SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.16213 · NeurIPS · 2023

ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation

Hang Su, Jun Zhu, Chongxuan Li, Yikai Wang, Fan Bao, Cheng Lu, Zhengyi Wang

arXiv · PDF · Open in the Atlas

Code that ran

2 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2305.16213.json · badge: /api/ran/2305.16213.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
threestudio-project/threestudio canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
yuanzhi-zhu/prolific_dreamer2d community
Papers with Code archive
1 ran · 2 no recorded run
FunctionStatusWhere it lives
predict_noise0_diffuser Ran
ran; our contract draft was wrong, not the code
yuanzhi-zhu/prolific_dreamer2d/model_utils.py
pointer only (licence: NONE) · get_code("aba8623ee1020604")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yuanzhi-zhu/prolific_dreamer2d when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

tail Ran
ran; our contract draft was wrong, not the code
threestudio-project/threestudio/gradio_app.py
code served (permissive licence) · get_code("e93da14f176f38af")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import io

# Create a file-like object with some content
file_content = b"""line 1
line 2
line 3
line 4
line 5
line 6
line 7
line 8
line 9
line 10
line 11
line 12
line 13
line 14
line 15
line 16
line 17
line 18
line 19
line 20
line 21
line 22
line 23
line 24
line 25"""

f = io.BytesIO(file_content)

ARGS = {
    "f": f,
    "window": 20
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
on_model_selector_change Not yet run
unverified (harvested, no recorded run)
threestudio-project/threestudio/gradio_app.py
code served (permissive licence) · get_code("849b90aa3c658242")
How it ran

no invocation recorded.

predict_noise0_diffuser_multistep Not yet run
unverified (harvested, no recorded run)
yuanzhi-zhu/prolific_dreamer2d/model_utils.py
pointer only (licence: NONE) · get_code("740af92e1f334629")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yuanzhi-zhu/prolific_dreamer2d when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

sds_vsd_grad_diffuser Not yet run
unverified (harvested, no recorded run)
yuanzhi-zhu/prolific_dreamer2d/model_utils.py
pointer only (licence: NONE) · get_code("1b1adaf9115ca2a2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yuanzhi-zhu/prolific_dreamer2d when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
tail 3 other papers
3 later
2310.16818 (2023-10)
DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
2312.02201 (2023-12)
ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation
2312.06439 (2023-12)
DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior
on_model_selector_change 2 other papers
2 later
2312.02201 (2023-12)
ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation
2312.06439 (2023-12)
DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Score distillation sampling (SDS) has shown great promise in text-to-3D generation by distilling pretrained large-scale text-to-image diffusion models, but suffers from over-saturation, over-smoothing, and low-diversity problems. In this work, we propose to model the 3D parameter as a random variable instead of a constant as in SDS and present variational score distillation (VSD), a principled particlebased variational framework to explain and address the aforementioned issues in text-to-3D generation. We show that SDS is a special case of VSD and leads to poor samples with both small and large CFG weights. In comparison, VSD works well with various CFG weights as ancestral sampling from diffusion models and simultaneously improves the diversity and sample quality with a common CFG weight (i.e., 7.5). We further present various improvements in the design space for text-to-3D such as distillation time schedule and density initialization, which are orthogonal to the distillation algorithm yet not well explored. Our overall approach, dubbed ProlificDreamer, can generate high rendering resolution (i.e., 512 × 512) and high-fidelity NeRF with rich structure and complex effects (e.g., smoke and drops). Further, initialized from NeRF, meshes fine-tuned by VSD are meticulously detailed and photo-realistic. Project page and codes: https://ml.cs.tsinghua.edu.cn/prolificdreamer/.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2305.16213")
get_code_for_paper("2305.16213")
have("2305.16213")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2305.16213.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2305.16213.svg)](https://syntology.ai/paper/2305.16213)

Connect an agent — have() is free.