-
Stefy Lanza (nextime / spora ) authored- Defer I2V model loading when in I2V mode without provided image - Generate image first with T2I model - Unload T2I model completely (del, empty_cache, gc.collect) - Then load I2V model and generate video - This ensures only one model is in memory at a time - Fixes Linux OOM killer issue when loading multiple models
0ccc1d52
| Name |
Last commit
|
Last update |
|---|---|---|
| EXAMPLES.md | ||
| LICENSE.md | ||
| README.md | ||
| SKILL.md | ||
| requirements.txt | ||
| videogen | ||
| videogen_mcp_server.py | ||
| videogen_models.json |