       * @default euler 
+       * @enum {string}
+       */
+      scheduler?: "ddim" | "ddpm" | "deis" | "lms" | "lms_k" | "pndm" | "heun" | "heun_k" | "euler" | "euler_k" | "euler_a" | "kdpm_2" | "kdpm_2_a" | "dpmpp_2s" | "dpmpp_2s_k" | "dpmpp_2m" | "dpmpp_2m_k" | "dpmpp_2m_sde" | "dpmpp_2m_sde_k" | "dpmpp_sde" | "dpmpp_sde_k" | "unipc";
+      /**
+       * Unet 
+       * @description UNet submodel
+       */
+      unet?: components["schemas"]["UNetField"];
+      /**
+       * Latents 
+       * @description Initial latents
+       */
+      latents?: components["schemas"]["LatentsField"];
+      /**
+       * Denoising Start 
+       * @default 0
+       */
+      denoising_start?: number;
+      /**
+       * Denoising End 
+       * @default 1
+       */
+      denoising_end?: number;
+    };
+    /**
+     * SDXLModelLoaderInvocation 
+     * @description Loads an sdxl base model, outputting its submodels.
+     */
+    SDXLModelLoaderInvocation: {
+      /**
+       * Id 
+       * @description The id of this node. Must be unique among all nodes.
+       */
+      id: string;
+      /**
+       * Is Intermediate 
+       * @description Whether or not this node is an intermediate node. 
+       * @default false
+       */
+      is_intermediate?: boolean;
+      /**
+       * Type 
+       * @default sdxl_model_loader 
+       * @enum {string}
+       */
+      type?: "sdxl_model_loader";
+      /**
+       * Model 
+       * @description The model to load
+       */
+      model: components["schemas"]["MainModelField"];
+    };
+    /**
+     * SDXLModelLoaderOutput 
+     * @description SDXL base model loader output
+     */
+    SDXLModelLoaderOutput: {
+      /**
+       * Type 
+       * @default sdxl_model_loader_output 
+       * @enum {string}
+       */
+      type?: "sdxl_model_loader_output";
+      /**
+       * Unet 
+       * @description UNet submodel
+       */
+      unet?: components["schemas"]["UNetField"];
+      /**
+       * Clip 
+       * @description Tokenizer and text_encoder submodels
+       */
+      clip?: components["schemas"]["ClipField"];
+      /**
+       * Clip2 
+       * @description Tokenizer and text_encoder submodels
+       */
+      clip2?: components["schemas"]["ClipField"];
+      /**
+       * Vae 
+       * @description Vae submodel
+       */
+      vae?: components["schemas"]["VaeField"];
+    };
+    /**
+     * SDXLRawPromptInvocation 
+     * @description Parse prompt using compel package to conditioning.
+     */
+    SDXLRawPromptInvocation: {
+      /**
+       * Id 
+       * @description The id of this node. Must be unique among all nodes.
+       */
+      id: string;
+      /**
+       * Is Intermediate 
+       * @description Whether or not this node is an intermediate node. 
+       * @default false
+       */
+      is_intermediate?: boolean;
+      /**
+       * Type 
+       * @default sdxl_raw_prompt 
+       * @enum {string}
+       */
+      type?: "sdxl_raw_prompt";
+      /**
+       * Prompt 
+       * @description Prompt 
+       * @default
+       */
+      prompt?: string;
+      /**
+       * Style 
+       * @description Style prompt 
+       * @default
+       */
+      style?: string;
+      /**
+       * Original Width 
+       * @default 1024
+       */
+      original_width?: number;
+      /**
+       * Original Height 
+       * @default 1024
+       */
+      original_height?: number;
+      /**
+       * Crop Top 
+       * @default 0
+       */
+      crop_top?: number;
+      /**
+       * Crop Left 
+       * @default 0
+       */
+      crop_left?: number;
+      /**
+       * Target Width 
+       * @default 1024
+       */
+      target_width?: number;
+      /**
+       * Target Height 
+       * @default 1024
+       */
+      target_height?: number;
+      /**
+       * Clip1 
+       * @description Clip to use
+       */
+      clip1?: components["schemas"]["ClipField"];
+      /**
+       * Clip2 
+       * @description Clip to use
+       */
+      clip2?: components["schemas"]["ClipField"];
+    };
+    /**
+     * SDXLRefinerCompelPromptInvocation 
+     * @description Parse prompt using compel package to conditioning.
+     */
+    SDXLRefinerCompelPromptInvocation: {
+      /**
+       * Id 
+       * @description The id of this node. Must be unique among all nodes.
+       */
+      id: string;
+      /**
+       * Is Intermediate 
+       * @description Whether or not this node is an intermediate node. 
