multimodalart HF Staff commited on
Commit
e835f7f
·
verified ·
1 Parent(s): bb6cd86

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -30,8 +30,8 @@ This Space runs the paper's [MiniMax-H3 port](https://github.com/scrya-com/mpeg-
30
  the ridge-fitted KV up-maps and the v3 region head applied to the int8 ConvRot base DiT
31
  ([Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3)), at the port's
32
  *quality preset* — 20 steps, the region chosen at step 16, 6 high-resolution steps, pixel-space
33
- merge. By default the model picks its own detail region; a manual box can be forced under
34
- *Advanced*.
35
 
36
  Because the 62 GiB Qwen3-VL text encoder does not fit beside the transformer on one GPU,
37
  prompt conditioning runs on the
 
30
  the ridge-fitted KV up-maps and the v3 region head applied to the int8 ConvRot base DiT
31
  ([Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3)), at the port's
32
  *quality preset* — 20 steps, the region chosen at step 16, 6 high-resolution steps, pixel-space
33
+ merge, on a short reference-length clip. By default the model picks its own detail region; a
34
+ manual box can be forced under *Advanced*.
35
 
36
  Because the 62 GiB Qwen3-VL text encoder does not fit beside the transformer on one GPU,
37
  prompt conditioning runs on the