Skip to content

GitLab

"...python/git@developer.sourcefind.cn:change/sglang.git" did not exist on "f556ac8bd8f6cfad85ce4da6d6b10c775cb43278"
Unverified Commit 22ea35cf authored by Steven Liu's avatar Steven Liu Committed by GitHub
Browse files

[docs] DiffEdit guide (#4722) 

* first draft

* minor edits
parent 5c404f20
Show whitespace changes
Inline Side-by-side
Showing with 298 additions and 327 deletions
docs/source/en/_toctree.yml
View file @ 22ea35cf
...@@ -66,6 +66,8 @@ ...@@ -66,6 +66,8 @@
title: Stable Diffusion XL title: Stable Diffusion XL
- local: using-diffusers/controlnet - local: using-diffusers/controlnet
title: ControlNet title: ControlNet
- local: using-diffusers/diffedit
title: DiffEdit
- local: using-diffusers/distilled_sd - local: using-diffusers/distilled_sd
title: Distilled Stable Diffusion inference title: Distilled Stable Diffusion inference
- local: using-diffusers/reproducibility - local: using-diffusers/reproducibility
......
docs/source/en/api/pipelines/diffedit.md
View file @ 22ea35cf
...@@ -24,321 +24,25 @@ This pipeline was contributed by [clarencechen](https://github.com/clarencechen) ...@@ -24,321 +24,25 @@ This pipeline was contributed by [clarencechen](https://github.com/clarencechen)
## Tips ## Tips
* The pipeline can generate masks that can be fed into other inpainting pipelines. Check out the code examples below to know more. * The pipeline can generate masks that can be fed into other inpainting pipelines.
* In order to generate an image using this pipeline, both an image mask (manually specified or generated using `generate_mask`) * In order to generate an image using this pipeline, both an image mask (source and target prompts can be manually specified or generated, and passed to [`~StableDiffusionDiffEditPipeline.generate_mask`])
and a set of partially inverted latents (generated using `invert`) _must_ be provided as arguments when calling the pipeline to generate the final edited image. and a set of partially inverted latents (generated using [`~StableDiffusionDiffEditPipeline.invert`]) _must_ be provided as arguments when calling the pipeline to generate the final edited image.
Refer to the code examples below for more details. * The function [`~StableDiffusionDiffEditPipeline.generate_mask`] exposes two prompt arguments, `source_prompt` and `target_prompt`
* The function `generate_mask` exposes two prompt arguments, `source_prompt` and `target_prompt`,
that let you control the locations of the semantic edits in the final image to be generated. Let's say, that let you control the locations of the semantic edits in the final image to be generated. Let's say,
you wanted to translate from "cat" to "dog". In this case, the edit direction will be "cat -> dog". To reflect you wanted to translate from "cat" to "dog". In this case, the edit direction will be "cat -> dog". To reflect
this in the generated mask, you simply have to set the embeddings related to the phrases including "cat" to this in the generated mask, you simply have to set the embeddings related to the phrases including "cat" to
`source_prompt_embeds` and "dog" to `target_prompt_embeds`. Refer to the code example below for more details. `source_prompt` and "dog" to `target_prompt`.
* When generating partially inverted latents using `invert`, assign a caption or text embedding describing the * When generating partially inverted latents using `invert`, assign a caption or text embedding describing the
overall image to the `prompt` argument to help guide the inverse latent sampling process. In most cases, the overall image to the `prompt` argument to help guide the inverse latent sampling process. In most cases, the
source concept is sufficently descriptive to yield good results, but feel free to explore alternatives. source concept is sufficently descriptive to yield good results, but feel free to explore alternatives.
Please refer to [this code example](#generating-image-captions-for-inversion) for more details.
* When calling the pipeline to generate the final edited image, assign the source concept to `negative_prompt` * When calling the pipeline to generate the final edited image, assign the source concept to `negative_prompt`
and the target concept to `prompt`. Taking the above example, you simply have to set the embeddings related to and the target concept to `prompt`. Taking the above example, you simply have to set the embeddings related to
the phrases including "cat" to `negative_prompt_embeds` and "dog" to `prompt_embeds`. Refer to the code example the phrases including "cat" to `negative_prompt` and "dog" to `prompt`.
below for more details.
