-
Alibaba Group
- Hangzhou
-
23:21
(UTC +08:00)
Stars
The benchmark of SOTA text-to-image diffusion models with a new benchmarking strategy based on MiniGPT-4, namely X-IQE.
A list of works on evaluation of visual generation models, including evaluation metrics, models, and systems
FgSegNet: Foreground Segmentation Network, Foreground Segmentation Using Convolutional Neural Networks for Multiscale Feature Encoding
[CVPR 2023] Explicit Visual Prompting for Low-Level Structure Segmentations
Workable training script for ControlNet tile
Inpaint images with ControlNet
Python implementation of colour transfer algorithm based on linear Monge-Kantorovitch solution
Effortless data labeling with AI support from Segment Anything and other awesome models.
[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
YOLO-World + EfficientViT SAM
SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.
InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥
Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>
Official repository for "PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout" (CVPR 2023).
Nightly release of ControlNet 1.1
Code for instruction-tuning Stable Diffusion.
MinImagen: A minimal implementation of the Imagen text-to-image model
Collaborative Score Distillation for Consistent Visual Synthesis (NeurIPS 2023)
An open-source framework for training large multimodal models.
Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)
SAM + CLIP + DIFFUSION for image to edit objects in images using plain text
Implementation of MDP: A Generalized Framework for Text-Guided Image Editing by Manipulating the Diffusion Path
[CVPR 2024] PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor
Paint by Example: Exemplar-based Image Editing with Diffusion Models