SalesforceAIResearch / DiffusionDPO
Code for "Diffusion Model Alignment Using Direct Preference Optimization"
☆229Updated 8 months ago
Related projects: ⓘ
- AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more samp…☆228Updated 6 months ago
- [ICCV 2023] Efficient Diffusion Training via Min-SNR Weighting Strategy☆214Updated 5 months ago
- [CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"☆160Updated 5 months ago
- Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models arXiv 2023 / CVPR 2024☆299Updated 5 months ago
- Official implementation of "Controlling Text-to-Image Diffusion by Orthogonal Finetuning".☆279Updated 9 months ago
- [Neurips 2023] T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation☆190Updated 3 weeks ago
- Code for the paper "Training Diffusion Models with Reinforcement Learning"☆317Updated last year
- GenEval: An object-focused framework for evaluating text-to-image alignment☆85Updated last month
- CV-VAE: A Compatible Video VAE for Latent Generative Video Models☆210Updated 2 weeks ago
- Step-aware Preference Optimization: Aligning Preference with Denoising Performance at Each Step☆133Updated 2 months ago
- 🔥 [CVPR2024] Official implementation of "Self-correcting LLM-controlled Diffusion Models (SLD)☆146Updated 5 months ago
- Better Aligning Text-to-Image Models with Human Preference. ICCV 2023☆264Updated last year
- Implementation of "DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning"☆75Updated last year
- An in-context conditioning version of MUSE with pre-trained checkpoints.☆105Updated last year
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis☆365Updated 3 months ago
- Code for Fast Training of Diffusion Models with Masked Transformers☆351Updated 4 months ago
- Official pytorch implementation of the paper: "An Edit Friendly DDPM Noise Space: Inversion and Manipulations". CVPR 2024.☆254Updated 2 months ago
- This repo contains the code for our paper An Image is Worth 32 Tokens for Reconstruction and Generation☆394Updated last week
- SpeeD: A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training☆148Updated 2 months ago
- [ICLR2024] The official implementation of paper "VDT: General-purpose Video Diffusion Transformers via Mask Modeling", by Haoyu Lu, Guoxi…☆205Updated 4 months ago
- [WACV 2024] Training-Free Layout Control with Cross-Attention Guidance☆230Updated 6 months ago
- (CVPR 2024) 🧩 TokenCompose: Text-to-Image Diffusion with Token-level Supervision☆107Updated 2 months ago
- RichHF-18K dataset contains rich human feedback labels we collected for our CVPR'24 paper: https://arxiv.org/pdf/2312.10240, along with t…☆96Updated 2 months ago
- Official PyTorch implementation of the paper "In-Context Learning Unlocked for Diffusion Models"☆371Updated 5 months ago
- ☆99Updated 6 months ago
- Scaling Diffusion Transformers with Mixture of Experts☆178Updated last week
- ☆415Updated 7 months ago
- Unofficial PyTorch implementation of the VideoLDM.☆144Updated last year
- DDPO for finetuning diffusion models, implemented in PyTorch with LoRA support☆397Updated 5 months ago
- ☆147Updated last year