* If you wanted to reverse the direction in the example above, i.e., "dog -> cat", then it's recommended to: * If you wanted to reverse the direction in the example above, i.e., "dog -> cat", then it's recommended to:
* Swap the `source_prompt` and `target_prompt` in the arguments to `generate_mask`. * Swap the `source_prompt` and `target_prompt` in the arguments to `generate_mask`.
* Change the input prompt for `invert` to include "dog". * Change the input prompt in [`~StableDiffusionDiffEditPipeline.invert`] to include "dog".
* Swap the `prompt` and `negative_prompt` in the arguments to call the pipeline to generate the final edited image. * Swap the `prompt` and `negative_prompt` in the arguments to call the pipeline to generate the final edited image.
* Note that the source and target prompts, or their corresponding embeddings, can also be automatically generated. Please, refer to [this discussion](#generating-source-and-target-embeddings) for more details. * The source and target prompts, or their corresponding embeddings, can also be automatically generated. Please refer to the [DiffEdit](/using-diffusers/diffedit) guide for more details.
## Usage example
### Based on an input image with a caption
When the pipeline is conditioned on an input image, we first obtain partially inverted latents from the input image using a
`DDIMInverseScheduler` with the help of a caption. Then we generate an editing mask to identify relevant regions in the image using the source and target prompts. Finally,
the inverted noise and generated mask is used to start the generation process.
First, let's load our pipeline:
```py
import torch
from diffusers import DDIMScheduler, DDIMInverseScheduler, StableDiffusionDiffEditPipeline
sd_model_ckpt = "stabilityai/stable-diffusion-2-1"
pipeline = StableDiffusionDiffEditPipeline.from_pretrained(
sd_model_ckpt,
torch_dtype=torch.float16,
safety_checker=None,
)
pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
pipeline.inverse_scheduler = DDIMInverseScheduler.from_config(pipeline.scheduler.config)
pipeline.enable_model_cpu_offload()
pipeline.enable_vae_slicing()
generator = torch.manual_seed(0)
```
Then, we load an input image to edit using our method:
```py
from diffusers.utils import load_image
img_url = "https://github.com/Xiang-cd/DiffEdit-stable-diffusion/raw/main/assets/origin.png"
raw_image = load_image(img_url).convert("RGB").resize((768, 768))
```
Then, we employ the source and target prompts to generate the editing mask:
```py
# See the "Generating source and target embeddings" section below to
# automate the generation of these captions with a pre-trained model like Flan-T5 as explained below.
source_prompt = "a bowl of fruits"
target_prompt = "a basket of fruits"
mask_image = pipeline.generate_mask(
image=raw_image,
source_prompt=source_prompt,
target_prompt=target_prompt,
generator=generator,
)
```
Then, we employ the caption and the input image to get the inverted latents:
```py
inv_latents = pipeline.invert(prompt=source_prompt, image=raw_image, generator=generator).latents
```
Now, generate the image with the inverted latents and semantically generated mask:
```py
image = pipeline(
prompt=target_prompt,
mask_image=mask_image,
image_latents=inv_latents,
generator=generator,
negative_prompt=source_prompt,
).images[0]
image.save("edited_image.png")
```
## Generating image captions for inversion
The authors originally used the source concept prompt as the caption for generating the partially inverted latents. However, we can also leverage open source and public image captioning models for the same purpose.
Below, we provide an end-to-end example with the [BLIP](https://huggingface.co/docs/transformers/model_doc/blip) model
for generating captions.
