city96
/

FLUX.1-dev-gguf

image-generation

Model card Files Files and versions Community

Resources

View closed (14)

Fp16 -> GGUF 8B script?

#40 opened 7 days ago by

Not able to download it

#38 opened about 1 month ago by

Create an equivalent to GGUF for Diffusers models?

#37 opened about 1 month ago by

FP16 (safetensors) & Q8_0 (gguf) example PNG (anime girl) comparison (with ComfyUI workflow!)

#36 opened about 1 month ago by

What's the python code for utilizing this quantized model?

#35 opened about 2 months ago by

Create config.json

#34 opened 2 months ago by

video

#33 opened 2 months ago by

run

#32 opened 2 months ago by

Is it using ggml to compute?

#30 opened 3 months ago by

FLUX GGUF conversion

#29 opened 3 months ago by

cant see the Q5_K_M gguf quant

#28 opened 3 months ago by

Q6_K does not play as well with LoRAs

#25 opened 3 months ago by

Q8 vs Q4_1 vs FP8 on a 1070ti

#23 opened 3 months ago by

Changelog

#22 opened 3 months ago by

Which one is the best?

#21 opened 3 months ago by

Can you add Q4K_m please ?

#19 opened 3 months ago by

code for use this quantized model

#18 opened 3 months ago by

Mahdimohseni0333

Compared to the regular FP8 model, what is the better performance of the 8BIT model here

#16 opened 3 months ago by

all K quants comparison using fp16/fp8 t5

#15 opened 3 months ago by

What is the _K on the new files ?

#14 opened 3 months ago by

Can it use LoRAs?

#13 opened 3 months ago by

Can you add a link to that "install instructions GitHub" ??? And possible a super simple ComfyUI demo workflow?

#12 opened 3 months ago by

Please explain the difference between the two models

#11 opened 3 months ago by

Can this kind of merged model be converted to GGUF?

#10 opened 3 months ago by

My experience

#9 opened 3 months ago by

SaisExperiments

k-quants possible?

#2 opened 3 months ago by