Instructions to use bytedance-research/ATI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use bytedance-research/ATI 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("bytedance-research/ATI", 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
Add library_name and link to code
#1
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,13 +1,15 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
language:
|
| 4 |
-
- en
|
| 5 |
base_model:
|
| 6 |
- Wan-AI/Wan2.1-I2V-14B-480P
|
|
|
|
|
|
|
|
|
|
| 7 |
pipeline_tag: image-to-video
|
| 8 |
tags:
|
| 9 |
- videogen
|
|
|
|
| 10 |
---
|
|
|
|
| 11 |
# ATI: Any Trajectory Instruction for Controllable Video Generation
|
| 12 |
|
| 13 |
<div align="center">
|
|
@@ -24,7 +26,7 @@ tags:
|
|
| 24 |
|
| 25 |
[](https://youtu.be/76jjPT0f8Hs)
|
| 26 |
|
| 27 |
-
This is the repo for Wan2.1 ATI (Any Trajectory Instruction for Controllable Video Generation), a trajectory-based motion control framework that unifies object, local and camera movements in video generation. This repo is based on [Wan2.1 offical implementation](https://github.com/Wan-Video/Wan2.1).
|
| 28 |
|
| 29 |
## Install
|
| 30 |
|
|
@@ -65,8 +67,6 @@ cp -r ./Wan2.1-I2V-14B-480P/google ./Wan2.1-ATI-14B-480P/
|
|
| 65 |
|
| 66 |
## Run
|
| 67 |
|
| 68 |
-
Frist download the ATI Wan2.1 from our HuggingFace Page.
|
| 69 |
-
|
| 70 |
We provide a demo sript to run ATI.
|
| 71 |
|
| 72 |
```
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
| 2 |
base_model:
|
| 3 |
- Wan-AI/Wan2.1-I2V-14B-480P
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
license: apache-2.0
|
| 7 |
pipeline_tag: image-to-video
|
| 8 |
tags:
|
| 9 |
- videogen
|
| 10 |
+
library_name: diffusers
|
| 11 |
---
|
| 12 |
+
|
| 13 |
# ATI: Any Trajectory Instruction for Controllable Video Generation
|
| 14 |
|
| 15 |
<div align="center">
|
|
|
|
| 26 |
|
| 27 |
[](https://youtu.be/76jjPT0f8Hs)
|
| 28 |
|
| 29 |
+
This is the repo for Wan2.1 ATI (Any Trajectory Instruction for Controllable Video Generation), a trajectory-based motion control framework that unifies object, local and camera movements in video generation. This repo is based on [Wan2.1 offical implementation](https://github.com/Wan-Video/Wan2.1). Code: https://github.com/bytedance/ATI
|
| 30 |
|
| 31 |
## Install
|
| 32 |
|
|
|
|
| 67 |
|
| 68 |
## Run
|
| 69 |
|
|
|
|
|
|
|
| 70 |
We provide a demo sript to run ATI.
|
| 71 |
|
| 72 |
```
|