First, let's load our automatic image captioning model:
```py
import torch
from transformers import BlipForConditionalGeneration, BlipProcessor
captioner_id = "Salesforce/blip-image-captioning-base"
processor = BlipProcessor.from_pretrained(captioner_id)
model = BlipForConditionalGeneration.from_pretrained(captioner_id, torch_dtype=torch.float16, low_cpu_mem_usage=True)
```
Then, we define a utility to generate captions from an input image using the model:
```py
@torch.no_grad()
def generate_caption(images, caption_generator, caption_processor):
text = "a photograph of"
inputs = caption_processor(images, text, return_tensors="pt").to(device="cuda", dtype=caption_generator.dtype)
caption_generator.to("cuda")
outputs = caption_generator.generate(**inputs, max_new_tokens=128)
# offload caption generator
caption_generator.to("cpu")
caption = caption_processor.batch_decode(outputs, skip_special_tokens=True)[0]
return caption
```
Then, we load an input image for conditioning and obtain a suitable caption for it:
```py
from diffusers.utils import load_image
img_url = "https://github.com/Xiang-cd/DiffEdit-stable-diffusion/raw/main/assets/origin.png"
raw_image = load_image(img_url).convert("RGB").resize((768, 768))
caption = generate_caption(raw_image, model, processor)
```
Then, we employ the generated caption and the input image to get the inverted latents:
```py
from diffusers import DDIMInverseScheduler, DDIMScheduler
pipeline = StableDiffusionDiffEditPipeline.from_pretrained(
"stabilityai/stable-diffusion-2-1", torch_dtype=torch.float16
)
pipeline = pipeline.to("cuda")
pipeline.enable_model_cpu_offload()
pipeline.enable_vae_slicing()
pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
pipeline.inverse_scheduler = DDIMInverseScheduler.from_config(pipeline.scheduler.config)
generator = torch.manual_seed(0)
inv_latents = pipeline.invert(prompt=caption, image=raw_image, generator=generator).latents
```
Now, generate the image with the inverted latents and semantically generated mask from our source and target prompts:
```py
source_prompt = "a bowl of fruits"
target_prompt = "a basket of fruits"
mask_image = pipeline.generate_mask(
image=raw_image,
source_prompt=source_prompt,
target_prompt=target_prompt,
generator=generator,
)
image = pipeline(
prompt=target_prompt,
mask_image=mask_image,
image_latents=inv_latents,
generator=generator,
negative_prompt=source_prompt,
).images[0]
image.save("edited_image.png")
```
## Generating source and target embeddings
The authors originally required the user to manually provide the source and target prompts for discovering
edit directions. However, we can also leverage open source and public models for the same purpose.
Below, we provide an end-to-end example with the [Flan-T5](https://huggingface.co/docs/transformers/model_doc/flan-t5) model
for generating source an target embeddings.
**1. Load the generation model**:
```py
import torch
from transformers import AutoTokenizer, T5ForConditionalGeneration
tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-xl")
model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xl", device_map="auto", torch_dtype=torch.float16)
```
**2. Construct a starting prompt**:
```py
source_concept = "bowl"
target_concept = "basket"
source_text = f"Provide a caption for images containing a {source_concept}. "
"The captions should be in English and should be no longer than 150 characters."
target_text = f"Provide a caption for images containing a {target_concept}. "
"The captions should be in English and should be no longer than 150 characters."
```
Here, we're interested in the "bowl -> basket" direction.
**3. Generate prompts**:
We can use a utility like so for this purpose.
```py
@torch.no_grad
def generate_prompts(input_prompt):
input_ids = tokenizer(input_prompt, return_tensors="pt").input_ids.to("cuda")
outputs = model.generate(
input_ids, temperature=0.8, num_return_sequences=16, do_sample=True, max_new_tokens=128, top_k=10
)
return tokenizer.batch_decode(outputs, skip_special_tokens=True)
```
And then we just call it to generate our prompts:
```py
source_prompts = generate_prompts(source_text)
target_prompts = generate_prompts(target_text)
```
We encourage you to play around with the different parameters supported by the
`generate()` method ([documentation](https://huggingface.co/docs/transformers/main/en/main_classes/text_generation#transformers.generation_tf_utils.TFGenerationMixin.generate)) for the generation quality you are looking for.
**4. Load the embedding model**:
Here, we need to use the same text encoder model used by the subsequent Stable Diffusion model.