+       * @default false
+       */
+      is_intermediate?: boolean;
+      /**
+       * Type 
+       * @default sdxl_refiner_compel_prompt 
+       * @enum {string}
+       */
+      type?: "sdxl_refiner_compel_prompt";
+      /**
+       * Style 
+       * @description Style prompt 
+       * @default
+       */
+      style?: string;
+      /**
+       * Original Width 
+       * @default 1024
+       */
+      original_width?: number;
+      /**
+       * Original Height 
+       * @default 1024
+       */
+      original_height?: number;
+      /**
+       * Crop Top 
+       * @default 0
+       */
+      crop_top?: number;
+      /**
+       * Crop Left 
+       * @default 0
+       */
+      crop_left?: number;
+      /**
+       * Aesthetic Score 
+       * @default 6
+       */
+      aesthetic_score?: number;
+      /**
+       * Clip2 
+       * @description Clip to use
+       */
+      clip2?: components["schemas"]["ClipField"];
+    };
+    /**
+     * SDXLRefinerModelLoaderInvocation 
+     * @description Loads an sdxl refiner model, outputting its submodels.
+     */
+    SDXLRefinerModelLoaderInvocation: {
+      /**
+       * Id 
+       * @description The id of this node. Must be unique among all nodes.
+       */
+      id: string;
+      /**
+       * Is Intermediate 
+       * @description Whether or not this node is an intermediate node. 
+       * @default false
+       */
+      is_intermediate?: boolean;
+      /**
+       * Type 
+       * @default sdxl_refiner_model_loader 
+       * @enum {string}
+       */
+      type?: "sdxl_refiner_model_loader";
+      /**
+       * Model 
+       * @description The model to load
+       */
+      model: components["schemas"]["MainModelField"];
+    };
+    /**
+     * SDXLRefinerModelLoaderOutput 
+     * @description SDXL refiner model loader output
+     */
+    SDXLRefinerModelLoaderOutput: {
+      /**
+       * Type 
+       * @default sdxl_refiner_model_loader_output 
+       * @enum {string}
+       */
+      type?: "sdxl_refiner_model_loader_output";
+      /**
+       * Unet 
+       * @description UNet submodel
+       */
+      unet?: components["schemas"]["UNetField"];
+      /**
+       * Clip2 
+       * @description Tokenizer and text_encoder submodels
+       */
+      clip2?: components["schemas"]["ClipField"];
+      /**
+       * Vae 
+       * @description Vae submodel
+       */
+      vae?: components["schemas"]["VaeField"];
+    };
+    /**
+     * SDXLRefinerRawPromptInvocation 
+     * @description Parse prompt using compel package to conditioning.
+     */
+    SDXLRefinerRawPromptInvocation: {
+      /**
+       * Id 
+       * @description The id of this node. Must be unique among all nodes.
+       */
+      id: string;
+      /**
+       * Is Intermediate 
+       * @description Whether or not this node is an intermediate node. 
+       * @default false
+       */
+      is_intermediate?: boolean;
+      /**
+       * Type 
+       * @default sdxl_refiner_raw_prompt 
+       * @enum {string}
+       */
+      type?: "sdxl_refiner_raw_prompt";
+      /**
+       * Style 
+       * @description Style prompt 
+       * @default
+       */
+      style?: string;
+      /**
+       * Original Width 
+       * @default 1024
+       */
+      original_width?: number;
+      /**
+       * Original Height 
+       * @default 1024
+       */
+      original_height?: number;
+      /**
+       * Crop Top 
+       * @default 0
+       */
+      crop_top?: number;
+      /**
+       * Crop Left 
+       * @default 0
+       */
+      crop_left?: number;
+      /**
+       * Aesthetic Score 
+       * @default 6
+       */
+      aesthetic_score?: number;
+      /**
+       * Clip2 
+       * @description Clip to use
+       */
+      clip2?: components["schemas"]["ClipField"];
+    };
+    /**
+     * SDXLTextToLatentsInvocation 
+     * @description Generates latents from conditionings.
+     */
+    SDXLTextToLatentsInvocation: {
+      /**
+       * Id 
+       * @description The id of this node. Must be unique among all nodes.
+       */
+      id: string;
+      /**
+       * Is Intermediate 
+       * @description Whether or not this node is an intermediate node. 
+       * @default false
+       */
+      is_intermediate?: boolean;
+      /**
+       * Type 
+       * @default t2l_sdxl 
+       * @enum {string}
+       */
+      type?: "t2l_sdxl";
+      /**
+       * Positive Conditioning 
+       * @description Positive conditioning for generation
+       */
+      positive_conditioning?: components["schemas"]["ConditioningField"];
+      /**
+       * Negative Conditioning 
+       * @description Negative conditioning for generation
+       */
+      negative_conditioning?: components["schemas"]["ConditioningField"];
+      /**
+       * Noise 
+       * @description The noise to use
+       */
+      noise?: components["schemas"]["LatentsField"];
+      /**
+       * Steps 
+       * @description The number of steps to use to generate the image 
+       * @default 10
+       */
+      steps?: number;
+      /**
+       * Cfg Scale 
+       * @description The Classifier-Free Guidance, higher values may result in a result closer to the prompt 
+       * @default 7.5
+       */
+      cfg_scale?: number | (number)[];
+      /**
+       * Scheduler 
+       * @description The scheduler to use 
+       * @default euler 
+       * @enum {string}
+       */
+      scheduler?: "ddim" | "ddpm" | "deis" | "lms" | "lms_k" | "pndm" | "heun" | "heun_k" | "euler" | "euler_k" | "euler_a" | "kdpm_2" | "kdpm_2_a" | "dpmpp_2s" | "dpmpp_2s_k" | "dpmpp_2m" | "dpmpp_2m_k" | "dpmpp_2m_sde" | "dpmpp_2m_sde_k" | "dpmpp_sde" | "dpmpp_sde_k" | "unipc";
+      /**
+       * Unet 
+       * @description UNet submodel
+       */
+      unet?: components["schemas"]["UNetField"];
+      /**
+       * Denoising End 
+       * @default 1
+       */
+      denoising_end?: number;
+    };
     /**
      * ScaleLatentsInvocation 
      * @description Scales latents by a given factor.
@@ -4226,6 +4815,56 @@ export type components = {
       vae?: string;
       variant: components["schemas"]["ModelVariantType"];
     };
+    /** StableDiffusionXLModelCheckpointConfig */
+    StableDiffusionXLModelCheckpointConfig: {
+      /** Model Name */
+      model_name: string;
+      base_model: components["schemas"]["BaseModelType"];
+      /**
+       * Model Type 
+       * @enum {string}
+       */
+      model_type: "main";
+      /** Path */
+      path: string;
+      /** Description */
+      description?: string;
+      /**
+       * Model Format 
+       * @enum {string}
+       */
+      model_format: "checkpoint";
+      error?: components["schemas"]["ModelError"];
+      /** Vae */
+      vae?: string;
+      /** Config */
+      config: string;
+      variant: components["schemas"]["ModelVariantType"];
+    };
+    /** StableDiffusionXLModelDiffusersConfig */
+    StableDiffusionXLModelDiffusersConfig: {
+      /** Model Name */
+      model_name: string;
+      base_model: components["schemas"]["BaseModelType"];
+      /**
+       * Model Type 
+       * @enum {string}
+       */
+      model_type: "main";
+      /** Path */
+      path: string;
+      /** Description */
+      description?: string;
+      /**
+       * Model Format 
+       * @enum {string}
+       */
+      model_format: "diffusers";
+      error?: components["schemas"]["ModelError"];
+      /** Vae */
+      vae?: string;
+      variant: components["schemas"]["ModelVariantType"];
+    };
     /**
      * StepParamEasingInvocation 
      * @description Experimental per-step parameter easing for denoising steps
@@ -4313,7 +4952,7 @@ export type components = {
      * @description An enumeration. 
      * @enum {string}
      */
-    SubModelType: "unet" | "text_encoder" | "tokenizer" | "vae" | "scheduler" | "safety_checker";
+    SubModelType: "unet" | "text_encoder" | "text_encoder_2" | "tokenizer" | "tokenizer_2" | "vae" | "scheduler" | "safety_checker";
     /**
      * SubtractInvocation 
      * @description Subtracts two numbers
@@ -4612,18 +5251,24 @@ export type components = {
        */
       image?: components["schemas"]["ImageField"];
     };
-    /**
-     * StableDiffusion1ModelFormat 
-     * @description An enumeration. 
-     * @enum {string}
-     */
-    StableDiffusion1ModelFormat: "checkpoint" | "diffusers";
     /**
      * StableDiffusion2ModelFormat 
      * @description An enumeration. 
      * @enum {string}
      */
     StableDiffusion2ModelFormat: "checkpoint" | "diffusers";
+    /**
+     * StableDiffusionXLModelFormat 
+     * @description An enumeration. 
+     * @enum {string}
+     */
+    StableDiffusionXLModelFormat: "checkpoint" | "diffusers";
+    /**
+     * StableDiffusion1ModelFormat 
+     * @description An enumeration. 
+     * @enum {string}
+     */
+    StableDiffusion1ModelFormat: "checkpoint" | "diffusers";
   };
   responses: never;
   parameters: never;
@@ -4734,7 +5379,7 @@ export type operations = {
     };
     requestBody: {
       content: {
-        "application/json": components["schemas"]["LoadImageInvocation"] | components["schemas"]["ShowImageInvocation"] | components["schemas"]["ImageCropInvocation"] | components["schemas"]["ImagePasteInvocation"] | components["schemas"]["MaskFromAlphaInvocation"] | components["schemas"]["ImageMultiplyInvocation"] | components["schemas"]["ImageChannelInvocation"] | components["schemas"]["ImageConvertInvocation"] | components["schemas"]["ImageBlurInvocation"] | components["schemas"]["ImageResizeInvocation"] | components["schemas"]["ImageScaleInvocation"] | components["schemas"]["ImageLerpInvocation"] | components["schemas"]["ImageInverseLerpInvocation"] | components["schemas"]["ControlNetInvocation"] | components["schemas"]["ImageProcessorInvocation"] | components["schemas"]["MainModelLoaderInvocation"] | components["schemas"]["LoraLoaderInvocation"] | components["schemas"]["VaeLoaderInvocation"] | components["schemas"]["MetadataAccumulatorInvocation"] | components["schemas"]["RangeInvocation"] | components["schemas"]["RangeOfSizeInvocation"] | components["schemas"]["RandomRangeInvocation"] | components["schemas"]["ImageCollectionInvocation"] | components["schemas"]["CompelInvocation"] | components["schemas"]["ClipSkipInvocation"] | components["schemas"]["CvInpaintInvocation"] | components["schemas"]["TextToLatentsInvocation"] | components["schemas"]["LatentsToImageInvocation"] | components["schemas"]["ResizeLatentsInvocation"] | components["schemas"]["ScaleLatentsInvocation"] | components["schemas"]["ImageToLatentsInvocation"] | components["schemas"]["InpaintInvocation"] | components["schemas"]["InfillColorInvocation"] | components["schemas"]["InfillTileInvocation"] | components["schemas"]["InfillPatchMatchInvocation