mirror of
https://github.com/ostris/ai-toolkit.git
synced 2026-01-26 16:39:47 +00:00
Added sd1.5 and 2.1 do the diffusers pipeline flow
This commit is contained in:
Jaret Burkett
@@ -1,7 +1,8 @@
|
||||
from typing import Union, List, Optional, Dict, Any, Tuple, Callable
|
||||
|
||||
import torch
|
||||
from diffusers import StableDiffusionXLPipeline
|
||||
from diffusers import StableDiffusionXLPipeline, StableDiffusionPipeline
|
||||
from diffusers.pipelines.stable_diffusion import StableDiffusionPipelineOutput
|
||||
from diffusers.pipelines.stable_diffusion_xl.pipeline_stable_diffusion_xl import rescale_noise_cfg
|
||||
|
||||
|
||||
@@ -13,10 +14,7 @@ class CustomStableDiffusionXLPipeline(StableDiffusionXLPipeline):
|
||||
self,
|
||||
prompt: Union[str, List[str]] = None,
|
||||
prompt_2: Optional[Union[str, List[str]]] = None,
|
||||
height: Optional[int] = None,
|
||||
width: Optional[int] = None,
|
||||
num_inference_steps: int = 50,
|
||||
denoising_end: Optional[float] = None,
|
||||
guidance_scale: float = 5.0,
|
||||
negative_prompt: Optional[Union[str, List[str]]] = None,
|
||||
negative_prompt_2: Optional[Union[str, List[str]]] = None,
|
||||
@@ -28,16 +26,9 @@ class CustomStableDiffusionXLPipeline(StableDiffusionXLPipeline):
|
||||
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
|
||||
pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
|
||||
negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
|
||||
output_type: Optional[str] = "pil",
|
||||
return_dict: bool = True,
|
||||
callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
|
||||
callback_steps: int = 1,
|
||||
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
|
||||
guidance_rescale: float = 0.0,
|
||||
original_size: Optional[Tuple[int, int]] = None,
|
||||
crops_coords_top_left: Tuple[int, int] = (0, 0),
|
||||
target_size: Optional[Tuple[int, int]] = None,
|
||||
# predict_noise: bool = False,
|
||||
timestep: Optional[int] = None,
|
||||
):
|
||||
r"""
|
||||
@@ -226,8 +217,6 @@ class CustomStableDiffusionXLPipeline(StableDiffusionXLPipeline):
|
||||
# 4. Prepare timesteps
|
||||
self.scheduler.set_timesteps(num_inference_steps, device=device)
|
||||
|
||||
timesteps = self.scheduler.timesteps
|
||||
|
||||
# 5. Prepare latent variables
|
||||
num_channels_latents = self.unet.config.in_channels
|
||||
latents = self.prepare_latents(
|
||||
@@ -245,7 +234,7 @@ class CustomStableDiffusionXLPipeline(StableDiffusionXLPipeline):
|
||||
add_text_embeds = pooled_prompt_embeds
|
||||
add_time_ids = self._get_add_time_ids(
|
||||
original_size, crops_coords_top_left, target_size, dtype=prompt_embeds.dtype
|
||||
).to(device) # TODO DOES NOT CAST ORIGINALLY
|
||||
).to(device) # TODO DOES NOT CAST ORIGINALLY
|
||||
|
||||
if do_classifier_free_guidance:
|
||||
prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds], dim=0)
|
||||
@@ -286,3 +275,260 @@ class CustomStableDiffusionXLPipeline(StableDiffusionXLPipeline):
|
||||
print('Called cpu offload', gpu_id)
|
||||
# fuck off
|
||||
pass
|
||||
|
||||
|
||||
class CustomStableDiffusionPipeline(StableDiffusionPipeline):
|
||||
|
||||
# replace the call so it matches SDXL call so we can use the same code and also stop early
|
||||
def __call__(
|
||||
self,
|
||||
prompt: Union[str, List[str]] = None,
|
||||
prompt_2: Optional[Union[str, List[str]]] = None,
|
||||
height: Optional[int] = None,
|
||||
width: Optional[int] = None,
|
||||
num_inference_steps: int = 50,
|
||||
denoising_end: Optional[float] = None,
|
||||
guidance_scale: float = 5.0,
|
||||
negative_prompt: Optional[Union[str, List[str]]] = None,
|
||||
negative_prompt_2: Optional[Union[str, List[str]]] = None,
|
||||
num_images_per_prompt: Optional[int] = 1,
|
||||
eta: float = 0.0,
|
||||
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
|
||||
latents: Optional[torch.FloatTensor] = None,
|
||||
prompt_embeds: Optional[torch.FloatTensor] = None,
|
||||
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
|
||||
pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
|
||||
negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
|
||||
output_type: Optional[str] = "pil",
|
||||
return_dict: bool = True,
|
||||
callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
|
||||
callback_steps: int = 1,
|
||||
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
|
||||
guidance_rescale: float = 0.0,
|
||||
original_size: Optional[Tuple[int, int]] = None,
|
||||
crops_coords_top_left: Tuple[int, int] = (0, 0),
|
||||
target_size: Optional[Tuple[int, int]] = None,
|
||||
):
|
||||
# 0. Default height and width to unet
|
||||
height = height or self.unet.config.sample_size * self.vae_scale_factor
|
||||
width = width or self.unet.config.sample_size * self.vae_scale_factor
|
||||
|
||||
# 1. Check inputs. Raise error if not correct
|
||||
self.check_inputs(
|
||||
prompt, height, width, callback_steps, negative_prompt, prompt_embeds, negative_prompt_embeds
|
||||
)
|
||||
|
||||
# 2. Define call parameters
|
||||
if prompt is not None and isinstance(prompt, str):
|
||||
batch_size = 1
|
||||
elif prompt is not None and isinstance(prompt, list):
|
||||
batch_size = len(prompt)
|
||||
else:
|
||||
batch_size = prompt_embeds.shape[0]
|
||||
|
||||
device = self._execution_device
|
||||
# here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
|
||||
# of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
|
||||
# corresponds to doing no classifier free guidance.
|
||||
do_classifier_free_guidance = guidance_scale > 1.0
|
||||
|
||||
# 3. Encode input prompt
|
||||
text_encoder_lora_scale = (
|
||||
cross_attention_kwargs.get("scale", None) if cross_attention_kwargs is not None else None
|
||||
)
|
||||
prompt_embeds = self._encode_prompt(
|
||||
prompt,
|
||||
device,
|
||||
num_images_per_prompt,
|
||||
do_classifier_free_guidance,
|
||||
negative_prompt,
|
||||
prompt_embeds=prompt_embeds,
|
||||
negative_prompt_embeds=negative_prompt_embeds,
|
||||
lora_scale=text_encoder_lora_scale,
|
||||
)
|
||||
|
||||
# 4. Prepare timesteps
|
||||
self.scheduler.set_timesteps(num_inference_steps, device=device)
|
||||
timesteps = self.scheduler.timesteps
|
||||
|
||||
# 5. Prepare latent variables
|
||||
num_channels_latents = self.unet.config.in_channels
|
||||
latents = self.prepare_latents(
|
||||
batch_size * num_images_per_prompt,
|
||||
num_channels_latents,
|
||||
height,
|
||||
width,
|
||||
prompt_embeds.dtype,
|
||||
device,
|
||||
generator,
|
||||
latents,
|
||||
)
|
||||
|
||||
# 6. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
|
||||
extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)
|
||||
|
||||
# 7. Denoising loop
|
||||
num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
|
||||
|
||||
# 7.1 Apply denoising_end
|
||||
if denoising_end is not None and type(denoising_end) == float and denoising_end > 0 and denoising_end < 1:
|
||||
discrete_timestep_cutoff = int(
|
||||
round(
|
||||
self.scheduler.config.num_train_timesteps
|
||||
- (denoising_end * self.scheduler.config.num_train_timesteps)
|
||||
)
|
||||
)
|
||||
num_inference_steps = len(list(filter(lambda ts: ts >= discrete_timestep_cutoff, timesteps)))
|
||||
timesteps = timesteps[:num_inference_steps]
|
||||
|
||||
with self.progress_bar(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 = self.scheduler.scale_model_input(latent_model_input, t)
|
||||
|
||||
# predict the noise residual
|
||||
noise_pred = self.unet(
|
||||
latent_model_input,
|
||||
t,
|
||||
encoder_hidden_states=prompt_embeds,
|
||||
cross_attention_kwargs=cross_attention_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 + guidance_scale * (noise_pred_text - noise_pred_uncond)
|
||||
|
||||
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 = self.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) % self.scheduler.order == 0):
|
||||
progress_bar.update()
|
||||
if callback is not None and i % callback_steps == 0:
|
||||
callback(i, t, latents)
|
||||
|
||||
if not output_type == "latent":
|
||||
image = self.vae.decode(latents / self.vae.config.scaling_factor, return_dict=False)[0]
|
||||
image, has_nsfw_concept = self.run_safety_checker(image, device, prompt_embeds.dtype)