```py
from diffusers import StableDiffusionDiffEditPipeline
pipeline = StableDiffusionDiffEditPipeline.from_pretrained(
"stabilityai/stable-diffusion-2-1", torch_dtype=torch.float16
)
pipeline = pipeline.to("cuda")
pipeline.enable_model_cpu_offload()
pipeline.enable_vae_slicing()
generator = torch.manual_seed(0)
```
**5. Compute embeddings**:
```py
import torch
@torch.no_grad()
def embed_prompts(sentences, tokenizer, text_encoder, device="cuda"):
embeddings = []
for sent in sentences:
text_inputs = tokenizer(
sent,
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(device), attention_mask=None)[0]
embeddings.append(prompt_embeds)
return torch.concatenate(embeddings, dim=0).mean(dim=0).unsqueeze(0)
source_embeddings = embed_prompts(source_prompts, pipeline.tokenizer, pipeline.text_encoder)
target_embeddings = embed_prompts(target_captions, pipeline.tokenizer, pipeline.text_encoder)
```
And you're done! Now, you can use these embeddings directly while calling the pipeline:
```py
from diffusers import DDIMInverseScheduler, DDIMScheduler
from diffusers.utils import load_image
pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
pipeline.inverse_scheduler = DDIMInverseScheduler.from_config(pipeline.scheduler.config)
img_url = "https://github.com/Xiang-cd/DiffEdit-stable-diffusion/raw/main/assets/origin.png"
raw_image = load_image(img_url).convert("RGB").resize((768, 768))
mask_image = pipeline.generate_mask(
image=raw_image,
source_prompt_embeds=source_embeds,
target_prompt_embeds=target_embeds,
generator=generator,
)
inv_latents = pipeline.invert(
prompt_embeds=source_embeds,
image=raw_image,
generator=generator,
).latents
images = pipeline(
mask_image=mask_image,
image_latents=inv_latents,
prompt_embeds=target_embeddings,
negative_prompt_embeds=source_embeddings,
generator=generator,
).images
images[0].save("edited_image.png")
```
## StableDiffusionDiffEditPipeline ## StableDiffusionDiffEditPipeline
[[autodoc]] StableDiffusionDiffEditPipeline [[autodoc]] StableDiffusionDiffEditPipeline
...@@ -346,3 +50,6 @@ images[0].save("edited_image.png") ...@@ -346,3 +50,6 @@ images[0].save("edited_image.png")
- generate_mask - generate_mask
- invert - invert
- __call__ - __call__
## StableDiffusionPipelineOutput
[[autodoc]] pipelines.stable_diffusion.StableDiffusionPipelineOutput
\ No newline at end of file
docs/source/en/using-diffusers/diffedit.md 0 → 100644
View file @ 22ea35cf
# DiffEdit
[[open-in-colab]]
Image editing typically requires providing a mask of the area to be edited. DiffEdit automatically generates the mask for you based on a text query, making it easier overall to create a mask without image editing software. The DiffEdit algorithm works in three steps:
1. the diffusion model denoises an image conditioned on some query text and reference text which produces different noise estimates for different areas of the image; the difference is used to infer a mask to identify which area of the image needs to be changed to match the query text
2. the input image is encoded into latent space with DDIM
3. the latents are decoded with the diffusion model conditioned on the text query, using the mask as a guide such that pixels outside the mask remain the same as in the input image
This guide will show you how to use DiffEdit to edit images without manually creating a mask.
Before you begin, make sure you have the following libraries installed:
```py
# uncomment to install the necessary libraries in Colab
#!pip install diffusers transformers accelerate safetensors
```
The [`StableDiffusionDiffEditPipeline`] requires an image mask and a set of partially inverted latents. The image mask is generated from the [`~StableDiffusionDiffEditPipeline.generate_mask`] function, and includes two parameters, `source_prompt` and `target_prompt`. These parameters determine what to edit in the image. For example, if you want to change a bowl of *fruits* to a bowl of *pears*, then:
```py
source_prompt = "a bowl of fruits"
target_prompt = "a bowl of pears"
```
The partially inverted latents are generated from the [`~StableDiffusionDiffEditPipeline.invert`] function, and it is generally a good idea to include a `prompt` or *caption* describing the image to help guide the inverse latent sampling process. The caption can often be your `source_prompt`, but feel free to experiment with other text descriptions!