"] | components["schemas"]["AddInvocation"] | components["schemas"]["SubtractInvocation"] | components["schemas"]["MultiplyInvocation"] | components["schemas"]["DivideInvocation"] | components["schemas"]["RandomIntInvocation"] | components["schemas"]["NoiseInvocation"] | components["schemas"]["ParamIntInvocation"] | components["schemas"]["ParamFloatInvocation"] | components["schemas"]["FloatLinearRangeInvocation"] | components["schemas"]["StepParamEasingInvocation"] | components["schemas"]["DynamicPromptInvocation"] | components["schemas"]["RealESRGANInvocation"] | components["schemas"]["GraphInvocation"] | components["schemas"]["IterateInvocation"] | components["schemas"]["CollectInvocation"] | components["schemas"]["CannyImageProcessorInvocation"] | components["schemas"]["HedImageProcessorInvocation"] | components["schemas"]["LineartImageProcessorInvocation"] | components["schemas"]["LineartAnimeImageProcessorInvocation"] | components["schemas"]["OpenposeImageProcessorInvocation"] | components["schemas"]["MidasDepthImageProcessorInvocation"] | components["schemas"]["NormalbaeImageProcessorInvocation"] | components["schemas"]["MlsdImageProcessorInvocation"] | components["schemas"]["PidiImageProcessorInvocation"] | components["schemas"]["ContentShuffleImageProcessorInvocation"] | components["schemas"]["ZoeDepthImageProcessorInvocation"] | components["schemas"]["MediapipeFaceProcessorInvocation"] | components["schemas"]["LeresImageProcessorInvocation"] | components["schemas"]["TileResamplerProcessorInvocation"] | components["schemas"]["SegmentAnythingProcessorInvocation"] | components["schemas"]["LatentsToLatentsInvocation"];
+        "application/json": components["schemas"]["LoadImageInvocation"] | components["schemas"]["ShowImageInvocation"] | components["schemas"]["ImageCropInvocation"] | components["schemas"]["ImagePasteInvocation"] | components["schemas"]["MaskFromAlphaInvocation"] | components["schemas"]["ImageMultiplyInvocation"] | components["schemas"]["ImageChannelInvocation"] | components["schemas"]["ImageConvertInvocation"] | components["schemas"]["ImageBlurInvocation"] | components["schemas"]["ImageResizeInvocation"] | components["schemas"]["ImageScaleInvocation"] | components["schemas"]["ImageLerpInvocation"] | components["schemas"]["ImageInverseLerpInvocation"] | components["schemas"]["ControlNetInvocation"] | components["schemas"]["ImageProcessorInvocation"] | components["schemas"]["MainModelLoaderInvocation"] | components["schemas"]["LoraLoaderInvocation"] | components["schemas"]["VaeLoaderInvocation"] | components["schemas"]["MetadataAccumulatorInvocation"] | components["schemas"]["RangeInvocation"] | components["schemas"]["RangeOfSizeInvocation"] | components["schemas"]["RandomRangeInvocation"] | components["schemas"]["ImageCollectionInvocation"] | components["schemas"]["CompelInvocation"] | components["schemas"]["SDXLCompelPromptInvocation"] | components["schemas"]["SDXLRefinerCompelPromptInvocation"] | components["schemas"]["SDXLRawPromptInvocation"] | components["schemas"]["SDXLRefinerRawPromptInvocation"] | components["schemas"]["ClipSkipInvocation"] | components["schemas"]["CvInpaintInvocation"] | components["schemas"]["TextToLatentsInvocation"] | components["schemas"]["LatentsToImageInvocation"] | components["schemas"]["ResizeLatentsInvocation"] | components["schemas"]["ScaleLatentsInvocation"] | components["schemas"]["ImageToLatentsInvocation"] | components["schemas"]["InpaintInvocation"] | components["schemas"]["InfillColorInvocation"] | components["schemas"]["InfillTileInvocation"] | components["schemas"]["InfillPatchMatchInvocation"] | components["schemas"]["AddInvocation"] | components["schemas"]["SubtractInvocation"] | components["schemas"]["MultiplyInvocation"] | components["schemas"]["DivideInvocation"] | components["schemas"]["RandomIntInvocation"] | components["schemas"]["NoiseInvocation"] | components["schemas"]["ParamIntInvocation"] | components["schemas"]["ParamFloatInvocation"] | components["schemas"]["FloatLinearRangeInvocation"] | components["schemas"]["StepParamEasingInvocation"] | components["schemas"]["DynamicPromptInvocation"] | components["schemas"]["PromptsFromFileInvocation"] | components["schemas"]["SDXLModelLoaderInvocation"] | components["schemas"]["SDXLRefinerModelLoaderInvocation"] | components["schemas"]["SDXLTextToLatentsInvocation"] | components["schemas"]["SDXLLatentsToLatentsInvocation"] | components["schemas"]["RealESRGANInvocation"] | components["schemas"]["GraphInvocation"] | components["schemas"]["IterateInvocation"] | components["schemas"]["CollectInvocation"] | components["schemas"]["CannyImageProcessorInvocation"] | components["schemas"]["HedImageProcessorInvocation"] | components["schemas"]["LineartImageProcessorInvocation"] | components