Merge branch 'main' into install/install-ip-adapters

invokeai/app/api/routers/models.py

@@ -146,7 +146,8 @@ async def update_model(
 async def import_model(
     location: str = Body(description="A model path, repo_id or URL to import"),
     prediction_type: Optional[Literal["v_prediction", "epsilon", "sample"]] = Body(
-        description="Prediction type for SDv2 checkpoint files", default="v_prediction"
+        description="Prediction type for SDv2 checkpoints and rare SDv1 checkpoints",
+        default=None,
     ),
 ) -> ImportModelResponse:
     """Add a model using its local path, repo_id, or remote URL. Model characteristics will be probed and configured automatically"""
@@ -155,6 +156,8 @@ async def import_model(
     prediction_types = {x.value: x for x in SchedulerPredictionType}
     logger = ApiDependencies.invoker.services.logger
 
+    print(f"DEBUG: prediction_type = {prediction_type}")
+
     try:
         installed_models = ApiDependencies.invoker.services.model_manager.heuristic_import(
             items_to_import=items_to_import, prediction_type_helper=lambda x: prediction_types.get(prediction_type)

invokeai/app/api_app.py

@@ -8,7 +8,6 @@ app_config.parse_args()
 
 if True:  # hack to make flake8 happy with imports coming after setting up the config
     import asyncio
-    import logging
     import mimetypes
     import socket
     from inspect import signature

invokeai/backend/install/model_install_backend.py

@@ -47,8 +47,14 @@ Config_preamble = """
 
 LEGACY_CONFIGS = {
     BaseModelType.StableDiffusion1: {
-        ModelVariantType.Normal: "v1-inference.yaml",
-        ModelVariantType.Inpaint: "v1-inpainting-inference.yaml",
+        ModelVariantType.Normal: {
+            SchedulerPredictionType.Epsilon: "v1-inference.yaml",
+            SchedulerPredictionType.VPrediction: "v1-inference-v.yaml",
+        },
+        ModelVariantType.Inpaint: {
+            SchedulerPredictionType.Epsilon: "v1-inpainting-inference.yaml",
+            SchedulerPredictionType.VPrediction: "v1-inpainting-inference-v.yaml",
+        },
     },
     BaseModelType.StableDiffusion2: {
         ModelVariantType.Normal: {
@@ -302,7 +308,7 @@ class ModelInstall(object):
             location = download_with_resume(url, Path(staging))
             if not location:
                 logger.error(f"Unable to download {url}. Skipping.")
-            info = ModelProbe().heuristic_probe(location)
+            info = ModelProbe().heuristic_probe(location, self.prediction_helper)
             dest = self.config.models_path / info.base_type.value / info.model_type.value / location.name
             dest.parent.mkdir(parents=True, exist_ok=True)
             models_path = shutil.move(location, dest)
@@ -409,7 +415,7 @@ class ModelInstall(object):
                     possible_conf = path.with_suffix(".yaml")
                     if possible_conf.exists():
                         legacy_conf = str(self.relative_to_root(possible_conf))
-                    elif info.base_type == BaseModelType.StableDiffusion2:
+                    elif info.base_type in [BaseModelType.StableDiffusion1, BaseModelType.StableDiffusion2]:
                         legacy_conf = Path(
                             self.config.legacy_conf_dir,
                             LEGACY_CONFIGS[info.base_type][info.variant_type][info.prediction_type],

invokeai/backend/model_management/convert_ckpt_to_diffusers.py

@@ -1279,12 +1279,12 @@ def download_from_original_stable_diffusion_ckpt(
         extract_ema = original_config["model"]["params"]["use_ema"]
 
     if (
-        model_version == BaseModelType.StableDiffusion2
+        model_version in [BaseModelType.StableDiffusion2, BaseModelType.StableDiffusion1]
         and original_config["model"]["params"].get("parameterization") == "v"
     ):
         prediction_type = "v_prediction"
         upcast_attention = True
-        image_size = 768
+        image_size = 768 if model_version == BaseModelType.StableDiffusion2 else 512
     else:
         prediction_type = "epsilon"
         upcast_attention = False

invokeai/backend/model_management/model_probe.py

@@ -90,8 +90,7 @@ class ModelProbe(object):
         to place it somewhere in the models directory hierarchy. If the model is
         already loaded into memory, you may provide it as model in order to avoid
         opening it a second time. The prediction_type_helper callable is a function that receives
-        the path to the model and returns the BaseModelType. It is called to distinguish
-        between V2-Base and V2-768 SD models.
+        the path to the model and returns the SchedulerPredictionType.
         """
         if model_path:
             format_type = "diffusers" if model_path.is_dir() else "checkpoint"
@@ -305,25 +304,36 @@ class PipelineCheckpointProbe(CheckpointProbeBase):
         else:
             raise InvalidModelException("Cannot determine base type")
 
