soon-yau/upgpt
UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose Transfer
This tool helps creative professionals and researchers generate, edit, and transfer poses on human images. You provide an image of a person, a desired pose (like a reference image or text description), and potentially a textual prompt. The system then outputs new images of that person in the specified pose, allowing for advanced editing or creating entirely new visual content. It's ideal for anyone who needs to quickly manipulate human figures for various visual projects.
103 stars. No commits in the last 6 months.
Use this if you need to generate images of people in specific poses, edit existing person images, or transfer a pose from one image onto a different person.
Not ideal if you're looking to generate images of objects, landscapes, or animals, as it's specifically designed for human figures.
Stars
103
Forks
9
Language
Jupyter Notebook
License
—
Category
Last pushed
May 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/soon-yau/upgpt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huggingface/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
bghira/SimpleTuner
A general fine-tuning kit geared toward image/video/audio diffusion models.
mcmonkeyprojects/SwarmUI
SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an...
nateraw/stable-diffusion-videos
Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts
TheDesignFounder/DreamLayer
Benchmark diffusion models faster. Automate evals, seeds, and metrics for reproducible results.