["schemas"]["LineartAnimeImageProcessorInvocation"] | components["schemas"]["OpenposeImageProcessorInvocation"] | components["schemas"]["MidasDepthImageProcessorInvocation"] | components["schemas"]["NormalbaeImageProcessorInvocation"] | components["schemas"]["MlsdImageProcessorInvocation"] | components["schemas"]["PidiImageProcessorInvocation"] | components["schemas"]["ContentShuffleImageProcessorInvocation"] | components["schemas"]["ZoeDepthImageProcessorInvocation"] | components["schemas"]["MediapipeFaceProcessorInvocation"] | components["schemas"]["LeresImageProcessorInvocation"] | components["schemas"]["TileResamplerProcessorInvocation"] | components["schemas"]["SegmentAnythingProcessorInvocation"] | components["schemas"]["LatentsToLatentsInvocation"];
       };
     };
     responses: {
@@ -4771,7 +5416,7 @@ export type operations = {
     };
     requestBody: {
       content: {
-        "application/json": components["schemas"]["LoadImageInvocation"] | components["schemas"]["ShowImageInvocation"] | components["schemas"]["ImageCropInvocation"] | components["schemas"]["ImagePasteInvocation"] | components["schemas"]["MaskFromAlphaInvocation"] | components["schemas"]["ImageMultiplyInvocation"] | components["schemas"]["ImageChannelInvocation"] | components["schemas"]["ImageConvertInvocation"] | components["schemas"]["ImageBlurInvocation"] | components["schemas"]["ImageResizeInvocation"] | components["schemas"]["ImageScaleInvocation"] | components["schemas"]["ImageLerpInvocation"] | components["schemas"]["ImageInverseLerpInvocation"] | components["schemas"]["ControlNetInvocation"] | components["schemas"]["ImageProcessorInvocation"] | components["schemas"]["MainModelLoaderInvocation"] | components["schemas"]["LoraLoaderInvocation"] | components["schemas"]["VaeLoaderInvocation"] | components["schemas"]["MetadataAccumulatorInvocation"] | components["schemas"]["RangeInvocation"] | components["schemas"]["RangeOfSizeInvocation"] | components["schemas"]["RandomRangeInvocation"] | components["schemas"]["ImageCollectionInvocation"] | components["schemas"]["CompelInvocation"] | components["schemas"]["ClipSkipInvocation"] | components["schemas"]["CvInpaintInvocation"] | components["schemas"]["TextToLatentsInvocation"] | components["schemas"]["LatentsToImageInvocation"] | components["schemas"]["ResizeLatentsInvocation"] | components["schemas"]["ScaleLatentsInvocation"] | components["schemas"]["ImageToLatentsInvocation"] | components["schemas"]["InpaintInvocation"] | components["schemas"]["InfillColorInvocation"] | components["schemas"]["InfillTileInvocation"] | components["schemas"]["InfillPatchMatchInvocation"] | components["schemas"]["AddInvocation"] | components["schemas"]["SubtractInvocation"] | components["schemas"]["MultiplyInvocation"] | components["schemas"]["DivideInvocation"] | components["schemas"]["RandomIntInvocation"] | components["schemas"]["NoiseInvocation"] | components["schemas"]["ParamIntInvocation"] | components["schemas"]["ParamFloatInvocation"] | components["schemas"]["FloatLinearRangeInvocation"] | components["schemas"]["StepParamEasingInvocation"] | components["schemas"]["DynamicPromptInvocation"] | components["schemas"]["RealESRGANInvocation"] | components["schemas"]["GraphInvocation"] | components["schemas"]["IterateInvocation"] | components["schemas"]["CollectInvocation"] | components["schemas"]["CannyImageProcessorInvocation"] | components["schemas"]["HedImageProcessorInvocation"] | components["schemas"]["LineartImageProcessorInvocation"] | components["schemas"]["LineartAnimeImageProcessorInvocation"] | components["schemas"]["OpenposeImageProcessorInvocation"] | components["schemas"]["MidasDepthImageProcessorInvocation"] | components["schemas"]["NormalbaeImageProcessorInvocation"] | components["schemas"]["MlsdImageProcessorInvocation"] | components["schemas"]["PidiImageProcessorInvocation"] | components["schemas"]["ContentShuffleImageProcessorInvocation"] | components["schemas"]["ZoeDepthImageProcessorInvocation"] | components["schemas"]["MediapipeFaceProcessorInvocation"] | components["schemas"]["LeresImageProcessorInvocation"] | components["schemas"]["TileResamplerProcessorInvocation"] | components["schemas"]["SegmentAnythingProcessorInvocation"] | components["schemas"]["LatentsToLatentsInvocation"];
