ankanbhunia/PIDM
Person Image Synthesis via Denoising Diffusion Model (CVPR 2023)
This project helps fashion designers, advertisers, or creative professionals generate realistic images of people in different poses or outfits. You provide an input image of a person and desired poses (or a reference image for styling), and it creates new images of that person adopting the new poses or apparel. This is ideal for quickly visualizing how clothing looks on various models without costly photoshoots.
500 stars. No commits in the last 6 months.
Use this if you need to generate new, high-quality images of people, either by changing their pose or their clothing appearance, from an existing image.
Not ideal if you need to generate images of entirely new people or objects from scratch, or if your primary focus is on editing specific features rather than full-body transformations.
Stars
500
Forks
61
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jun 11, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ankanbhunia/PIDM"
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...