qwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_comfyui.safetensors
#199
by
lisi31415926
- opened
qwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_comfyui.safetensors
Qwen-Image-Edit-2511-Lightning-4steps-V1.0-fp32.safetensors
Are you using the latest FP8 and Lightning? I think this version（qwen_image_edit_2511_fp8_e4m3fn_scaled_lightning_comfyui.safetensors） is better adapted.
THANKS, YOU ARE GREAT
I work with bf16 and fp32, then downscale to fp8 on save. Using scaled models from the start doesn't save correctly.
I work with bf16 and fp32, then downscale to fp8 on save. Using scaled models from the start doesn't save correctly.
ok thanks for you rely, good job