Let's load the pipeline, scheduler, inverse scheduler, and enable some optimizations to reduce memory usage:
```py
import torch
from diffusers import DDIMScheduler, DDIMInverseScheduler, StableDiffusionDiffEditPipeline
pipeline = StableDiffusionDiffEditPipeline.from_pretrained(
"stabilityai/stable-diffusion-2-1",
torch_dtype=torch.float16,
safety_checker=None,
use_safetensors=True,
)
pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
pipeline.inverse_scheduler = DDIMInverseScheduler.from_config(pipeline.scheduler.config)
pipeline.enable_model_cpu_offload()
pipeline.enable_vae_slicing()
```
Load the image to edit:
```py
from diffusers.utils import load_image
img_url = "https://github.com/Xiang-cd/DiffEdit-stable-diffusion/raw/main/assets/origin.png"
raw_image = load_image(img_url).convert("RGB").resize((768, 768))
```
Use the [`~StableDiffusionDiffEditPipeline.generate_mask`] function to generate the image mask. You'll need to pass it the `source_prompt` and `target_prompt` to specify what to edit in the image:
```py
source_prompt = "a bowl of fruits"
target_prompt = "a basket of pears"
mask_image = pipeline.generate_mask(
image=raw_image,
source_prompt=source_prompt,
target_prompt=target_prompt,
)
```
Next, create the inverted latents and pass it a caption describing the image:
```py
inv_latents = pipeline.invert(prompt=source_prompt, image=raw_image).latents
```
Finally, pass the image mask and inverted latents to the pipeline. The `target_prompt` becomes the `prompt` now, and the `source_prompt` is used as the `negative_prompt`:
```py
image = pipeline(
prompt=target_prompt,
mask_image=mask_image,
image_latents=inv_latents,
negative_prompt=source_prompt,
).images[0]
image.save("edited_image.png")
```
<div class="flex gap-4">
<div>
<img class="rounded-xl" src="https://github.com/Xiang-cd/DiffEdit-stable-diffusion/raw/main/assets/origin.png"/>
<figcaption class="mt-2 text-center text-sm text-gray-500">original image</figcaption>
</div>
<div>
<img class="rounded-xl" src="https://github.com/Xiang-cd/DiffEdit-stable-diffusion/blob/main/assets/target.png?raw=true"/>
<figcaption class="mt-2 text-center text-sm text-gray-500">edited image</figcaption>
</div>
</div>
## Generate source and target embeddings
The source and target embeddings can be automatically generated with the [Flan-T5](https://huggingface.co/docs/transformers/model_doc/flan-t5) model instead of creating them manually.
Load the Flan-T5 model and tokenizer from the 🤗 Transformers library:
```py
import torch
from transformers import AutoTokenizer, T5ForConditionalGeneration
tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-xl")
model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xl", device_map="auto", torch_dtype=torch.float16)
```
Provide some initial text to prompt the model to generate the source and target prompts.
```py
source_concept = "bowl"
target_concept = "basket"
source_text = f"Provide a caption for images containing a {source_concept}. "
"The captions should be in English and should be no longer than 150 characters."
target_text = f"Provide a caption for images containing a {target_concept}. "
"The captions should be in English and should be no longer than 150 characters."
```
Next, create a utility function to generate the prompts:
```py
@torch.no_grad
def generate_prompts(input_prompt):
input_ids = tokenizer(input_prompt, return_tensors="pt").input_ids.to("cuda")
outputs = model.generate(
input_ids, temperature=0.8, num_return_sequences=16, do_sample=True, max_new_tokens=128, top_k=10
)
return tokenizer.batch_decode(outputs, skip_special_tokens=True)
source_prompts = generate_prompts(source_text)
target_prompts = generate_prompts(target_text)
print(source_prompts)
print(target_prompts)
```
<Tip>
Check out the [generation strategy](https://huggingface.co/docs/transformers/main/en/generation_strategies) guide if you're interested in learning more about strategies for generating different quality text.
