bram-w / trl
Train transformer language models with reinforcement learning.
☆16Updated 10 months ago
Related projects ⓘ
Alternatives and complementary repositories for trl
- [NeurIPS'2024] Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps☆85Updated 4 months ago
- Diffusers Implementation of Controlling Text-to-Image Diffusion by Orthogonal Finetuning☆34Updated last year
- A retrain of AnimateDiff to be conditional on an init image☆33Updated last year
- Official codebase for Margin-aware Preference Optimization for Aligning Diffusion Models without Reference (MaPO).☆61Updated 5 months ago
- ☆71Updated last year
- Official implementation of UniCtrl: Improving the Spatiotemporal Consistency of Text-to-Video Diffusion Models via Training-Free Unified …☆64Updated 2 weeks ago
- SDXL Training Improvements☆43Updated this week
- ☆25Updated 3 months ago
- Public code release for the paper "ProCreate, Don’t Reproduce! Propulsive Energy Diffusion for Creative Generation"☆34Updated 2 weeks ago
- Official implementation of "Perturbed-Attention Guidance"☆53Updated 4 months ago
- ☆29Updated this week
- Fine-Grained Subject-Specific Attribute Expression Control in T2I Models☆108Updated 5 months ago
- ☆62Updated 5 months ago
- A example pipeline to use InstructPix2Pix and the associated fine-tuned motion module☆31Updated last year
- Implementation of "SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing"☆84Updated 10 months ago
- ☆119Updated last month
- implementation of AnimateDiff.☆31Updated last year
- Official Implementation of weights2weights☆121Updated this week
- The implementation of the paper "Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention" (NeurIPS`…☆103Updated last month
- Motion Module fine tuner for AnimateDiff.☆79Updated last year
- finetune your florence2 model easy☆20Updated 3 months ago
- ☆43Updated 10 months ago
- ☆100Updated last month
- ☆24Updated 5 months ago
- Official implementation of "Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective Dynamics" (NeurIPS 2023)☆37Updated last year
- MuDI: Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models (NeurIPS 2024)☆72Updated last week
- 🔥 [CVPR 2024] The official repo for Zero-Painter!☆62Updated 5 months ago
- Gradient-Free Textual Inversion for Personalized Text-to-Image Generation☆38Updated last year
- [ICLR 2024] Code for FreeNoise based on AnimateDiff☆106Updated 10 months ago