Image-to-Video
Diffusers
Safetensors
video-generation
audio-video-generation
reference-to-video
long-video
multi-shot
dmd
Instructions to use jdopensource/JoyAI-Echo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use jdopensource/JoyAI-Echo 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("jdopensource/JoyAI-Echo", 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
Gelercat commited on
Commit ·
9ec5d87
1
Parent(s): ebc7a0a
docs: align model card with Echo 1.5 release
Browse files
README.md
CHANGED
|
@@ -114,7 +114,7 @@ cd JoyAI-Echo/echo_longvideo
|
|
| 114 |
### 3. Run batch inference
|
| 115 |
|
| 116 |
```bash
|
| 117 |
-
python inference.py --config configs/inference.yaml
|
| 118 |
python inference.py --config configs/inference.fp8.yaml # FP8
|
| 119 |
python inference.py --config configs/inference.fp4.yaml # FP4
|
| 120 |
```
|
|
@@ -141,14 +141,15 @@ possible, especially [LTX-2.3](https://huggingface.co/Lightricks/LTX-2.3),
|
|
| 141 |
## Citation
|
| 142 |
|
| 143 |
```bibtex
|
| 144 |
-
@
|
| 145 |
-
title={Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds},
|
| 146 |
-
author=
|
| 147 |
-
|
| 148 |
-
|
| 149 |
-
|
| 150 |
-
|
| 151 |
-
|
|
|
|
| 152 |
}
|
| 153 |
```
|
| 154 |
|
|
@@ -156,11 +157,6 @@ possible, especially [LTX-2.3](https://huggingface.co/Lightricks/LTX-2.3),
|
|
| 156 |
|
| 157 |
This project is based on LTX-2 by Lightricks Ltd.
|
| 158 |
|
| 159 |
-
Portions of the original LTX-2 codebase have been modified by JD.com for
|
| 160 |
-
academic and research purposes only. This project is not intended for
|
| 161 |
-
commercial use. For commercial use of LTX-2 or its derivatives, please contact
|
| 162 |
-
Lightricks Ltd.
|
| 163 |
-
|
| 164 |
All original copyright, license, patent, trademark, and attribution notices
|
| 165 |
from LTX-2 are retained. This project remains subject to the LTX-2 Community
|
| 166 |
License Agreement.
|
|
|
|
| 114 |
### 3. Run batch inference
|
| 115 |
|
| 116 |
```bash
|
| 117 |
+
python inference.py --config configs/inference.bf16.yaml # BF16
|
| 118 |
python inference.py --config configs/inference.fp8.yaml # FP8
|
| 119 |
python inference.py --config configs/inference.fp4.yaml # FP4
|
| 120 |
```
|
|
|
|
| 141 |
## Citation
|
| 142 |
|
| 143 |
```bibtex
|
| 144 |
+
@article{duan2026joyaiecho15,
|
| 145 |
+
title = {Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds},
|
| 146 |
+
author = {Duan, Nan and Huang, Haoyang and Jin, Weiyang and Li, Haoran and Li, Yaowei and Li, Yuming and Liu, Yijun and Lu, Xin and Ma, Xiaoxiao and Ma, Yanwen and Su, Yaofeng and Sun, Yilang and Wang, Haoyu and Xue, Zeyue and Zhang, Songchun and Zhuang, Junhao},
|
| 147 |
+
journal = {arXiv preprint arXiv:2608.23383},
|
| 148 |
+
year = {2026},
|
| 149 |
+
eprint = {2608.23383},
|
| 150 |
+
archivePrefix = {arXiv},
|
| 151 |
+
primaryClass = {cs.CV},
|
| 152 |
+
url = {https://arxiv.org/abs/2608.23383}
|
| 153 |
}
|
| 154 |
```
|
| 155 |
|
|
|
|
| 157 |
|
| 158 |
This project is based on LTX-2 by Lightricks Ltd.
|
| 159 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 160 |
All original copyright, license, patent, trademark, and attribution notices
|
| 161 |
from LTX-2 are retained. This project remains subject to the LTX-2 Community
|
| 162 |
License Agreement.
|