</Tip>
Load the text encoder model used by the [`StableDiffusionDiffEditPipeline`] to encode the text. You'll use the text encoder to compute the text embeddings:
```py
import torch
from diffusers import StableDiffusionDiffEditPipeline
pipeline = StableDiffusionDiffEditPipeline.from_pretrained(
"stabilityai/stable-diffusion-2-1", torch_dtype=torch.float16, use_safetensors=True
).to("cuda")
pipeline.enable_model_cpu_offload()
pipeline.enable_vae_slicing()
@torch.no_grad()
def embed_prompts(sentences, tokenizer, text_encoder, device="cuda"):
embeddings = []
for sent in sentences:
text_inputs = tokenizer(
sent,
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(device), attention_mask=None)[0]
embeddings.append(prompt_embeds)
return torch.concatenate(embeddings, dim=0).mean(dim=0).unsqueeze(0)
source_embeds = embed_prompts(source_prompts, pipeline.tokenizer, pipeline.text_encoder)
target_embeds = embed_prompts(target_prompts, pipeline.tokenizer, pipeline.text_encoder)
```
Finally, pass the embeddings to the [`~StableDiffusionDiffEditPipeline.generate_mask`] and [`~StableDiffusionDiffEditPipeline.invert`] functions, and pipeline to generate the image:
```diff
from diffusers import DDIMInverseScheduler, DDIMScheduler
from diffusers.utils import load_image
pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
pipeline.inverse_scheduler = DDIMInverseScheduler.from_config(pipeline.scheduler.config)
img_url = "https://github.com/Xiang-cd/DiffEdit-stable-diffusion/raw/main/assets/origin.png"
raw_image = load_image(img_url).convert("RGB").resize((768, 768))
mask_image = pipeline.generate_mask(
image=raw_image,
+ source_prompt_embeds=source_embeds,
+ target_prompt_embeds=target_embeds,
)
inv_latents = pipeline.invert(
+ prompt_embeds=source_embeds,
image=raw_image,
).latents
images = pipeline(
mask_image=mask_image,
image_latents=inv_latents,
+ prompt_embeds=target_embeds,
+ negative_prompt_embeds=source_embeds,
).images
images[0].save("edited_image.png")
```
## Generate a caption for inversion
While you can use the `source_prompt` as a caption to help generate the partially inverted latents, you can also use the [BLIP](https://huggingface.co/docs/transformers/model_doc/blip) model to automatically generate a caption.
Load the BLIP model and processor from the 🤗 Transformers library:
```py
import torch
from transformers import BlipForConditionalGeneration, BlipProcessor
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base", torch_dtype=torch.float16, low_cpu_mem_usage=True)
```
Create a utility function to generate a caption from the input image:
```py
@torch.no_grad()
def generate_caption(images, caption_generator, caption_processor):
text = "a photograph of"
inputs = caption_processor(images, text, return_tensors="pt").to(device="cuda", dtype=caption_generator.dtype)
caption_generator.to("cuda")
outputs = caption_generator.generate(**inputs, max_new_tokens=128)
# offload caption generator
caption_generator.to("cpu")
caption = caption_processor.batch_decode(outputs, skip_special_tokens=True)[0]
return caption
```
Load an input image and generate a caption for it using the `generate_caption` function:
```py
from diffusers.utils import load_image
img_url = "https://github.com/Xiang-cd/DiffEdit-stable-diffusion/raw/main/assets/origin.png"
raw_image = load_image(img_url).convert("RGB").resize((768, 768))
caption = generate_caption(raw_image, model, processor)
```
<div class="flex justify-center">
<figure>
<img class="rounded-xl" src="https://github.com/Xiang-cd/DiffEdit-stable-diffusion/raw/main/assets/origin.png"/>
<figcaption class="text-center">generated caption: "a photograph of a bowl of fruit on a table"</figcaption>
</figure>
</div>
Now you can drop the caption into the [`~StableDiffusionDiffEditPipeline.invert`] function to generate the partially inverted latents!
\ No newline at end of file
src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_diffedit.py
View file @ 22ea35cf
...@@ -246,32 +246,30 @@ class StableDiffusionDiffEditPipeline(DiffusionPipeline, TextualInversionLoaderM ...@@ -246,32 +246,30 @@ class StableDiffusionDiffEditPipeline(DiffusionPipeline, TextualInversionLoaderM
This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods
implemented for all pipelines (downloading, saving, running on a particular device, etc.). implemented for all pipelines (downloading, saving, running on a particular device, etc.).
