Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,10 @@ tags:
|
|
| 16 |
- sparse-attention
|
| 17 |
---
|
| 18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
# FastH3 VSA-DataFree LoRA + Gate for ComfyUI (experimental)
|
| 20 |
|
| 21 |
Two files that let you run **FastVideo's Video Sparse Attention (VSA) 4-step distillation LoRA** for MiniMax H3 inside ComfyUI's native H3 stack, without needing FastVideo's own inference pipeline.
|
|
|
|
| 16 |
- sparse-attention
|
| 17 |
---
|
| 18 |
|
| 19 |
+
## TL;DR
|
| 20 |
+
|
| 21 |
+
Two files that let ComfyUI run **MiniMax H3 video generation in 4 steps** using FastVideo's Video Sparse Attention. On a 24 GB RTX 3090 Ti, this drops a 5-second, 0.8 MP clip from ~8 minutes (base, 20 steps) to under 1 minute (draft) or ~2.5 minutes (best quality). Requires the [companion custom node](https://github.com/barelymining/ComfyUI-MiniMax-H3-FastVideo) — you can't load these with a normal LoRA loader alone.
|
| 22 |
+
|
| 23 |
# FastH3 VSA-DataFree LoRA + Gate for ComfyUI (experimental)
|
| 24 |
|
| 25 |
Two files that let you run **FastVideo's Video Sparse Attention (VSA) 4-step distillation LoRA** for MiniMax H3 inside ComfyUI's native H3 stack, without needing FastVideo's own inference pipeline.
|