Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into lstein/bugfix/compel

Browse Source
This commit is contained in:
Eugene Brodsky
2023-05-12 08:22:18 -04:00
committed by GitHub
parent 95d4bd3012 4270e7ae25
commit af060188bd
78 changed files with 674 additions and 559 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
invokeai/backend/args.py
View File

@ -108,17 +108,20 @@ APP_VERSION = invokeai.version.__version__
SAMPLER_CHOICES = [
"ddim",
"k_dpm_2_a",
"k_dpm_2",
"k_dpmpp_2_a",
"k_dpmpp_2",
"k_euler_a",
"k_euler",
"k_heun",
"k_lms",
"plms",
# diffusers:
"ddpm",
"deis",
"lms",
"pndm",
"heun",
"euler",
"euler_k",
"euler_a",
"kdpm_2",
"kdpm_2_a",
"dpmpp_2s",
"dpmpp_2m",
"dpmpp_2m_k",
"unipc",
]
PRECISION_CHOICES = [
@ -631,7 +634,7 @@ class Args(object):
choices=SAMPLER_CHOICES,
metavar="SAMPLER_NAME",
help=f'Set the default sampler. Supported samplers: {", ".join(SAMPLER_CHOICES)}',
default="k_lms",
default="lms",
)
render_group.add_argument(
"--log_tokenization",

26
invokeai/backend/generate.py
View File

@ -37,6 +37,7 @@ from .safety_checker import SafetyChecker
from .prompting import get_uc_and_c_and_ec
from .prompting.conditioning import log_tokenization
from .stable_diffusion import HuggingFaceConceptsLibrary
from .stable_diffusion.schedulers import SCHEDULER_MAP
from .util import choose_precision, choose_torch_device
def fix_func(orig):
@ -141,7 +142,7 @@ class Generate:
model=None,
conf="configs/models.yaml",
embedding_path=None,
sampler_name="k_lms",
sampler_name="lms",
ddim_eta=0.0, # deterministic
full_precision=False,
precision="auto",
@ -1047,29 +1048,12 @@ class Generate:
def _set_scheduler(self):
default = self.model.scheduler
# See https://github.com/huggingface/diffusers/issues/277#issuecomment-1371428672
scheduler_map = dict(
ddim=diffusers.DDIMScheduler,
dpmpp_2=diffusers.DPMSolverMultistepScheduler,
k_dpm_2=diffusers.KDPM2DiscreteScheduler,
k_dpm_2_a=diffusers.KDPM2AncestralDiscreteScheduler,
# DPMSolverMultistepScheduler is technically not `k_` anything, as it is neither
# the k-diffusers implementation nor included in EDM (Karras 2022), but we can
# provide an alias for compatibility.
k_dpmpp_2=diffusers.DPMSolverMultistepScheduler,
k_euler=diffusers.EulerDiscreteScheduler,
k_euler_a=diffusers.EulerAncestralDiscreteScheduler,
k_heun=diffusers.HeunDiscreteScheduler,
k_lms=diffusers.LMSDiscreteScheduler,
plms=diffusers.PNDMScheduler,
)
if self.sampler_name in scheduler_map:
sampler_class = scheduler_map[self.sampler_name]
if self.sampler_name in SCHEDULER_MAP:
sampler_class, sampler_extra_config = SCHEDULER_MAP[self.sampler_name]
msg = (
f"Setting Sampler to {self.sampler_name} ({sampler_class.__name__})"
)
self.sampler = sampler_class.from_config(self.model.scheduler.config)
self.sampler = sampler_class.from_config({**self.model.scheduler.config, **sampler_extra_config})
else:
msg = (
f" Unsupported Sampler: {self.sampler_name} "+

