Lists (2)
Stars
🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt
Official implementation of "ControlFace: Harnessing Facial Parametric Control for Face Rigging".
[CVPR 2025] Official implementation of "AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models"
Official Implementation of CLIP-Guided StyleGAN Inversion for Text-Driven Real Image Editing published in ACM TOG 2023
Pytorch Implementation of "SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation"(CVPR 2024)
[CVPR2024] CapHuman: Capture Your Moments in Parallel Universes
Official Implementation of ICLR'24: Kosmos-G: Generating Images in Context with Multimodal Large Language Models
[TMLR] Official PyTorch implementation of "λ-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space"
[ICLR 2025] Official implementation of MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance
Pretrained models for TensorFlow.js
COYO-700M: Large-scale Image-Text Pair Dataset
FaceChain is a deep-learning toolchain for generating your Digital-Twin.
[WACV 2024] LibreFace: An Open-Source Toolkit for Deep Facial Expression Analysis
StoryMaker: Towards consistent characters in text-to-image generation
UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization
[Siggraph Asia 2024] Follow-Your-Emoji: This repo is the official implementation of "Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation"
Fine-Grained Subject-Specific Attribute Expression Control in T2I Models
Towards Localized Fine-Grained Control for Facial Expression Generation
[CVPR2024] VideoBooth: Diffusion-based Video Generation with Image Prompts
Codes for ID-Specific Video Customized Diffusion
Pytorch implementation of paper "One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing"
This repo contains the code for PreciseControl project [ECCV'24]
[IJCV] FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention
Using Low-rank adaptation to quickly fine-tune diffusion models.