Update 19/02/26: uploaded v2 with some layers kept at BF16 and longer calibration (more steps, adjusted learning rate, etc). Clearly better than the first version I did, doesn't get "fuzzy" on edges or hair.
NVFP4 version of
Qwen-Image-2512 and
Qwen2.5-VL-7B-Instruct, both created from BF16 versions in
Comfy-Org/Qwen repo. Made with
Silveroxides/convert_to_quant script.
Drop-in replacement in Comfy, there's a bit of quality loss as in nunchaku models or others nvfp4.
⚠️ I strongly suspect a bottleneck somewhere (memory bandwidth? dequant ops?) that throttles the GPU down in some cases, running small batches instead of single image seems to remove it. I only have surface knowledge of this stuff and don't know how to troubleshoot it.
(wall time, on a 5090. Vanilla = 50 steps & CFG 4, Lightning = 8 steps & CFG 1 with
Lightning lora)
