Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
fireworks-ai
/
FLUX.1-schnell-fp8-flumina
like
0
Follow
Fireworks AI
80
Safetensors
License:
apache-2.0
Model card
Files
Files and versions
Community
58082af
FLUX.1-schnell-fp8-flumina
7 contributors
History:
20 commits
aredden
Merge branch 'main' of https://github.com/aredden/flux-fp16-acc-api into main
58082af
6 months ago
configs
Adding device specific configs & more input image type options + small model spec from args change
6 months ago
modules
Fix non-prequantized inference
6 months ago
.gitignore
125 Bytes
Small fixes & clean up
6 months ago
README.md
11.3 kB
Update README.md
6 months ago
api.py
798 Bytes
Add img2img, more options, gradio interface
6 months ago
float8_quantize.py
14.3 kB
Add fields to configs, fix issue with offload from bnb, remove extra random text code
6 months ago
flux_emphasis.py
14.1 kB
Add img2img, more options, gradio interface
6 months ago
flux_pipeline.py
21.9 kB
Adding device specific configs & more input image type options + small model spec from args change
6 months ago
image_encoder.py
1.07 kB
Adding device specific configs & more input image type options + small model spec from args change
6 months ago
main.py
3.28 kB
Add offloading & improved fp8 inference.
6 months ago
main_gr.py
4.28 kB
Small fixes & clean up
6 months ago
quantize_swap_and_dispatch.py
9.11 kB
Updates..
6 months ago
requirements.txt
245 Bytes
Add uvicorn requirement
6 months ago
sampling.py
4.25 kB
Add img2img, more options, gradio interface
6 months ago
util.py
9.21 kB
Adding device specific configs & more input image type options + small model spec from args change
6 months ago