Originally posted on Huggingface.
AuraFlow is the fully open-sourced largest flow-based text-to-image generation model.
This model achieves state-of-the-art results on GenEval. Read our blog post for more technical details.
The model is currently in beta. We are working on improving it and the community's feedback is important. Join fal's Discord to give us feedback and stay in touch with the model development.
Credits: A huge thank you to @cloneofsimo and @isidentical for bringing this project to life. It's incredible what two cracked engineers can achieve in such a short period of time. We also extend our gratitude to the incredible researchers whose prior work laid the foundation for our efforts.
FAQ
Comments (9)
16gb damnn... make porn?
Real question, they don't all...
is this a new model?
can we use it in AUTOMATIC1111
It took about 20 days to go from version 0.1 to version 0.2. At this rate, it will take about 160 days to reach version 1.0 (Finished product), around January 2025.
Relevant XKCD post: https://xkcd.com/605/
That's not how versionning works
AuraFlow 0.3 was released
https://huggingface.co/fal/AuraFlow-v0.3
and that line was just corrected on huggingface as well with the comment :
"Not largest now, damn it BFL" ~cloneofsimo~ 😄
"AuraFlow is the fully open-sourced largest flow-based text-to-image generation model."
→ "AuraFlow v0.3 is the fully open-sourced flow-based text-to-image generation model."
Details
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.