The Pytorch Implementation of ''Target-aware Image Editing via Cycle-consistent Constraints''

Draw ALL Your Imagine: A Holistic Benchmark and Agent Framework for Complex Instruction-based Image Generation

[NeurIPS 2025] Official implementation of "XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation".

official code for unigame

Unified Video Editing with Temporal Reasoner

Taming large-scale full-parameter few-step training with self-adversarial flows! 👏🏻

[NeurIPS 2025] IEAP: Image Editing As Programs with Diffusion Models

[SIGGRAPH 2025] AssetDropper: Asset Extraction via Diffusion Models with Reward-Driven Optimization

TokenAR: Multiple Subject Generation via Autoregressive Token-level enhancement

https://little-misfit.github.io/GRAG-Image-Editing/

Offline implementation of UniREditBench: A Unified Reasoning-based Image Editing Benchmark.

[AAAI 2026]🔥🔥🔥FocusDPO: Dynamic Preference Optimization for Multi-Subject Personalized Image Generation via Adaptive Focus

Implementation for project LoRAShop (NeurIPS 2025 - Spotlight)

Official repository for Scone (Subject-driven Composition and Distinction Enhancement) model, designed to support multi-subject composition and subject distinction tasks in complex contexts.

[AAAI 2026] The Official Implementation for "Anomagic: Crossmodal Prompt-driven Zero-shot Anomaly Generation"

Official Repository of "OmniTry: Virtual Try-On Anything without Masks"

This repository is the official implementation of NeurIPS 2025 Paper "Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable".

Complex-Edit: CoT-Like Instruction Generation for Complexity-Controllable Image Editing Benchmark

The official implementation of COOPER: A Unified Model for Cooperative Perception and Reasoning in Spatial Intelligence.

Official implementation of the paper “UniAlignment: Semantic Alignment for Unified Image Generation, Understanding, Manipulation and Perception” (AAAI2026)

Jodi: Unification of Visual Generation and Understanding via Joint Modeling

iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation

OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions

OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions (NeurIPS 2025)

PSR