Kijai
/

flux-fp8

Model card Files Files and versions Community

Resources

View closed (7)

FP8 for flux depth and flux canny.

#36 opened 15 days ago by

HOW TO USE THE flux-fp8 IN PYTHON?

#35 opened 22 days ago by

Is your dev-fp8-e4m3fn version consistent with the official fp8 version released by Comfyui?

#33 opened 2 months ago by

Which model is better for low vram/ram?

#32 opened 3 months ago by

Noisy Output When used in the Flux Inpainting Pipeline

#31 opened 3 months ago by

cuda out of memory for flux1-dev-fp8.safetensors

#30 opened 3 months ago by

Silent exit when loading via FluxTransformer2DModel.from_single_file and no GPU use

#29 opened 3 months ago by

Inquiry on Latest Update for flux1-dev-fp8

#27 opened 4 months ago by

fp8 inference

#26 opened 4 months ago by

wrong model

#25 opened 4 months ago by

Update README.md

#24 opened 4 months ago by

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

#23 opened 4 months ago by

Unet?

#22 opened 4 months ago by

quite slow to load the fp8 model

#21 opened 5 months ago by

RuntimeError: "addmm_cuda" not implemented for 'Float8_e4m3fn'

#20 opened 5 months ago by

gradient-diffusion

How to load into VRAM?

#19 opened 5 months ago by

What setting to use for flux1-dev-fp8

#18 opened 5 months ago by

'float8_e4m3fn' attribute error

#17 opened 5 months ago by

Loading flux-fp8 with diffusers

#16 opened 5 months ago by

FP8 Checkpoint version size mismatch?

#15 opened 5 months ago by

Can this model be used on Apple Silicon?

#14 opened 5 months ago by

How to use fp8 models + original flux repo?

#13 opened 5 months ago by

Quantization Method?

#7 opened 5 months ago by

ComfyUi Workflow

#6 opened 5 months ago by

Can you make FP8 version of schnell as well please?

#5 opened 5 months ago by

Diffusers?

#4 opened 5 months ago by

Minimum vram requirements?

#3 opened 5 months ago by

joachimsallstrom

FP16

#2 opened 5 months ago by

Metadata lost from model

#1 opened 5 months ago by