fireworks-ai
/

FLUX.1-schnell-fp8-flumina

Model card Files Files and versions

FLUX.1-schnell-fp8-flumina

201 kB

7 contributors

History: 64 commits

aredden's picture

Fix issue where cublas linear not installed causing TypeError

153dd91 about 1 year ago

configs
Adding device specific configs & more input image type options + small model spec from args change over 1 year ago
modules
lora unloading initial about 1 year ago
.gitignore

125 Bytes

Small fixes & clean up over 1 year ago
LICENSE

11.3 kB

Create LICENSE over 1 year ago
README.md

22.3 kB

update readme about 1 year ago
api.py

3.68 kB

Make lora loading api endpoint functional about 1 year ago
float8_quantize.py

18.6 kB

Fix issue where cublas linear not installed causing TypeError about 1 year ago
flux_emphasis.py

14.3 kB

Fix unbound local error when pad_tokens=False about 1 year ago
flux_pipeline.py

26.5 kB

Make lora loading api endpoint functional about 1 year ago
image_encoder.py

1.07 kB

Adding device specific configs & more input image type options + small model spec from args change over 1 year ago
lora_loading.py

27.6 kB

Fix issue where cublas linear not installed causing TypeError about 1 year ago
main.py

6.29 kB

Add quantize embedders/modulation to argparse options over 1 year ago
main_gr.py

4.28 kB

Small fixes & clean up over 1 year ago
requirements.txt

202 Bytes

remove torchao dependency, quantize entirely via linear over 1 year ago
util.py

10.7 kB

lora unloading initial about 1 year ago