Stars
Qwen-Image-Lightning: Speed up Qwen-Image model with distillation
This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation''
Qwen-Image text to image lora trainer
小红书（XiaoHongShu、RedNote）链接提取/作品采集工具：提取账号发布、收藏、点赞、专辑作品链接；提取搜索结果作品、用户链接；采集小红书作品信息；提取小红书作品下载地址；下载小红书无水印作品文件
[CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution
FashionCLIP is a CLIP-like model fine-tuned for the fashion domain.
Code for Learning Subject-Aware Cropping by Outpainting Professional Photos
Official Implementation and Dataset of "PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency", CVPR 2021
🎁 6,500,000+ Unsplash images made available for research and machine learning
Official inference repo for FLUX.1 models
Official codes of CCSRv2 and CCSRv1: Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution
Collect super-resolution related papers, data, repositories
Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
An out-of-box human parsing representation extractor.
State-of-the-art 2D and 3D Face Analysis Project
InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥
Nightly release of ControlNet 1.1
Open-Sora: Democratizing Efficient Video Production for All
Official implementation of Magic Clothing: Controllable Garment-Driven Image Synthesis
DCT (discrete cosine transform) functions for pytorch