FreedomGu/DiffPortrait3D
Official Repository of [CVPR'24 Highlight Diffportrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis]
This project helps generate realistic, multi-angle views of a person's face from just a single portrait photo. You input one image, and it produces a series of new photos showing the person's face from various camera angles, while maintaining their identity and expression. This is useful for 3D artists, animators, and creators who need to generate diverse facial poses for digital avatars or video content without extensive manual modeling.
157 stars. No commits in the last 6 months.
Use this if you need to create multiple 3D-consistent views of a human portrait from a single 2D image for animation, virtual try-ons, or digital character development.
Not ideal if you require highly precise, photogrammetry-level 3D models or if you need to generate full-body views.
Stars
157
Forks
9
Language
Python
License
MIT
Category
Last pushed
Jan 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/FreedomGu/DiffPortrait3D"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PRIS-CV/DemoFusion
Let us democratise high-resolution generation! (CVPR 2024)
mit-han-lab/distrifuser
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Tencent-Hunyuan/HunyuanPortrait
[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced...
giuvecchio/matfuse
MatFuse: Controllable Material Generation with Diffusion Models (CVPR2024)
Shilin-LU/TF-ICON
[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official...