AI is happening. The future is updating.Minimax-h3_Singularity_v2_pruned
Pruned and quantized versions of the ref2va v2 release of WarmBloodAban/Minimax-h3_Singularity, in the same layout as ComfyUI's own pruned MiniMax H3 releases. Load them in ComfyUI with **Load Diffusion Model**, with `weight_dtype` left at `default`. The int8 and w6a8 files are built from `Minimax-h3_Singularity_ref2va_v2_bf16.safetensors`. The first build started from the int8 release. Measured against the bf16 release: The w4a8 file is unchanged. Built from bf16 it rendered further from the bf16 release on every seed tested (20.2 dB against 21.5 dB), so the build from the int8 release stays.
Pruned and quantized versions of the ref2va v2 release of WarmBloodAban/Minimax-h3_Singularity, in the same layout as ComfyUI's own pruned MiniMax H3 releases. Load them in ComfyUI with **Load Diffusion Model**, with `weight_dtype` left at `default`. The int8 and w6a8 files are built from `Minimax-h3_Singularity_ref2va_v2_bf16.safetensors`. The first build started from the int8 release. Measured against the bf16 release: The w4a8 file is unchanged. Built from bf16 it rendered further from the bf16 release on every seed tested (20.2 dB against 21.5 dB), so the build from the int8 release stays.