+        "application/json": components["schemas"]["LoadImageInvocation"] | components["schemas"]["ShowImageInvocation"] | components["schemas"]["ImageCropInvocation"] | components["schemas"]["ImagePasteInvocation"] | components["schemas"]["MaskFromAlphaInvocation"] | components["schemas"]["ImageMultiplyInvocation"] | components["schemas"]["ImageChannelInvocation"] | components["schemas"]["ImageConvertInvocation"] | components["schemas"]["ImageBlurInvocation"] | components["schemas"]["ImageResizeInvocation"] | components["schemas"]["ImageScaleInvocation"] | components["schemas"]["ImageLerpInvocation"] | components["schemas"]["ImageInverseLerpInvocation"] | components["schemas"]["ControlNetInvocation"] | components["schemas"]["ImageProcessorInvocation"] | components["schemas"]["MainModelLoaderInvocation"] | components["schemas"]["LoraLoaderInvocation"] | components["schemas"]["VaeLoaderInvocation"] | components["schemas"]["MetadataAccumulatorInvocation"] | components["schemas"]["RangeInvocation"] | components["schemas"]["RangeOfSizeInvocation"] | components["schemas"]["RandomRangeInvocation"] | components["schemas"]["ImageCollectionInvocation"] | components["schemas"]["CompelInvocation"] | components["schemas"]["SDXLCompelPromptInvocation"] | components["schemas"]["SDXLRefinerCompelPromptInvocation"] | components["schemas"]["SDXLRawPromptInvocation"] | components["schemas"]["SDXLRefinerRawPromptInvocation"] | components["schemas"]["ClipSkipInvocation"] | components["schemas"]["CvInpaintInvocation"] | components["schemas"]["TextToLatentsInvocation"] | components["schemas"]["LatentsToImageInvocation"] | components["schemas"]["ResizeLatentsInvocation"] | components["schemas"]["ScaleLatentsInvocation"] | components["schemas"]["ImageToLatentsInvocation"] | components["schemas"]["InpaintInvocation"] | components["schemas"]["InfillColorInvocation"] | components["schemas"]["InfillTileInvocation"] | components["schemas"]["InfillPatchMatchInvocation"] | components["schemas"]["AddInvocation"] | components["schemas"]["SubtractInvocation"] | components["schemas"]["MultiplyInvocation"] | components["schemas"]["DivideInvocation"] | components["schemas"]["RandomIntInvocation"] | components["schemas"]["NoiseInvocation"] | components["schemas"]["ParamIntInvocation"] | components["schemas"]["ParamFloatInvocation"] | components["schemas"]["FloatLinearRangeInvocation"] | components["schemas"]["StepParamEasingInvocation"] | components["schemas"]["DynamicPromptInvocation"] | components["schemas"]["PromptsFromFileInvocation"] | components["schemas"]["SDXLModelLoaderInvocation"] | components["schemas"]["SDXLRefinerModelLoaderInvocation"] | components["schemas"]["SDXLTextToLatentsInvocation"] | components["schemas"]["SDXLLatentsToLatentsInvocation"] | components["schemas"]["RealESRGANInvocation"] | components["schemas"]["GraphInvocation"] | components["schemas"]["IterateInvocation"] | components["schemas"]["CollectInvocation"] | components["schemas"]["CannyImageProcessorInvocation"] | components["schemas"]["HedImageProcessorInvocation"] | components["schemas"]["LineartImageProcessorInvocation"] | components["schemas"]["LineartAnimeImageProcessorInvocation"] | components["schemas"]["OpenposeImageProcessorInvocation"] | components["schemas"]["MidasDepthImageProcessorInvocation"] | components["schemas"]["NormalbaeImageProcessorInvocation"] | components["schemas"]["MlsdImageProcessorInvocation"] | components["schemas"]["PidiImageProcessorInvocation"] | components["schemas"]["ContentShuffleImageProcessorInvocation"] | components["schemas"]["ZoeDepthImageProcessorInvocation"] | components["schemas"]["MediapipeFaceProcessorInvocation"] | components["schemas"]["LeresImageProcessorInvocation"] | components["schemas"]["TileResamplerProcessorInvocation"] | components["schemas"]["SegmentAnythingProcessorInvocation"] | components["schemas"]["LatentsToLatentsInvocation"];
       };
     };
     responses: {
@@ -4969,8 +5614,8 @@ export type operations = {
   list_models: {
     parameters: {
       query?: {
-        /** @description Base model */
-        base_model?: components["schemas"]["BaseModelType"];
+        /** @description Base models to include */
+        base_models?: (components["schemas"]["BaseModelType"])[];
         /** @description The type of model to get */
         model_type?: components["schemas"]["ModelType"];
       };
@@ -5035,14 +5680,14 @@ export type operations = {
     };
     requestBody: {
       content: {
-        "application/json": components["schemas"]["StableDiffusion1ModelCheckpointConfig"] | components["schemas"]["StableDiffusion1ModelDiffusersConfig"] | components["schemas"]["VaeModelConfig"] | components["schemas"]["LoRAModelConfig"] | components["schemas"]["ControlNetModelConfig"] | components["schemas"]["TextualInversionModelConfig"] | components["schemas"]["StableDiffusion2ModelCheckpointConfig"] | components["schemas"]["StableDiffusion2ModelDiffusersConfig"];
+        "application/json": components["schemas"]["StableDiffusion1ModelCheckpointConfig"] | components["schemas"]["StableDiffusion1ModelDiffusersConfig"] | components["schemas"]["VaeModelConfig"] | components["schemas"]["LoRAModelConfig"] | components["schemas"]["ControlNetModelConfig"] | components["schemas"]["TextualInversionModelConfig"] | components["schemas"]["StableDiffusion2ModelCheckpointConfig"] | components["schemas"]["StableDiffusion2ModelDiffusersConfig"] | components["schemas"]["StableDiffusionXLModelCheckpointConfig"] | components["schemas"]["StableDiffusionXLModelDiffusersConfig"];
