[Community] Add SDE Drag pipeline (#6105)

* Add community pipeline: sde_drag.py * Update README.md * Update README.md Update example code and visual example * Update sde_drag.py Update code example.
huggingface · Dec 14, 2023 · c46711e · c46711e
1 parent 1d686ba
commit c46711e
Show file tree

Hide file tree

Showing 2 changed files with 634 additions and 0 deletions.
diff --git a/examples/community/README.md b/examples/community/README.md
@@ -48,6 +48,7 @@ prompt-to-prompt | change parts of a prompt and retain image structure (see [pap
 |   Latent Consistency Pipeline                                                                                                    | Implementation of [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://arxiv.org/abs/2310.04378)                                                                                                                                                                                                                                                                                                                                                                                                                                      | [Latent Consistency Pipeline](#latent-consistency-pipeline)      | - |              [Simian Luo](https://github.com/luosiallen) |
 |   Latent Consistency Img2img Pipeline                                                                                                    | Img2img pipeline for Latent Consistency Models                                                                                                                                                                                                                                                                                                                                                                                                                                    | [Latent Consistency Img2Img Pipeline](#latent-consistency-img2img-pipeline)      | - |              [Logan Zoellner](https://github.com/nagolinc) |
 |   Latent Consistency Interpolation Pipeline                                                                                                    | Interpolate the latent space of Latent Consistency Models with multiple prompts                                                                                                                                                                                                                                                                                                                                                                                                                                    | [Latent Consistency Interpolation Pipeline](#latent-consistency-interpolation-pipeline) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1pK3NrLWJSiJsBynLns1K1-IDTW9zbPvl?usp=sharing) | [Aryan V S](https://github.com/a-r-r-o-w) |
+| SDE Drag Pipeline                                                                                                                         | The pipeline supports drag editing of images using stochastic differential equations                                                                                                                                                                                                                                                                                                                                                                                                                | [SDE Drag Pipeline](#sde-drag-pipeline)                                                     | - | [NieShen](https://github.com/NieShenRuc) [Fengqi Zhu](https://github.com/Monohydroxides) |
 |   Regional Prompting Pipeline                                                                                               | Assign multiple prompts for different regions                                                                                                                                                                                                                                                                                                                                                    |  [Regional Prompting Pipeline](#regional-prompting-pipeline) | - | [hako-mikan](https://github.com/hako-mikan) |
 | LDM3D-sr (LDM3D upscaler)                                                                                                             | Upscale low resolution RGB and depth inputs to high resolution                                                                                                                                                                                                                                                                                                                                                                                                                              | [StableDiffusionUpscaleLDM3D Pipeline](https://github.com/estelleafl/diffusers/tree/ldm3d_upscaler_community/examples/community#stablediffusionupscaleldm3d-pipeline)                                                                             | -                                                                                                                                                                                                             |                                                        [Estelle Aflalo](https://github.com/estelleafl) |
 | AnimateDiff ControlNet Pipeline                                                                                                    | Combines AnimateDiff with precise motion control using ControlNets                                                                                                                                                                                                                                                                                                                                                                                                                                    | [AnimateDiff ControlNet Pipeline](#animatediff-controlnet-pipeline) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1SKboYeGjEQmQPWoFC0aLYpBlYdHXkvAu?usp=sharing) | [Aryan V S](https://github.com/a-r-r-o-w) and [Edoardo Botta](https://github.com/EdoardoBotta) |
@@ -2986,3 +2987,42 @@ def image_grid(imgs, save_path=None):
 image_grid(images, save_path="./outputs/")
 ```
  ![output_example](https://github.com/PRIS-CV/DemoFusion/blob/main/output_example.png)
+
+### SDE Drag pipeline
+
+This pipeline provides drag-and-drop image editing using stochastic differential equations. It enables image editing by inputting prompt, image, mask_image, source_points, and target_points.
+
+![SDE Drag Image](https://github.com/huggingface/diffusers/assets/75928535/bd54f52f-f002-4951-9934-b2a4592771a5)
+
+See [paper](https://arxiv.org/abs/2311.01410), [paper page](https://ml-gsai.github.io/SDE-Drag-demo/), [original repo](https://github.com/ML-GSAI/SDE-Drag) for more infomation.
+
+```py
+import PIL
+import torch
+from diffusers import DDIMScheduler, DiffusionPipeline
+
+# Load the pipeline
+model_path = "runwayml/stable-diffusion-v1-5"
+scheduler = DDIMScheduler.from_pretrained(model_path, subfolder="scheduler")
+pipe = DiffusionPipeline.from_pretrained(model_path, scheduler=scheduler, custom_pipeline="sde_drag")
+pipe.to('cuda')
+
+# To save GPU memory, torch.float16 can be used, but it may compromise image quality.
+# If not training LoRA, please avoid using torch.float16
+# pipe.to(torch.float16)
+
+# Provide prompt, image, mask image, and the starting and target points for drag editing.
+prompt = "prompt of the image"
+image = PIL.Image.open('/path/to/image')
+mask_image = PIL.Image.open('/path/to/mask_image')
+source_points = [[123, 456]]
+target_points = [[234, 567]]
+
+# train_lora is optional, and in most cases, using train_lora can better preserve consistency with the original image.
+pipe.train_lora(prompt, image)
+
+output = pipe(prompt, image, mask_image, source_points, target_points)
+output_image = PIL.Image.fromarray(output)
+output_image.save("./output.png")
+
+```