Instructions to use deathlegionteam/LEGION-Video-Gen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use deathlegionteam/LEGION-Video-Gen with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("deathlegionteam/LEGION-Video-Gen", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Upload requirements.txt with huggingface_hub
Browse files- requirements.txt +19 -0
requirements.txt
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# LEGION VIDEO GENERATION - Dependencies
|
| 2 |
+
torch>=2.0.0
|
| 3 |
+
diffusers>=0.32.0
|
| 4 |
+
transformers>=4.40.0
|
| 5 |
+
accelerate>=0.30.0
|
| 6 |
+
sentencepiece
|
| 7 |
+
protobuf
|
| 8 |
+
opencv-python-headless
|
| 9 |
+
imageio
|
| 10 |
+
imageio-ffmpeg
|
| 11 |
+
ffmpeg-python
|
| 12 |
+
gradio>=4.0.0
|
| 13 |
+
fastapi>=0.100.0
|
| 14 |
+
uvicorn[standard]
|
| 15 |
+
Pillow>=10.0.0
|
| 16 |
+
safetensors>=0.4.0
|
| 17 |
+
tqdm
|
| 18 |
+
einops
|
| 19 |
+
huggingface-hub>=0.23.0
|