       };
     };
     responses: {
       /** @description The model was updated successfully */
       200: {
         content: {
-          "application/json": components["schemas"]["StableDiffusion1ModelCheckpointConfig"] | components["schemas"]["StableDiffusion1ModelDiffusersConfig"] | components["schemas"]["VaeModelConfig"] | components["schemas"]["LoRAModelConfig"] | components["schemas"]["ControlNetModelConfig"] | components["schemas"]["TextualInversionModelConfig"] | components["schemas"]["StableDiffusion2ModelCheckpointConfig"] | components["schemas"]["StableDiffusion2ModelDiffusersConfig"];
+          "application/json": components["schemas"]["StableDiffusion1ModelCheckpointConfig"] | components["schemas"]["StableDiffusion1ModelDiffusersConfig"] | components["schemas"]["VaeModelConfig"] | components["schemas"]["LoRAModelConfig"] | components["schemas"]["ControlNetModelConfig"] | components["schemas"]["TextualInversionModelConfig"] | components["schemas"]["StableDiffusion2ModelCheckpointConfig"] | components["schemas"]["StableDiffusion2ModelDiffusersConfig"] | components["schemas"]["StableDiffusionXLModelCheckpointConfig"] | components["schemas"]["StableDiffusionXLModelDiffusersConfig"];
         };
       };
       /** @description Bad request */
@@ -5073,13 +5718,15 @@ export type operations = {
       /** @description The model imported successfully */
       201: {
         content: {
-          "application/json": components["schemas"]["StableDiffusion1ModelCheckpointConfig"] | components["schemas"]["StableDiffusion1ModelDiffusersConfig"] | components["schemas"]["VaeModelConfig"] | components["schemas"]["LoRAModelConfig"] | components["schemas"]["ControlNetModelConfig"] | components["schemas"]["TextualInversionModelConfig"] | components["schemas"]["StableDiffusion2ModelCheckpointConfig"] | components["schemas"]["StableDiffusion2ModelDiffusersConfig"];
+          "application/json": components["schemas"]["StableDiffusion1ModelCheckpointConfig"] | components["schemas"]["StableDiffusion1ModelDiffusersConfig"] | components["schemas"]["VaeModelConfig"] | components["schemas"]["LoRAModelConfig"] | components["schemas"]["ControlNetModelConfig"] | components["schemas"]["TextualInversionModelConfig"] | components["schemas"]["StableDiffusion2ModelCheckpointConfig"] | components["schemas"]["StableDiffusion2ModelDiffusersConfig"] | components["schemas"]["StableDiffusionXLModelCheckpointConfig"] | components["schemas"]["StableDiffusionXLModelDiffusersConfig"];
         };
       };
       /** @description The model could not be found */
       404: never;
       /** @description There is already a model corresponding to this path or repo_id */
       409: never;
+      /** @description Unrecognized file/folder format */
+      415: never;
       /** @description Validation Error */
       422: {
         content: {
@@ -5097,14 +5744,14 @@ export type operations = {
   add_model: {
     requestBody: {
       content: {
-        "application/json": components["schemas"]["StableDiffusion1ModelCheckpointConfig"] | components["schemas"]["StableDiffusion1ModelDiffusersConfig"] | components["schemas"]["VaeModelConfig"] | components["schemas"]["LoRAModelConfig"] | components["schemas"]["ControlNetModelConfig"] | components["schemas"]["TextualInversionModelConfig"] | components["schemas"]["StableDiffusion2ModelCheckpointConfig"] | components["schemas"]["StableDiffusion2ModelDiffusersConfig"];
+        "application/json": components["schemas"]["StableDiffusion1ModelCheckpointConfig"] | components["schemas"]["StableDiffusion1ModelDiffusersConfig"] | components["schemas"]["VaeModelConfig"] | components["schemas"]["LoRAModelConfig"] | components["schemas"]["ControlNetModelConfig"] | components["schemas"]["TextualInversionModelConfig"] | components["schemas"]["StableDiffusion2ModelCheckpointConfig"] | components["schemas"]["StableDiffusion2ModelDiffusersConfig"] | components["schemas"]["StableDiffusionXLModelCheckpointConfig"] | components["schemas"]["StableDiffusionXLModelDiffusersConfig"];
       };
     };
     responses: {
       /** @description The model added successfully */
       201: {
         content: {
-          "application/json": components["schemas"]["StableDiffusion1ModelCheckpointConfig"] | components["schemas"]["StableDiffusion1ModelDiffusersConfig"] | components["schemas"]["VaeModelConfig"] | components["schemas"]["LoRAModelConfig"] | components["schemas"]["ControlNetModelConfig"] | components["schemas"]["TextualInversionModelConfig"] | components["schemas"]["StableDiffusion2ModelCheckpointConfig"] | components["schemas"]["StableDiffusion2ModelDiffusersConfig"];
