RockeyCoss / SPOLinks
[CVPR 2025] Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization
β252Updated 6 months ago
Alternatives and similar repositories for SPO
Users that are interested in SPO are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2024] π«CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matchingβ164Updated 10 months ago
- [ICLR2025] A versatile image-to-image visual assistant, designed for image generation, manipulation, and translation based on free-from uβ¦β209Updated 5 months ago
- Official implementation of HPSv3: Towards Wide-Spectrum Human Preference Score (ICCV2025)β184Updated 3 weeks ago
- [NeurIPS 2024] CV-VAE: A Compatible Video VAE for Latent Generative Video Modelsβ282Updated 10 months ago
- [ICCV2025] The code of our work "Golden Noise for Diffusion Models: A Learning Framework".β186Updated last month
- β237Updated last year
- [NeurIPS 2024] ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimizationβ157Updated 3 weeks ago
- β90Updated last year
- β112Updated last year
- Subjects200K datasetβ118Updated 8 months ago
- [ICLR 2025] IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generationβ197Updated 7 months ago
- β50Updated 9 months ago
- Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScopeβ¦β302Updated 6 months ago
- β264Updated last year
- SigLIP-based Aesthetic Score Predictorβ317Updated 9 months ago
- [ICCV 2025] VisualCloze: A universal image generation framework that can support a wide range of in-domain tasks and generalize to unseenβ¦β257Updated 3 weeks ago
- [ICLR 2025] Official implementation of MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidanceβ296Updated 2 months ago
- β119Updated last month
- [CVPR 2024] Official PyTorch implementation of FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Compositionβ166Updated last month
- Officail Implementation for "ReNoise: Real Image Inversion Through Iterative Noising"β249Updated last year
- [CVPR 2024] Official implementation of CVPR 2024 paper: "Inversion-Free Image Editing with Natural Language"β343Updated last year
- [CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"β240Updated last year
- β174Updated 11 months ago
- STAR: Scale-wise Text-to-image generation via Auto-Regressive representationsβ146Updated 7 months ago
- VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generationβ320Updated 6 months ago
- [NeurIPS 2025 D&Bπ₯] ImgEdit: A Unified Image Editing Dataset and Benchmarkβ189Updated last month
- Official implementation of paper "One-dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications".β144Updated last year
- Code repository for T2V-Turbo and T2V-Turbo-v2β303Updated 8 months ago
- MAG-Edit: Localized Image Editing in Complex Scenarios via Mask-Based Attention-Adjusted Guidance (ACM MM2024)β134Updated 5 months ago
- [Neurips 2023 & TPAMI] T2I-CompBench (++) for Compositional Text-to-image Generation Evaluationβ293Updated last month