26
invokeai/backend/generator/base.py
View File

@ -31,6 +31,7 @@ from ..util.util import rand_perlin_2d
from ..safety_checker import SafetyChecker
from ..prompting.conditioning import get_uc_and_c_and_ec
from ..stable_diffusion.diffusers_pipeline import StableDiffusionGeneratorPipeline
from ..stable_diffusion.schedulers import SCHEDULER_MAP
downsampling = 8
@ -71,19 +72,6 @@ class InvokeAIGeneratorOutput:
# we are interposing a wrapper around the original Generator classes so that
# old code that calls Generate will continue to work.
class InvokeAIGenerator(metaclass=ABCMeta):
scheduler_map = dict(
ddim=diffusers.DDIMScheduler,
dpmpp_2=diffusers.DPMSolverMultistepScheduler,
k_dpm_2=diffusers.KDPM2DiscreteScheduler,
k_dpm_2_a=diffusers.KDPM2AncestralDiscreteScheduler,
k_dpmpp_2=diffusers.DPMSolverMultistepScheduler,
k_euler=diffusers.EulerDiscreteScheduler,
k_euler_a=diffusers.EulerAncestralDiscreteScheduler,
k_heun=diffusers.HeunDiscreteScheduler,
k_lms=diffusers.LMSDiscreteScheduler,
plms=diffusers.PNDMScheduler,
)
def __init__(self,
model_info: dict,
params: InvokeAIGeneratorBasicParams=InvokeAIGeneratorBasicParams(),
@ -175,14 +163,20 @@ class InvokeAIGenerator(metaclass=ABCMeta):
'''
Return list of all the schedulers that we currently handle.
'''
return list(self.scheduler_map.keys())
return list(SCHEDULER_MAP.keys())
def load_generator(self, model: StableDiffusionGeneratorPipeline, generator_class: Type[Generator]):
return generator_class(model, self.params.precision)
def get_scheduler(self, scheduler_name:str, model: StableDiffusionGeneratorPipeline)->Scheduler:
scheduler_class = self.scheduler_map.get(scheduler_name,'ddim')
scheduler = scheduler_class.from_config(model.scheduler.config)
scheduler_class, scheduler_extra_config = SCHEDULER_MAP.get(scheduler_name, SCHEDULER_MAP['ddim'])
scheduler_config = model.scheduler.config
if "_backup" in scheduler_config:
scheduler_config = scheduler_config["_backup"]
scheduler_config = {**scheduler_config, **scheduler_extra_config, "_backup": scheduler_config}
scheduler = scheduler_class.from_config(scheduler_config)
# hack copied over from generate.py
if not hasattr(scheduler, 'uses_inpainting_model'):
scheduler.uses_inpainting_model = lambda: False

3
invokeai/backend/model_management/convert_ckpt_to_diffusers.py
View File

@ -47,6 +47,7 @@ from diffusers import (
LDMTextToImagePipeline,
LMSDiscreteScheduler,
PNDMScheduler,
UniPCMultistepScheduler,
StableDiffusionPipeline,
UNet2DConditionModel,
)
@ -1209,6 +1210,8 @@ def load_pipeline_from_original_stable_diffusion_ckpt(
scheduler = EulerAncestralDiscreteScheduler.from_config(scheduler.config)
elif scheduler_type == "dpm":
scheduler = DPMSolverMultistepScheduler.from_config(scheduler.config)
elif scheduler_type == 'unipc':
scheduler = UniPCMultistepScheduler.from_config(scheduler.config)
elif scheduler_type == "ddim":
scheduler = scheduler
else:

14
invokeai/backend/model_management/model_manager.py
View File

@ -30,7 +30,7 @@ from diffusers import (
UNet2DConditionModel,
SchedulerMixin,
logging as dlogging,
)
)
from huggingface_hub import scan_cache_dir
from omegaconf import OmegaConf
from omegaconf.dictconfig import DictConfig
@ -68,7 +68,7 @@ class SDModelComponent(Enum):
scheduler="scheduler"
safety_checker="safety_checker"
feature_extractor="feature_extractor"
DEFAULT_MAX_MODELS = 2
class ModelManager(object):
@ -182,7 +182,7 @@ class ModelManager(object):
vae from the model currently in the GPU.
"""
return self._get_sub_model(model_name, SDModelComponent.vae)
def get_model_tokenizer(self, model_name: str=None)->CLIPTokenizer:
"""Given a model name identified in models.yaml, load the model into
GPU if necessary and return its assigned CLIPTokenizer. If no
@ -190,12 +190,12 @@ class ModelManager(object):
currently in the GPU.
"""
return self._get_sub_model(model_name, SDModelComponent.tokenizer)
def get_model_unet(self, model_name: str=None)->UNet2DConditionModel:
"""Given a model name identified in models.yaml, load the model into
GPU if necessary and return its assigned UNet2DConditionModel. If no model
name is provided, return the UNet from the model
currently in the GPU.
currently in the GPU.
"""
return self._get_sub_model(model_name, SDModelComponent.unet)
@ -222,7 +222,7 @@ class ModelManager(object):
currently in the GPU.
"""
return self._get_sub_model(model_name, SDModelComponent.scheduler)
def _get_sub_model(
self,
model_name: str=None,
@ -1228,7 +1228,7 @@ class ModelManager(object):
sha.update(chunk)
hash = sha.hexdigest()
toc = time.time()
self.logger.debug(f"sha256 = {hash} ({count} files hashed in", "%4.2fs)" % (toc - tic))
self.logger.debug(f"sha256 = {hash} ({count} files hashed in {toc - tic:4.2f}s)")
with open(hashpath, "w") as f:
f.write(hash)
return hash

33
invokeai/backend/stable_diffusion/diffusers_pipeline.py
View File

@ -509,10 +509,13 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
run_id=None,
callback: Callable[[PipelineIntermediateState], None] = None,
) -> tuple[torch.Tensor, Optional[AttentionMapSaver]]:
if self.scheduler.config.get("cpu_only", False):
scheduler_device = torch.device('cpu')
else:
scheduler_device = self._model_group.device_for(self.unet)
if timesteps is None:
self.scheduler.set_timesteps(
num_inference_steps, device=self._model_group.device_for(self.unet)
)
self.scheduler.set_timesteps(num_inference_steps, device=scheduler_device)
timesteps = self.scheduler.timesteps
infer_latents_from_embeddings = GeneratorToCallbackinator(
self.generate_latents_from_embeddings, PipelineIntermediateState
@ -726,12 +729,8 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
noise: torch.Tensor,
run_id=None,
callback=None,
) -> InvokeAIStableDiffusionPipelineOutput:
timesteps, _ = self.get_img2img_timesteps(
num_inference_steps,
strength,
device=self._model_group.device_for(self.unet),
)
) -> InvokeAIStableDiffusionPipelineOutput:
timesteps, _ = self.get_img2img_timesteps(num_inference_steps, strength)
result_latents, result_attention_maps = self.latents_from_embeddings(
latents=initial_latents if strength < 1.0 else torch.zeros_like(
initial_latents, device=initial_latents.device, dtype=initial_latents.dtype
@ -757,13 +756,19 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
return self.check_for_safety(output, dtype=conditioning_data.dtype)
def get_img2img_timesteps(
self, num_inference_steps: int, strength: float, device
self, num_inference_steps: int, strength: float, device=None
) -> (torch.Tensor, int):
img2img_pipeline = StableDiffusionImg2ImgPipeline(**self.components)
assert img2img_pipeline.scheduler is self.scheduler
img2img_pipeline.scheduler.set_timesteps(num_inference_steps, device=device)
if self.scheduler.config.get("cpu_only", False):
scheduler_device = torch.device('cpu')
else:
scheduler_device = self._model_group.device_for(self.unet)
img2img_pipeline.scheduler.set_timesteps(num_inference_steps, device=scheduler_device)
timesteps, adjusted_steps = img2img_pipeline.get_timesteps(
num_inference_steps, strength, device=device
num_inference_steps, strength, device=scheduler_device
)
# Workaround for low strength resulting in zero timesteps.
# TODO: submit upstream fix for zero-step img2img
@ -797,9 +802,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
if init_image.dim() == 3:
init_image = init_image.unsqueeze(0)
timesteps, _ = self.get_img2img_timesteps(
num_inference_steps, strength, device=device
)
timesteps, _ = self.get_img2img_timesteps(num_inference_steps, strength)
# 6. Prepare latent variables
# can't quite use upstream StableDiffusionImg2ImgPipeline.prepare_latents

1
invokeai/backend/stable_diffusion/schedulers/__init__.py Normal file
View File

@ -0,0 +1 @@
from .schedulers import SCHEDULER_MAP

22
invokeai/backend/stable_diffusion/schedulers/schedulers.py Normal file
View File

@ -0,0 +1,22 @@
from diffusers import DDIMScheduler, DPMSolverMultistepScheduler, KDPM2DiscreteScheduler, \
KDPM2AncestralDiscreteScheduler, EulerDiscreteScheduler, EulerAncestralDiscreteScheduler, \
HeunDiscreteScheduler, LMSDiscreteScheduler, PNDMScheduler, UniPCMultistepScheduler, \
DPMSolverSinglestepScheduler, DEISMultistepScheduler, DDPMScheduler
SCHEDULER_MAP = dict(
ddim=(DDIMScheduler, dict()),
ddpm=(DDPMScheduler, dict()),
deis=(DEISMultistepScheduler, dict()),
lms=(LMSDiscreteScheduler, dict()),
pndm=(PNDMScheduler, dict()),
heun=(HeunDiscreteScheduler, dict()),
euler=(EulerDiscreteScheduler, dict(use_karras_sigmas=False)),
euler_k=(EulerDiscreteScheduler, dict(use_karras_sigmas=True)),
euler_a=(EulerAncestralDiscreteScheduler, dict()),
kdpm_2=(KDPM2DiscreteScheduler, dict()),
kdpm_2_a=(KDPM2AncestralDiscreteScheduler, dict()),
dpmpp_2s=(DPMSolverSinglestepScheduler, dict()),
dpmpp_2m=(DPMSolverMultistepScheduler, dict(use_karras_sigmas=False)),
dpmpp_2m_k=(DPMSolverMultistepScheduler, dict(use_karras_sigmas=True)),
unipc=(UniPCMultistepScheduler, dict(cpu_only=True))
)

23
invokeai/backend/web/modules/parameters.py
View File

@ -4,17 +4,20 @@ from .parse_seed_weights import parse_seed_weights
SAMPLER_CHOICES = [
"ddim",
"k_dpm_2_a",
"k_dpm_2",
"k_dpmpp_2_a",
"k_dpmpp_2",
"k_euler_a",
"k_euler",
"k_heun",
"k_lms",
"plms",
# diffusers:
"ddpm",
"deis",
"lms",
"pndm",
"heun",
"euler",
"euler_k",
"euler_a",
"kdpm_2",
"kdpm_2_a",
"dpmpp_2s",
"dpmpp_2m",
"dpmpp_2m_k",
"unipc",
]