muzishen/IMAGPose
[NeurIPS 2024] 🕺IMAGPose🕺: A Unified Conditional Framework for Pose-Guided Person Generation. IMAGPose enables versatile pose-guided image generation with high detail fidelity, pose alignment, and cross-view consistency, overcoming limitations of existing methods.
This project helps create realistic images of people in various poses. You provide an existing image of a person and a target pose (or multiple poses), and it generates new images of that person adopting the desired stance, even from different camera angles. This is ideal for content creators, marketers, and designers who need to visualize a person in different body positions without re-shooting.
349 stars. No commits in the last 6 months.
Use this if you need to generate high-quality images of a person in new poses, or apply multiple poses simultaneously to a single source image, or use multi-view source images for improved realism.
Not ideal if you're looking to generate images of objects or scenes, or if you don't have a specific source person image as input.
Stars
349
Forks
11
Language
Python
License
Apache-2.0
Category
Last pushed
Sep 30, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/muzishen/IMAGPose"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
UCSC-VLAA/story-iter
[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization
PaddlePaddle/PaddleMIX
Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks,...
keivalya/mini-vla
a minimal, beginner-friendly VLA to show how robot policies can fuse images, text, and states to...
adobe-research/custom-diffusion
Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)
byliutao/1Prompt1Story
🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation...