[NeurIPS 2025] OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from sim…

Official code for our ICCV2025 paper "SDMatte: Grafting Diffusion Models for Interactive Matting"

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

Official inference code and LongText-Bench benchmark for our paper X-Omni (https://arxiv.org/pdf/2507.22058).

[WIP] Layer Diffusion for WebUI (via Forge)

Generative Omnimatte (CVPR 2025)

Bria Image Background Remover: -- minimal RAM/VRAM | 6GB install. ported from: https://huggingface.co/spaces/briaai/BRIA-RMBG-2.0

LaDeco - Layer Decomposer: This repository is to provide method and tool to decompose image layers. The tool is based on deep learning methods of Matting-Anything (MAM, for image matting), and LaMa…

[CVPR 2025] Official repo for ART:Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation

This repository includes the official project of Mask Guided (MG) Matting, presented in our paper: Mask Guided Matting via Progressive Refinement Network

Official implementation of "Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals" (NeurIPS 2025)

Code Implementation of the Paper: EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering

RepText: Rendering Visual Text via Replicating 🔥

🎓 Update Poster Generation Research Papers Daily

OpenCOLE: Towards Reproducible Automatic Graphic Design Generation [Inoue+, CVPRW2024 (GDUG)]

(CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

SkyReels-V2: Infinite-length Film Generative model

[Information Fusion (Vol.103, Mar. '24)] Boosting Image Matting with Pretrained Plain Vision Transformers

Official Repo For "Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos"

Lets make video diffusion practical!

Coherent Video Inpainting Using Optical Flow-Guided Efficient Diffusion

[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

Official PyTorch Code and Models of "RePaint: Inpainting using Denoising Diffusion Probabilistic Models", CVPR 2022

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2