CarperAI / DRLX
Diffusion Reinforcement Learning Library
☆174Updated 9 months ago
Related projects ⓘ
Alternatives and complementary repositories for DRLX
- This is the official repo for the paper "Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles", Tang et…☆195Updated last year
- Simple large-scale training of stable diffusion with multi-node support.☆126Updated last year
- AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more samp…☆242Updated 3 weeks ago
- Huggingface-compatible SDXL Unet implementation that is readily hackable☆401Updated last year
- This repository implements the idea of "caption upsampling" from DALL-E 3 with Zephyr-7B and gathers results with SDXL.☆153Updated last year
- Iterable datapipelines for pytorch training.☆81Updated 2 months ago
- ☆110Updated 2 years ago
- ☆319Updated 2 months ago
- Faster generation with text-to-image diffusion models.☆195Updated last month
- ☆444Updated 9 months ago
- Better Aligning Text-to-Image Models with Human Preference. ICCV 2023☆266Updated last year
- Implementation of Key-Locked Rank One Editing, from Nvidia AI☆230Updated last year
- Open reproduction of MUSE for fast text2image generation.☆332Updated 5 months ago
- ☆71Updated last year
- Reproduction of DDPO paper (RLHF for diffusion)☆69Updated last year
- Implementation of "SVDiff: Compact Parameter Space for Diffusion Fine-Tuning"☆369Updated 9 months ago
- Implementation of Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models☆321Updated last year
- Code for "Diffusion Model Alignment Using Direct Preference Optimization"