-    def get_scheduler_prediction_type(self) -> SchedulerPredictionType:
+    def get_scheduler_prediction_type(self) -> Optional[SchedulerPredictionType]:
+        """Return model prediction type."""
+        # if there is a .yaml associated with this checkpoint, then we do not need
+        # to probe for the prediction type as it will be ignored.
+        if self.checkpoint_path and self.checkpoint_path.with_suffix(".yaml").exists():
+            return None
+
         type = self.get_base_type()
-        if type == BaseModelType.StableDiffusion1:
-            return SchedulerPredictionType.Epsilon
-        checkpoint = self.checkpoint
-        state_dict = self.checkpoint.get("state_dict") or checkpoint
-        key_name = "model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_k.weight"
-        if key_name in state_dict and state_dict[key_name].shape[-1] == 1024:
-            if "global_step" in checkpoint:
-                if checkpoint["global_step"] == 220000:
-                    return SchedulerPredictionType.Epsilon
-                elif checkpoint["global_step"] == 110000:
-                    return SchedulerPredictionType.VPrediction
-            if (
-                self.checkpoint_path and self.helper and not self.checkpoint_path.with_suffix(".yaml").exists()
-            ):  # if a .yaml config file exists, then this step not needed
-                return self.helper(self.checkpoint_path)
-            else:
-                return None
+        if type == BaseModelType.StableDiffusion2:
+            checkpoint = self.checkpoint
+            state_dict = self.checkpoint.get("state_dict") or checkpoint
+            key_name = "model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_k.weight"
+            if key_name in state_dict and state_dict[key_name].shape[-1] == 1024:
+                if "global_step" in checkpoint:
+                    if checkpoint["global_step"] == 220000:
+                        return SchedulerPredictionType.Epsilon
+                    elif checkpoint["global_step"] == 110000:
+                        return SchedulerPredictionType.VPrediction
+            if self.helper and self.checkpoint_path:
+                if helper_guess := self.helper(self.checkpoint_path):
+                    return helper_guess
+            return SchedulerPredictionType.VPrediction  # a guess for sd2 ckpts
+
+        elif type == BaseModelType.StableDiffusion1:
+            if self.helper and self.checkpoint_path:
+                if helper_guess := self.helper(self.checkpoint_path):
+                    return helper_guess
+            return SchedulerPredictionType.Epsilon  # a reasonable guess for sd1 ckpts
+        else:
+            return None
 
 
 class VaeCheckpointProbe(CheckpointProbeBase):

invokeai/backend/model_management/model_search.py

@@ -71,7 +71,13 @@ class ModelSearch(ABC):
                 if any(
                     [
                         (path / x).exists()
-                        for x in {"config.json", "model_index.json", "learned_embeds.bin", "pytorch_lora_weights.bin"}
+                        for x in {
+                            "config.json",
+                            "model_index.json",
+                            "learned_embeds.bin",
+                            "pytorch_lora_weights.bin",
+                            "image_encoder.txt",
+                        }
                     ]
                 ):
                     try:

invokeai/configs/stable-diffusion/v1-inference-v.yaml

@@ -0,0 +1,80 @@
+model:
+  base_learning_rate: 1.0e-04
+  target: invokeai.backend.models.diffusion.ddpm.LatentDiffusion
+  params:
+    parameterization: "v"
+    linear_start: 0.00085
+    linear_end: 0.0120
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    first_stage_key: "jpg"
+    cond_stage_key: "txt"
+    image_size: 64
+    channels: 4
+    cond_stage_trainable: false   # Note: different from the one we trained before
+    conditioning_key: crossattn
+    monitor: val/loss_simple_ema
+    scale_factor: 0.18215
+    use_ema: False
+
+    scheduler_config: # 10000 warmup steps
+      target: invokeai.backend.stable_diffusion.lr_scheduler.LambdaLinearScheduler
+      params:
+        warm_up_steps: [ 10000 ]
+        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
+        f_start: [ 1.e-6 ]
+        f_max: [ 1. ]
+        f_min: [ 1. ]
+
+    personalization_config:
+      target: invokeai.backend.stable_diffusion.embedding_manager.EmbeddingManager
+      params:
+        placeholder_strings: ["*"]
+        initializer_words: ['sculpture']
+        per_image_tokens: false
+        num_vectors_per_token: 1
+        progressive_words: False
+
+    unet_config:
+      target: invokeai.backend.stable_diffusion.diffusionmodules.openaimodel.UNetModel
+      params:
+        image_size: 32 # unused
+        in_channels: 4
+        out_channels: 4
+        model_channels: 320
+        attention_resolutions: [ 4, 2, 1 ]
+        num_res_blocks: 2
+        channel_mult: [ 1, 2, 4, 4 ]
+        num_heads: 8
+        use_spatial_transformer: True
+        transformer_depth: 1
+        context_dim: 768
+        use_checkpoint: True
+        legacy: False
+
+    first_stage_config:
+      target: invokeai.backend.stable_diffusion.autoencoder.AutoencoderKL
+      params:
+        embed_dim: 4
+        monitor: val/rec_loss
+        ddconfig:
+          double_z: true
+          z_channels: 4
+          resolution: 256
+          in_channels: 3
+          out_ch: 3
+          ch: 128
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+        lossconfig:
+          target: torch.nn.Identity
+
+    cond_stage_config:
+      target: invokeai.backend.stable_diffusion.encoders.modules.WeightedFrozenCLIPEmbedder

