Skip to content

GitLab

Unverified Commit 6549b04e authored by Steven Liu's avatar Steven Liu Committed by GitHub
Browse files

[docs] AutoPipeline (#12160) 

* refresh

* feedback

* feedback

* supported models

* fix
parent 130fd8df
Show whitespace changes
Inline Side-by-side
Showing with 29 additions and 85 deletions
docs/source/en/tutorials/autopipeline.md
View file @ 6549b04e
...@@ -12,112 +12,56 @@ specific language governing permissions and limitations under the License. ...@@ -12,112 +12,56 @@ specific language governing permissions and limitations under the License.
# AutoPipeline # AutoPipeline
Diffusers provides many pipelines for basic tasks like generating images, videos, audio, and inpainting. On top of these, there are specialized pipelines for adapters and features like upscaling, super-resolution, and more. Different pipeline classes can even use the same checkpoint because they share the same pretrained model! With so many different pipelines, it can be overwhelming to know which pipeline class to use. [AutoPipeline](../api/models/auto_model) is a *task-and-model* pipeline that automatically selects the correct pipeline subclass based on the task. It handles the complexity of loading different pipeline subclasses without needing to know the specific pipeline subclass name.
The [AutoPipeline](../api/pipelines/auto_pipeline) class is designed to simplify the variety of pipelines in Diffusers. It is a generic *task-first* pipeline that lets you focus on a task ([`AutoPipelineForText2Image`], [`AutoPipelineForImage2Image`], and [`AutoPipelineForInpainting`]) without needing to know the specific pipeline class. The [AutoPipeline](../api/pipelines/auto_pipeline) automatically detects the correct pipeline class to use. This is unlike [`DiffusionPipeline`], a *model-only* pipeline that automatically selects the pipeline subclass based on the model.
For example, let's use the [dreamlike-art/dreamlike-photoreal-2.0](https://hf.co/dreamlike-art/dreamlike-photoreal-2.0) checkpoint. [`AutoPipelineForImage2Image`] returns a specific pipeline subclass, (for example, [`StableDiffusionXLImg2ImgPipeline`]), which can only be used for image-to-image tasks.
Under the hood, [AutoPipeline](../api/pipelines/auto_pipeline):
1. Detects a `"stable-diffusion"` class from the [model_index.json](https://hf.co/dreamlike-art/dreamlike-photoreal-2.0/blob/main/model_index.json) file.
2. Depending on the task you're interested in, it loads the [`StableDiffusionPipeline`], [`StableDiffusionImg2ImgPipeline`], or [`StableDiffusionInpaintPipeline`]. Any parameter (`strength`, `num_inference_steps`, etc.) you would pass to these specific pipelines can also be passed to the [AutoPipeline](../api/pipelines/auto_pipeline).
<hfoptions id="autopipeline">
<hfoption id="text-to-image">
```py ```py
from diffusers import AutoPipelineForText2Image
import torch import torch
pipe_txt2img = AutoPipelineForText2Image.from_pretrained(
"dreamlike-art/dreamlike-photoreal-2.0", torch_dtype=torch.float16, use_safetensors=True
).to("cuda")
prompt = "cinematic photo of Godzilla eating sushi with a cat in a izakaya, 35mm photograph, film, professional, 4k, highly detailed"
generator = torch.Generator(device="cpu").manual_seed(37)
image = pipe_txt2img(prompt, generator=generator).images[0]
image
```
<div class="flex justify-center">
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/autopipeline-text2img.png"/>
</div>
</hfoption>
<hfoption id="image-to-image">
```py
from diffusers import AutoPipelineForImage2Image from diffusers import AutoPipelineForImage2Image
from diffusers.utils import load_image
import torch
pipe_img2img = AutoPipelineForImage2Image.from_pretrained(
"dreamlike-art/dreamlike-photoreal-2.0", torch_dtype=torch.float16, use_safetensors=True
).to("cuda")
init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/autopipeline-text2img.png")
prompt = "cinematic photo of Godzilla eating burgers with a cat in a fast food restaurant, 35mm photograph, film, professional, 4k, highly detailed"
generator = torch.Generator(device="cpu").manual_seed(53)
image = pipe_img2img(prompt, image=init_image, generator=generator).images[0]
image
