AlignProp
AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion
Fine-tune text-to-image models to improve their image quality and alignment with text descriptions.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeAlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion
AlignProp has 324 stars on GitHub. It has been forked 11 times. AlignProp is written mainly in Python. It has been in active development since 2023. AlignProp is available under the MIT license. Its main topics are alignment, diffusion-models, reinforcement-learning, stable-diffusion.
What is AlignProp?
AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion
Is AlignProp open source?
AlignProp is an open-source project. It is released under the MIT license.
Is AlignProp free?
Yes. AlignProp is free and open source — you can use, modify and self-host it.
What license does AlignProp use?
AlignProp is available under the MIT license.
What language is AlignProp written in?
AlignProp is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/mihirp1998-alignprop.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.