# deepseek-ai/DreamCraft3D

[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior

Repository: https://github.com/deepseek-ai/DreamCraft3D
Canonical: https://ross.abutalabs.com/products/dreamcraft3d
Homepage: https://mrtornado24.github.io/DreamCraft3D/
Language: Python
License: MIT
License Family: permissive
Topics: 3d-generation, aigc, diffusion-models, generative-model, image-to-3d, 3d-creation
Last push: 2025-04-22T11:09:39+00:00

## Health v2 (maintenance only)
Score: 35/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 17, release rhythm 35, longevity 74
- inputs: {"age_days": 1045, "days_push": 498, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3021, forks 357 (observed 2026-08-28T04:07:38.486814+00:00)

## What it is
Official PyTorch implementation of DreamCraft3D, an ICLR 2024 hierarchical 3D content generation method that turns a single 2D image into a high-fidelity, coherent 3D object. It combines score distillation sampling for geometry sculpting with a bootstrapped, DreamBooth-personalized diffusion prior for photorealistic texture boosting.

## Use cases
- generate a 3d model from a single image
- create textured 3d meshes from a reference photo
- image to 3d asset generation with diffusion models
- produce photorealistic 3d objects for games or rendering
- research score distillation for 3d generation
- turn concept art into a 3d mesh

## When to choose
- you need to convert a single 2D image into a coherent, textured 3D mesh
- you want a research-grade implementation of score distillation and bootstrapped diffusion priors
- you have GPU resources and want state-of-the-art single-image 3D generation quality

## When to avoid
- you need fast, real-time 3D generation - optimization is slow and GPU-intensive
- you want a polished end-user application rather than research code
- you lack a CUDA-capable GPU or the environment to run diffusion models

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, deep-learning, image-processing, graphics, simulation
- domain: artificial-intelligence, machine-learning, graphics, computer-vision
- platform: python
- tags: 3d-generation, diffusion-models, image-to-3d, score-distillation, text-to-3d, aigc, generative-models, research-code, gpu, linux

## Member repositories
- deepseek-ai/DreamCraft3D (main) score 35

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:38.486814+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 2026-08-30T07:29:55.759762+00:00, confidence not recorded.
  - readme: https://github.com/deepseek-ai/DreamCraft3D (fetched 2026-08-28T04:07:38.486814+00:00, sha 0f10facfdcb5)
  - homepage: https://mrtornado24.github.io/DreamCraft3D/ (fetched 2026-08-29T09:45:02.800680+00:00, sha 5d81ad21665f)
- Data as of 2026-08-30T08:39:29.467469+00:00.