```
Notice how the [dreamlike-art/dreamlike-photoreal-2.0](https://hf.co/dreamlike-art/dreamlike-photoreal-2.0) checkpoint is used for both text-to-image and image-to-image tasks? To save memory and avoid loading the checkpoint twice, use the [`~DiffusionPipeline.from_pipe`] method.
```py pipeline = AutoPipelineForImage2Image.from_pretrained(
pipe_img2img = AutoPipelineForImage2Image.from_pipe(pipe_txt2img).to("cuda") "RunDiffusion/Juggernaut-XL-v9", torch_dtype=torch.bfloat16, device_map="cuda",
image = pipeline(prompt, image=init_image, generator=generator).images[0] )
image print(pipeline)
"StableDiffusionXLImg2ImgPipeline {
"_class_name": "StableDiffusionXLImg2ImgPipeline",
...
"
``` ```
You can learn more about the [`~DiffusionPipeline.from_pipe`] method in the [Reuse a pipeline](../using-diffusers/loading#reuse-a-pipeline) guide. Loading the same model with [`DiffusionPipeline`] returns the [`StableDiffusionXLPipeline`] subclass. It can be used for text-to-image, image-to-image, or inpainting tasks depending on the inputs.
<div class="flex justify-center">
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/autopipeline-img2img.png"/>
</div>
</hfoption>
<hfoption id="inpainting">
```py ```py
from diffusers import AutoPipelineForInpainting
from diffusers.utils import load_image
import torch import torch
from diffusers import DiffusionPipeline
pipeline = AutoPipelineForInpainting.from_pretrained( pipeline = DiffusionPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, use_safetensors=True "RunDiffusion/Juggernaut-XL-v9", torch_dtype=torch.bfloat16, device_map="cuda",
).to("cuda") )
print(pipeline)
init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/autopipeline-img2img.png") "StableDiffusionXLPipeline {
mask_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/autopipeline-mask.png") "_class_name": "StableDiffusionXLPipeline",
...
prompt = "cinematic photo of a owl, 35mm photograph, film, professional, 4k, highly detailed" "
generator = torch.Generator(device="cpu").manual_seed(38)
image = pipeline(prompt, image=init_image, mask_image=mask_image, generator=generator, strength=0.4).images[0]
image
``` ```
<div class="flex justify-center"> Check the [mappings](https://github.com/huggingface/diffusers/blob/130fd8df54f24ffb006d84787b598d8adc899f23/src/diffusers/pipelines/auto_pipeline.py#L114) to see whether a model is supported or not.
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/autopipeline-inpaint.png"/>
</div>
</hfoption> Trying to load an unsupported model returns an error.
</hfoptions>
## Unsupported checkpoints
The [AutoPipeline](../api/pipelines/auto_pipeline) supports [Stable Diffusion](../api/pipelines/stable_diffusion/overview), [Stable Diffusion XL](../api/pipelines/stable_diffusion/stable_diffusion_xl), [ControlNet](../api/pipelines/controlnet), [Kandinsky 2.1](../api/pipelines/kandinsky.md), [Kandinsky 2.2](../api/pipelines/kandinsky_v22), and [DeepFloyd IF](../api/pipelines/deepfloyd_if) checkpoints.
If you try to load an unsupported checkpoint, you'll get an error.
```py ```py
from diffusers import AutoPipelineForImage2Image
import torch import torch
from diffusers import AutoPipelineForImage2Image
pipeline = AutoPipelineForImage2Image.from_pretrained( pipeline = AutoPipelineForImage2Image.from_pretrained(
"openai/shap-e-img2img", torch_dtype=torch.float16, use_safetensors=True "openai/shap-e-img2img", torch_dtype=torch.float16,
) )
"ValueError: AutoPipeline can't find a pipeline linked to ShapEImg2ImgPipeline for None" "ValueError: AutoPipeline can't find a pipeline linked to ShapEImg2ImgPipeline for None"
``` ```
There are three types of [AutoPipeline](../api/models/auto_model) classes, [`AutoPipelineForText2Image`], [`AutoPipelineForImage2Image`] and [`AutoPipelineForInpainting`]. Each of these classes have a predefined mapping, linking a pipeline to their task-specific subclass.
When [`~AutoPipelineForText2Image.from_pretrained`] is called, it extracts the class name from the `model_index.json` file and selects the appropriate pipeline subclass for the task based on the mapping.
\ No newline at end of file
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