Instructions to use FrancisRing/StableAnimator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use FrancisRing/StableAnimator with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("FrancisRing/StableAnimator", dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,21 +12,21 @@ StableAnimator: High-Quality Identity-Preserving Human Image Animation
|
|
| 12 |
[<sup>1</sup>Fudan University; <sup>2</sup>Microsoft Research Asia; <sup>3</sup>Huya Inc; <sup>4</sup>Carnegie Mellon University]
|
| 13 |
|
| 14 |
<p align="center">
|
| 15 |
-
<img src="assets/figures/case-47.gif" width="
|
| 16 |
-
<img src="assets/figures/case-61.gif" width="
|
| 17 |
-
<img src="assets/figures/case-45.gif" width="
|
| 18 |
-
<img src="assets/figures/case-46.gif" width="
|
| 19 |
-
<img src="assets/figures/case-5.gif" width="
|
| 20 |
-
<img src="assets/figures/case-17.gif" width="
|
| 21 |
<br/>
|
| 22 |
<span>Pose-driven Human image animations generated by StableAnimator, showing its power to synthesize <b>high-fidelity</b> and <b>ID-preserving videos</b>. All animations are <b>directly synthesized by StableAnimator without the use of any face-related post-processing tools</b>, such as the face-swapping tool FaceFusion or face restoration models like GFP-GAN and CodeFormer.</span>
|
| 23 |
</p>
|
| 24 |
|
| 25 |
<p align="center">
|
| 26 |
-
<img src="assets/figures/case-35.gif" width="
|
| 27 |
-
<img src="assets/figures/case-42.gif" width="
|
| 28 |
-
<img src="assets/figures/case-18.gif" width="
|
| 29 |
-
<img src="assets/figures/case-24.gif" width="
|
| 30 |
<br/>
|
| 31 |
<span>Comparison results between StableAnimator and state-of-the-art (SOTA) human image animation models highlight the superior performance of StableAnimator in delivering <b>high-fidelity, identity-preserving human image animation</b>.</span>
|
| 32 |
</p>
|
|
|
|
| 12 |
[<sup>1</sup>Fudan University; <sup>2</sup>Microsoft Research Asia; <sup>3</sup>Huya Inc; <sup>4</sup>Carnegie Mellon University]
|
| 13 |
|
| 14 |
<p align="center">
|
| 15 |
+
<img src="assets/figures/case-47.gif" width="512" />
|
| 16 |
+
<img src="assets/figures/case-61.gif" width="512" />
|
| 17 |
+
<img src="assets/figures/case-45.gif" width="512" />
|
| 18 |
+
<img src="assets/figures/case-46.gif" width="512" />
|
| 19 |
+
<img src="assets/figures/case-5.gif" width="512" />
|
| 20 |
+
<img src="assets/figures/case-17.gif" width="512" />
|
| 21 |
<br/>
|
| 22 |
<span>Pose-driven Human image animations generated by StableAnimator, showing its power to synthesize <b>high-fidelity</b> and <b>ID-preserving videos</b>. All animations are <b>directly synthesized by StableAnimator without the use of any face-related post-processing tools</b>, such as the face-swapping tool FaceFusion or face restoration models like GFP-GAN and CodeFormer.</span>
|
| 23 |
</p>
|
| 24 |
|
| 25 |
<p align="center">
|
| 26 |
+
<img src="assets/figures/case-35.gif" width="512" />
|
| 27 |
+
<img src="assets/figures/case-42.gif" width="512" />
|
| 28 |
+
<img src="assets/figures/case-18.gif" width="512" />
|
| 29 |
+
<img src="assets/figures/case-24.gif" width="512" />
|
| 30 |
<br/>
|
| 31 |
<span>Comparison results between StableAnimator and state-of-the-art (SOTA) human image animation models highlight the superior performance of StableAnimator in delivering <b>high-fidelity, identity-preserving human image animation</b>.</span>
|
| 32 |
</p>
|