# ashawkey/stable-dreamfusion

Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

Repository: https://github.com/ashawkey/stable-dreamfusion
Canonical: https://ross.abutalabs.com/products/stable-dreamfusion
Language: Python
License: Apache-2.0
License Family: permissive
Topics: text-to-3d, gui, nerf, stable-diffusion, dreamfusion, image-to-3d
Last push: 2023-12-10T23:17:27+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 1427, "days_push": 997, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8854, forks 770 (observed 2026-08-28T04:10:26.033617+00:00)

## What it is
A PyTorch implementation of Dreamfusion that generates 3D models from text prompts or images using NeRF combined with Stable Diffusion guidance. It supports Instant-NGP and vanilla NeRF backbones and can export generated 3D content as meshes.

## Use cases
- generate 3D models from text prompts
- create 3D assets from a single image
- export NeRF scenes as textured meshes
- experiment with score distillation sampling for 3D generation
- build a 3D content generation pipeline with stable diffusion
- render novel views of AI-generated 3D objects

## When to choose
- you want an open-source, hackable PyTorch implementation of Dreamfusion
- you need text-to-3D or image-to-3D generation with mesh export
- you want to experiment with NeRF backbones like Instant-NGP for 3D generation
- you need a research baseline for score distillation sampling

## When to avoid
- you need production-quality 3D generation matching the original paper
- you want the most up-to-date text-to-3D implementation (consider threestudio instead)
- you lack a CUDA-capable GPU
- you need a polished GUI application rather than a research codebase

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, stable-diffusion, graphics, simulation
- domain: artificial-intelligence, deep-learning, computer-vision, graphics, machine-learning
- platform: python, cross-platform
- tags: text-to-3d, image-to-3d, nerf, dreamfusion, 3d-generation, mesh-export, diffusion-models, pytorch, gpu, linux

## Member repositories
- ashawkey/stable-dreamfusion (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:26.033617+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:24:47.278966+00:00, confidence not recorded.
  - readme: https://github.com/ashawkey/stable-dreamfusion (fetched 2026-08-28T04:10:26.033617+00:00, sha 737bbc37f5a1)
- Data as of 2026-08-30T08:39:29.467469+00:00.