In addition the pipeline inherits the following loading methods: The pipeline also inherits the following loading and saving methods:
- *Textual-Inversion*: [`loaders.TextualInversionLoaderMixin.load_textual_inversion`] - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
- *LoRA*: [`loaders.LoraLoaderMixin.load_lora_weights`] - [`~loaders.LoraLoaderMixin.load_lora_weights`] for loading LoRA weights
- [`~loaders.LoraLoaderMixin.save_lora_weights`] for saving LoRA weights
as well as the following saving methods:
- *LoRA*: [`loaders.LoraLoaderMixin.save_lora_weights`]
Args: Args:
vae ([`AutoencoderKL`]): vae ([`AutoencoderKL`]):
Variational Auto-Encoder (VAE) model to encode and decode images to and from latent representations. Variational Auto-Encoder (VAE) model to encode and decode images to and from latent representations.
text_encoder ([`CLIPTextModel`]): text_encoder ([`~transformers.CLIPTextModel`]):
Frozen text-encoder ([clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14)). Frozen text-encoder ([clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14)).
tokenizer (`CLIPTokenizer`): tokenizer ([`~transformers.CLIPTokenizer`]):
A [`~transformers.CLIPTokenizer`] to tokenize text. A `CLIPTokenizer` to tokenize text.
unet ([`UNet2DConditionModel`]): unet ([`UNet2DConditionModel`]):
A [`UNet2DConditionModel`] to denoise the encoded image latents. A `UNet2DConditionModel` to denoise the encoded image latents.
scheduler ([`SchedulerMixin`]): scheduler ([`SchedulerMixin`]):
A scheduler to be used in combination with `unet` to denoise the encoded image latents. A scheduler to be used in combination with `unet` to denoise the encoded image latents.
inverse_scheduler (`[DDIMInverseScheduler]`): inverse_scheduler ([`DDIMInverseScheduler`]):
A scheduler to be used in combination with `unet` to fill in the unmasked part of the input latents. A scheduler to be used in combination with `unet` to fill in the unmasked part of the input latents.
safety_checker ([`StableDiffusionSafetyChecker`]): safety_checker ([`StableDiffusionSafetyChecker`]):
Classification module that estimates whether generated images could be considered offensive or harmful. Classification module that estimates whether generated images could be considered offensive or harmful.
Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details Please refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for more details
about a model's potential harms. about a model's potential harms.
feature_extractor ([`CLIPImageProcessor`]): feature_extractor ([`~transformers.CLIPImageProcessor`]):
A [`CLIPImageProcessor`] to extract features from generated images; used as inputs to the `safety_checker`. A `CLIPImageProcessor` to extract features from generated images; used as inputs to the `safety_checker`.
""" """
_optional_components = ["safety_checker", "feature_extractor", "inverse_scheduler"] _optional_components = ["safety_checker", "feature_extractor", "inverse_scheduler"]
...@@ -928,7 +926,8 @@ class StableDiffusionDiffEditPipeline(DiffusionPipeline, TextualInversionLoaderM ...@@ -928,7 +926,8 @@ class StableDiffusionDiffEditPipeline(DiffusionPipeline, TextualInversionLoaderM
output_type (`str`, *optional*, defaults to `"pil"`): output_type (`str`, *optional*, defaults to `"pil"`):
The output format of the generated image. Choose between `PIL.Image` or `np.array`. The output format of the generated image. Choose between `PIL.Image` or `np.array`.
cross_attention_kwargs (`dict`, *optional*): cross_attention_kwargs (`dict`, *optional*):
A kwargs dictionary that if specified is passed along to the [`AttentionProcessor`] as defined in A kwargs dictionary that if specified is passed along to the
[`~models.attention_processor.AttnProcessor`] as defined in
[`self.processor`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py). [`self.processor`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
Examples: Examples:
...@@ -1107,9 +1106,9 @@ class StableDiffusionDiffEditPipeline(DiffusionPipeline, TextualInversionLoaderM ...@@ -1107,9 +1106,9 @@ class StableDiffusionDiffEditPipeline(DiffusionPipeline, TextualInversionLoaderM
`Image` or tensor representing an image batch to produce the inverted latents guided by `prompt`. `Image` or tensor representing an image batch to produce the inverted latents guided by `prompt`.
