kyegomez/Fusion3D
An extremely experimental model that intakes images and generates 3D scenes of those images using Diffusion
This tool helps 3D artists, game designers, and virtual reality creators quickly generate three-dimensional scenes from existing images. You provide a set of 2D images, and it outputs a complete 3D scene representation of those images. This is ideal for anyone needing to rapidly prototype virtual environments or expand their 3D asset library.
Use this if you need to transform static 2D images into dynamic 3D scenes for creative projects or simulations.
Not ideal if you require precise, handcrafted 3D models with specific details or fine-tuned artistic control.
Stars
7
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/kyegomez/Fusion3D"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
filipstrand/mflux
MLX native implementations of state-of-the-art generative image models
potamides/DeTikZify
Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ.
FoundationVision/Infinity
[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
zai-org/CogView
Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image...
EleutherAI/DALLE-mtf
Open-AI's DALL-E for large scale training in mesh-tensorflow.