mmagic • Rank 20.5 • Science 54%

OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.

blobctrl • Rank 4.5 • Science 64%

[Arxiv'25] BlobCtrl: A Unified and Flexible Framework for Element-level Image Generation and Editing

grounded-segment-anything • Rank 13.8 • Science 54%

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

brushedit • Rank 6.4 • Science 46%

[TPAMI under review] The official implementation of paper "BrushEdit: All-In-One Image Inpainting and Editing"

https://github.com/aim-uofa/oir • Rank 5.5 • Science 23%

[ICLR 2024] Official PyTorch/Diffusers implementation of "Object-aware Inversion and Reassembly for Image Editing"

https://github.com/bytedance/comfyui_infiniteyou • Science 36%

🔥 [ICCV 2025 Highlight] Official ComfyUI native node supporting InfiniteYou with FLUX

https://github.com/bytedance/infiniteyou • Science 36%

🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity

forgedit • Science 54%

https://github.com/bytedance/superedit • Science 36%

[ICCV 2025] Official repo for: SuperEdit - Rectifying and Facilitating Supervision for Instruction-Based Image Editing

scene-representation-diffusion-model • Science 23%

Linear probe found representations of scene attributes in a text-to-image diffusion model