Ecosyste.ms: Awesome

Projects in Awesome Lists by mihirp1998

A curated list of projects in awesome lists by mihirp1998 .

• Sort

  • Recently synced
  • Stars

https://github.com/mihirp1998/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

alignment diffusion-models reinforcement-learning stable-diffusion text-to-image

Last synced: 31 Jul 2024

https://github.com/mihirp1998/VADER

Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope and StableVideoDiffusion by finetuning them using various reward models such as HPS, PickScore, VideoMAE, VJEPA, YOLO, Aesthetics etc.

alignment diffusion reinforcement-learning reinforcement-learning-human-feedback rl rlhf vader video-diffusion video-diffusion-alignment

Last synced: 31 Jul 2024