+          "application/json": components["schemas"]["StableDiffusion1ModelCheckpointConfig"] | components["schemas"]["StableDiffusion1ModelDiffusersConfig"] | components["schemas"]["VaeModelConfig"] | components["schemas"]["LoRAModelConfig"] | components["schemas"]["ControlNetModelConfig"] | components["schemas"]["TextualInversionModelConfig"] | components["schemas"]["StableDiffusion2ModelCheckpointConfig"] | components["schemas"]["StableDiffusion2ModelDiffusersConfig"] | components["schemas"]["StableDiffusionXLModelCheckpointConfig"] | components["schemas"]["StableDiffusionXLModelDiffusersConfig"];
         };
       };
       /** @description The model could not be found */
@@ -5144,7 +5791,7 @@ export type operations = {
       /** @description Model converted successfully */
       200: {
         content: {
-          "application/json": components["schemas"]["StableDiffusion1ModelCheckpointConfig"] | components["schemas"]["StableDiffusion1ModelDiffusersConfig"] | components["schemas"]["VaeModelConfig"] | components["schemas"]["LoRAModelConfig"] | components["schemas"]["ControlNetModelConfig"] | components["schemas"]["TextualInversionModelConfig"] | components["schemas"]["StableDiffusion2ModelCheckpointConfig"] | components["schemas"]["StableDiffusion2ModelDiffusersConfig"];
+          "application/json": components["schemas"]["StableDiffusion1ModelCheckpointConfig"] | components["schemas"]["StableDiffusion1ModelDiffusersConfig"] | components["schemas"]["VaeModelConfig"] | components["schemas"]["LoRAModelConfig"] | components["schemas"]["ControlNetModelConfig"] | components["schemas"]["TextualInversionModelConfig"] | components["schemas"]["StableDiffusion2ModelCheckpointConfig"] | components["schemas"]["StableDiffusion2ModelDiffusersConfig"] | components["schemas"]["StableDiffusionXLModelCheckpointConfig"] | components["schemas"]["StableDiffusionXLModelDiffusersConfig"];
         };
       };
       /** @description Bad request */
@@ -5233,7 +5880,7 @@ export type operations = {
       /** @description Model converted successfully */
       200: {
         content: {
-          "application/json": components["schemas"]["StableDiffusion1ModelCheckpointConfig"] | components["schemas"]["StableDiffusion1ModelDiffusersConfig"] | components["schemas"]["VaeModelConfig"] | components["schemas"]["LoRAModelConfig"] | components["schemas"]["ControlNetModelConfig"] | components["schemas"]["TextualInversionModelConfig"] | components["schemas"]["StableDiffusion2ModelCheckpointConfig"] | components["schemas"]["StableDiffusion2ModelDiffusersConfig"];
+          "application/json": components["schemas"]["StableDiffusion1ModelCheckpointConfig"] | components["schemas"]["StableDiffusion1ModelDiffusersConfig"] | components["schemas"]["VaeModelConfig"] | components["schemas"]["LoRAModelConfig"] | components["schemas"]["ControlNetModelConfig"] | components["schemas"]["TextualInversionModelConfig"] | components["schemas"]["StableDiffusion2ModelCheckpointConfig"] | components["schemas"]["StableDiffusion2ModelDiffusersConfig"] | components["schemas"]["StableDiffusionXLModelCheckpointConfig"] | components["schemas"]["StableDiffusionXLModelDiffusersConfig"];
         };
       };
       /** @description Incompatible models */

invokeai/frontend/web/src/services/api/types.d.ts

@@ -47,10 +47,12 @@ export type TextualInversionModelConfig =
   components['schemas']['TextualInversionModelConfig'];
 export type DiffusersModelConfig =
   | components['schemas']['StableDiffusion1ModelDiffusersConfig']
-  | components['schemas']['StableDiffusion2ModelDiffusersConfig'];
+  | components['schemas']['StableDiffusion2ModelDiffusersConfig']
+  | components['schemas']['StableDiffusionXLModelDiffusersConfig'];
 export type CheckpointModelConfig =
   | components['schemas']['StableDiffusion1ModelCheckpointConfig']
-  | components['schemas']['StableDiffusion2ModelCheckpointConfig'];
+  | components['schemas']['StableDiffusion2ModelCheckpointConfig']
+  | components['schemas']['StableDiffusionXLModelCheckpointConfig'];
 export type MainModelConfig = DiffusersModelConfig | CheckpointModelConfig;
 export type AnyModelConfig =
   | LoRAModelConfig

pyproject.toml

@@ -38,7 +38,7 @@ dependencies = [
   "albumentations",
   "click",
   "clip_anytorch",          # replacing "clip @ https://github.com/openai/CLIP/archive/eaa22acb90a5876642d0507623e859909230a52d.zip",
-  "compel>=1.2.1",
+  "compel==2.0.0rc2",
   "controlnet-aux>=0.0.6",
   "timm==0.6.13",           # needed to override timm latest in controlnet_aux, see  https://github.com/isl-org/ZoeDepth/issues/26
   "datasets",