Stars
[Tutorial] Few-Step Distillation for Text-to-Image Generation: A Practical Guide
iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation
The first Interleaved framework for textual reasoning within the visual generation process
The ultimate training toolkit for finetuning diffusion models
UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios
DiffusionNFT: Online Diffusion Reinforcement with Forward Process
HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation
Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference
[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation
Official implementation of Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Official implementation of HPSv3: Towards Wide-Spectrum Human Preference Score (ICCV2025)
This repository provides stand-alone visualisation utilities for probability distributions in log-SNR (λ) space, as used by recent diffusion models such as SD3 / FLUX and Style-Friendly SNR Sampler…
Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.
Lumina-Image 2.0: A Unified and Efficient Image Generative Framework
CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models (NeurIPS 2025)
Use Kimi latest model(kimi-k2-0711-preview) to drive your Claude Code.
Official Implementation of Paper Transfer between Modalities with MetaQueries
Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.
Scaling Preference Data Curation via Human-AI Synergy
Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework
[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL
ComfyUI-PosterCraft is now available in ComfyUI, PosterCraft is a unified framework for high-quality aesthetic poster generation that excels in precise text rendering, seamless integration of abstr…
