UniGen - Universal Generation Space
Image & Video Generation with multiple model families, variants, and full parameter control. Running on ZeroGPU (RTX PRO 6000 Blackwell).
| Tab | Sub-tabs | Model Families |
|---|---|---|
| Image | Text to Image, Image to Image | SDXL, SD1.5, SD3, FLUX, PixArt, Kolors, Playground |
| Video | Text to Video, Image to Video | Wan 2.1/2.2, LTX 2.3/2.5, CogVideoX, HunyuanVideo, Mochi, SVD |
Model Series
Model Variant
1 100
0 20
256 2048
256 2048
Model Series
Model Variant
1 100
0 20
256 2048
256 2048
0 1
Model Series
Model Variant
1 100
0 20
16 161
8 30
256 1280
256 1280
Model Series
Model Variant
1 100
0 20
16 161
8 30
256 1280
256 1280
Tips
- Seed -1 = random seed each generation
- Turbo/Lightning/Schnell models use fewer steps (1-4) and CFG=0
- FLUX models work best with specific resolutions (multiples of 16)
- Wan 1.3B is faster but lower quality than 14B
- LTX Distilled/Turbo use 4-8 steps for real-time generation
- Click Load Model when switching models/variants
- Models stay in VRAM until you switch or the worker is recycled
Adding New Models
Edit the MODEL_REGISTRY dictionary in app.py to add new model series and variants.
No other code changes needed!