|
||||
else:
|
||||
image = latents
|
||||
has_nsfw_concept = None
|
||||
|
||||
if has_nsfw_concept is None:
|
||||
do_denormalize = [True] * image.shape[0]
|
||||
else:
|
||||
do_denormalize = [not has_nsfw for has_nsfw in has_nsfw_concept]
|
||||
|
||||
image = self.image_processor.postprocess(image, output_type=output_type, do_denormalize=do_denormalize)
|
||||
|
||||
# Offload last model to CPU
|
||||
if hasattr(self, "final_offload_hook") and self.final_offload_hook is not None:
|
||||
self.final_offload_hook.offload()
|
||||
|
||||
if not return_dict:
|
||||
return (image, has_nsfw_concept)
|
||||
|
||||
return StableDiffusionPipelineOutput(images=image, nsfw_content_detected=has_nsfw_concept)
|
||||
|
||||
# some of the inputs are to keep it compatible with sdx
|
||||
def predict_noise(
|
||||
self,
|
||||
prompt: Union[str, List[str]] = None,
|
||||
prompt_2: Optional[Union[str, List[str]]] = None,
|
||||
num_inference_steps: int = 50,
|
||||
guidance_scale: float = 5.0,
|
||||
negative_prompt: Optional[Union[str, List[str]]] = None,
|
||||
negative_prompt_2: Optional[Union[str, List[str]]] = None,
|
||||
num_images_per_prompt: Optional[int] = 1,
|
||||
eta: float = 0.0,
|
||||
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
|
||||
latents: Optional[torch.FloatTensor] = None,
|
||||
prompt_embeds: Optional[torch.FloatTensor] = None,
|
||||
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
|
||||
pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
|
||||
negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
|
||||
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
|
||||
guidance_rescale: float = 0.0,
|
||||
crops_coords_top_left: Tuple[int, int] = (0, 0),
|
||||
timestep: Optional[int] = None,
|
||||
):
|
||||
|
||||
# 0. Default height and width to unet
|
||||
height = self.unet.config.sample_size * self.vae_scale_factor
|
||||
width = self.unet.config.sample_size * self.vae_scale_factor
|
||||
|
||||
# 2. Define call parameters
|
||||
if prompt is not None and isinstance(prompt, str):
|
||||
batch_size = 1
|
||||
elif prompt is not None and isinstance(prompt, list):
|
||||
batch_size = len(prompt)
|
||||
else:
|
||||
batch_size = prompt_embeds.shape[0]
|
||||
|
||||
device = self._execution_device
|
||||
# here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
|
||||
# of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
|
||||
# corresponds to doing no classifier free guidance.
|
||||
do_classifier_free_guidance = guidance_scale > 1.0
|
||||
|
||||
# 3. Encode input prompt
|
||||
text_encoder_lora_scale = (
|
||||
cross_attention_kwargs.get("scale", None) if cross_attention_kwargs is not None else None
|
||||
)
|
||||
prompt_embeds = self._encode_prompt(
|
||||
prompt,
|
||||
device,
|
||||
num_images_per_prompt,
|
||||
do_classifier_free_guidance,
|
||||
negative_prompt,
|
||||
prompt_embeds=prompt_embeds,
|
||||
negative_prompt_embeds=negative_prompt_embeds,
|
||||
lora_scale=text_encoder_lora_scale,
|
||||
)
|
||||
|
||||
# 4. Prepare timesteps
|
||||
self.scheduler.set_timesteps(num_inference_steps, device=device)
|
||||
|
||||
# 5. Prepare latent variables
|
||||
num_channels_latents = self.unet.config.in_channels
|
||||
latents = self.prepare_latents(
|
||||
batch_size * num_images_per_prompt,
|
||||
num_channels_latents,
|
||||
height,
|
||||
width,
|
||||
prompt_embeds.dtype,
|
||||
device,
|
||||
generator,
|
||||
latents,
|
||||
)
|
||||
|
||||
# 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 = self.scheduler.scale_model_input(latent_model_input, timestep)
|
||||
|
||||
# predict the noise residual
|
||||
noise_pred = self.unet(
|
||||
latent_model_input,
|
||||
timestep,
|
||||
encoder_hidden_states=prompt_embeds,
|
||||
cross_attention_kwargs=cross_attention_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 + guidance_scale * (noise_pred_text - noise_pred_uncond)
|
||||
|
||||
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)
|
||||
|
||||
return noise_pred
|
||||
|
||||
Reference in New Issue
Block a user