foxAIAI가 움직이고 미래가 업데이트됩니다.
한국어
中文English日本語한국어

MiniMax-H3-x-Z-Image-native

The comfy-native cuts of the MiniMax-H3 × Z-Image graft: Z-Image's spatial-attention profile on H3's engine — richer sets and textures, same identity, no per-shot sharpening creep. Full story, demos and verification on the GGUF page. Load with the plain **Load Diffusion Model** node, ComfyUI 0.32+. Files are the `pruned` H3 builds with the graft baked in (`zs05` = late-block gains, dose 0.5): - `bf16` — the master (ref2va) - `comfy-fp8` / `fp8e5m2` — fp8 scaled - `comfy-int8` / `int8_convrot` — the fast pick on RTX 50 - `comfy-w4a8` / `w4a4` / `nvfp4` — 4-bit family for 16 GB cards (`w4a8` is the quality pick; `nvfp4` is Blackwell-native, emulated elsewhere) - `comfy-mxfp8` — 8-bit microscaling, Blackwell-specialized; little benefit on older architectures - fl2va and ref2va variants where both exist; picking rules are identical to stock H3

번역 준비 중입니다. 원문을 표시합니다.

The comfy-native cuts of the MiniMax-H3 × Z-Image graft: Z-Image's spatial-attention profile on H3's engine — richer sets and textures, same identity, no per-shot sharpening creep. Full story, demos and verification on the GGUF page. Load with the plain **Load Diffusion Model** node, ComfyUI 0.32+. Files are the `pruned` H3 builds with the graft baked in (`zs05` = late-block gains, dose 0.5): - `bf16` — the master (ref2va) - `comfy-fp8` / `fp8e5m2` — fp8 scaled - `comfy-int8` / `int8_convrot` — the fast pick on RTX 50 - `comfy-w4a8` / `w4a4` / `nvfp4` — 4-bit family for 16 GB cards (`w4a8` is the quality pick; `nvfp4` is Blackwell-native, emulated elsewhere) - `comfy-mxfp8` — 8-bit microscaling, Blackwell-specialized; little benefit on older architectures - fl2va and ref2va variants where both exist; picking rules are identical to stock H3

출처

huggingface.co ↗