invokeai/frontend/web/dist/locales/en.json

@@ -574,7 +574,7 @@
         "onnxModels": "Onnx",
         "pathToCustomConfig": "Path To Custom Config",
         "pickModelType": "Pick Model Type",
-        "predictionType": "Prediction Type (for Stable Diffusion 2.x Models only)",
+        "predictionType": "Prediction Type (for Stable Diffusion 2.x Models and occasional Stable Diffusion 1.x Models)",
         "quickAdd": "Quick Add",
         "repo_id": "Repo ID",
         "repoIDValidationMsg": "Online repository of your model",

invokeai/frontend/web/public/locales/en.json

@@ -655,7 +655,7 @@
         "onnxModels": "Onnx",
         "pathToCustomConfig": "Path To Custom Config",
         "pickModelType": "Pick Model Type",
-        "predictionType": "Prediction Type (for Stable Diffusion 2.x Models only)",
+        "predictionType": "Prediction Type (for Stable Diffusion 2.x Models and occasional Stable Diffusion 1.x Models)",
         "quickAdd": "Quick Add",
         "repo_id": "Repo ID",
         "repoIDValidationMsg": "Online repository of your model",

invokeai/frontend/web/src/common/components/IAIMantineMultiSelect.tsx

@@ -44,7 +44,7 @@ const IAIMantineMultiSelect = forwardRef((props: IAIMultiSelectProps, ref) => {
 
   return (
     <Tooltip label={tooltip} placement="top" hasArrow isOpen={true}>
-      <FormControl ref={ref} isDisabled={disabled}>
+      <FormControl ref={ref} isDisabled={disabled} position="static">
         {label && <FormLabel>{label}</FormLabel>}
         <MultiSelect
           ref={inputRef}

invokeai/frontend/web/src/common/components/IAIMantineSearchableSelect.tsx

@@ -70,11 +70,10 @@ const IAIMantineSearchableSelect = forwardRef((props: IAISelectProps, ref) => {
 
   return (
     <Tooltip label={tooltip} placement="top" hasArrow>
-      <FormControl ref={ref} isDisabled={disabled}>
+      <FormControl ref={ref} isDisabled={disabled} position="static">
         {label && <FormLabel>{label}</FormLabel>}
         <Select
           ref={inputRef}
-          withinPortal
           disabled={disabled}
           searchValue={searchValue}
           onSearchChange={setSearchValue}

invokeai/frontend/web/src/common/components/IAIMantineSelect.tsx

@@ -22,7 +22,12 @@ const IAIMantineSelect = forwardRef((props: IAISelectProps, ref) => {
 
   return (
     <Tooltip label={tooltip} placement="top" hasArrow>
-      <FormControl ref={ref} isRequired={required} isDisabled={disabled}>
+      <FormControl
+        ref={ref}
+        isRequired={required}
+        isDisabled={disabled}
+        position="static"
+      >
         <FormLabel>{label}</FormLabel>
         <Select disabled={disabled} ref={inputRef} styles={styles} {...rest} />
       </FormControl>

invokeai/frontend/web/src/features/gallery/components/CurrentImage/CurrentImageButtons.tsx

@@ -287,7 +287,7 @@ const CurrentImageButtons = (props: CurrentImageButtonsProps) => {
             icon={<FaSeedling />}
             tooltip={`${t('parameters.useSeed')} (S)`}
             aria-label={`${t('parameters.useSeed')} (S)`}
-            isDisabled={!metadata?.seed}
+            isDisabled={metadata?.seed === null || metadata?.seed === undefined}
             onClick={handleUseSeed}
           />
           <IAIIconButton