inpaint_strength (`float`, *optional*, defaults to 0.8): inpaint_strength (`float`, *optional*, defaults to 0.8):
Indicates extent of the noising process to run latent inversion. Must be between 0 and 1. When Indicates extent of the noising process to run latent inversion. Must be between 0 and 1. When
`strength` is 1, the inversion process iss ru for the full number of iterations specified in `inpaint_strength` is 1, the inversion process is run for the full number of iterations specified in
`num_inference_steps`. `image` is used as a reference for the inversion process, adding more noise the `num_inference_steps`. `image` is used as a reference for the inversion process, and adding more noise
larger the `strength`. If `strength` is 0, no inpainting occurs. increases `inpaint_strength`. If `inpaint_strength` is 0, no inpainting occurs.
num_inference_steps (`int`, *optional*, defaults to 50): num_inference_steps (`int`, *optional*, defaults to 50):
The number of denoising steps. More denoising steps usually lead to a higher quality image at the The number of denoising steps. More denoising steps usually lead to a higher quality image at the
expense of slower inference. expense of slower inference.
...@@ -1143,12 +1142,13 @@ class StableDiffusionDiffEditPipeline(DiffusionPipeline, TextualInversionLoaderM ...@@ -1143,12 +1142,13 @@ class StableDiffusionDiffEditPipeline(DiffusionPipeline, TextualInversionLoaderM
The frequency at which the `callback` function is called. If not specified, the callback is called at The frequency at which the `callback` function is called. If not specified, the callback is called at
every step. every step.
cross_attention_kwargs (`dict`, *optional*): cross_attention_kwargs (`dict`, *optional*):
A kwargs dictionary that if specified is passed along to the [`AttentionProcessor`] as defined in A kwargs dictionary that if specified is passed along to the
[`~models.attention_processor.AttnProcessor`] as defined in
[`self.processor`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py). [`self.processor`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
lambda_auto_corr (`float`, *optional*, defaults to 20.0): lambda_auto_corr (`float`, *optional*, defaults to 20.0):
Lambda parameter to control auto correction. Lambda parameter to control auto correction.
lambda_kl (`float`, *optional*, defaults to 20.0): lambda_kl (`float`, *optional*, defaults to 20.0):
Lambda parameter to control Kullback–Leibler divergence output. Lambda parameter to control Kullback-Leibler divergence output.
num_reg_steps (`int`, *optional*, defaults to 0): num_reg_steps (`int`, *optional*, defaults to 0):
Number of regularization loss steps. Number of regularization loss steps.
num_auto_corr_rolls (`int`, *optional*, defaults to 5): num_auto_corr_rolls (`int`, *optional*, defaults to 5):
...@@ -1347,10 +1347,10 @@ class StableDiffusionDiffEditPipeline(DiffusionPipeline, TextualInversionLoaderM ...@@ -1347,10 +1347,10 @@ class StableDiffusionDiffEditPipeline(DiffusionPipeline, TextualInversionLoaderM
image_latents (`PIL.Image.Image` or `torch.FloatTensor`): image_latents (`PIL.Image.Image` or `torch.FloatTensor`):
Partially noised image latents from the inversion process to be used as inputs for image generation. Partially noised image latents from the inversion process to be used as inputs for image generation.
inpaint_strength (`float`, *optional*, defaults to 0.8): inpaint_strength (`float`, *optional*, defaults to 0.8):
Indicates extent to inpaint the masked area. Must be between 0 and 1. When `strength` is 1, the Indicates extent to inpaint the masked area. Must be between 0 and 1. When `inpaint_strength` is 1, the
denoising process is run on the masked area for the full number of iterations specified in denoising process is run on the masked area for the full number of iterations specified in
`num_inference_steps`. `image_latents` is used as a reference for the masked area, adding more noise to `num_inference_steps`. `image_latents` is used as a reference for the masked area, and adding more
that region the larger the `strength`. If `strength` is 0, no inpainting occurs. noise to a region increases `inpaint_strength`. If `inpaint_strength` is 0, no inpainting occurs.
num_inference_steps (`int`, *optional*, defaults to 50): num_inference_steps (`int`, *optional*, defaults to 50):
The number of denoising steps. More denoising steps usually lead to a higher quality image at the The number of denoising steps. More denoising steps usually lead to a higher quality image at the
expense of slower inference. expense of slower inference.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment