Kijai
/

flux-fp8

Model card Files Files and versions Community

Resources

View closed (5)

Inquiry on Latest Update for flux1-dev-fp8

#27 opened 11 days ago by

fp8 inference

#26 opened 20 days ago by

wrong model

#25 opened 23 days ago by

Update README.md

#24 opened 25 days ago by

"model weight dtype torch.float8_e4m3fn, manual cast: torch.bfloat16" with ROCM6.0

#23 opened 29 days ago by

Unet?

#22 opened about 1 month ago by

quite slow to load the fp8 model

#21 opened about 1 month ago by

RuntimeError: "addmm_cuda" not implemented for 'Float8_e4m3fn'

#20 opened about 1 month ago by

gradient-diffusion

How to load into VRAM?

#19 opened about 1 month ago by

What setting to use for flux1-dev-fp8

#18 opened about 1 month ago by

'float8_e4m3fn' attribute error

#17 opened about 2 months ago by

Loading flux-fp8 with diffusers

#16 opened about 2 months ago by

8au

FP8 Checkpoint version size mismatch?

#15 opened about 2 months ago by

Can this model be used on Apple Silicon?

#14 opened about 2 months ago by

How to use fp8 models + original flux repo?

#13 opened about 2 months ago by

Quantization Method?

#7 opened about 2 months ago by

ComfyUi Workflow

#6 opened about 2 months ago by

Can you make FP8 version of schnell as well please?

#5 opened about 2 months ago by

Diffusers?

#4 opened about 2 months ago by

Minimum vram requirements?

#3 opened about 2 months ago by

joachimsallstrom

FP16

#2 opened about 2 months ago by

Metadata lost from model

#1 opened about 2 months ago by