Papers › Muse: Text-To-Image Generation via Masked Generative Transformers

Muse: Text-To-Image Generation via Masked Generative Transformers

2 Jan 2023arXiv:2301.00704archive 2025-07-28

Huiwen Chang, Han Zhang, Jarred Barber, AJ Maschinot, Jose Lezama, Lu Jiang, Ming-Hsuan Yang, Kevin Murphy, William T. Freeman, Michael Rubinstein, Yuanzhen Li, Dilip Krishnan

We present Muse, a text-to-image Transformer model that achieves state-of-the-art image generation performance while being significantly more efficient than diffusion or autoregressive models. Muse is trained on a masked modeling task in discrete token space: given the text embedding extracted from a pre-trained large language model (LLM), Muse is trained to predict randomly masked image tokens. Compared to pixel-space diffusion models, such as Imagen and DALL-E 2, Muse is significantly more efficient due to the use of discrete tokens and requiring fewer sampling iterations; compared to autoregressive models, such as Parti, Muse is more efficient due to the use of parallel decoding. The use of a pre-trained LLM enables fine-grained language understanding, translating to high-fidelity image generation and the understanding of visual concepts such as objects, their spatial relationships, pose, cardinality etc. Our 900M parameter model achieves a new SOTA on CC3M, with an FID score of 6.06. The Muse 3B parameter model achieves an FID of 7.88 on zero-shot COCO evaluation, along with a CLIP score of 0.32. Muse also directly enables a number of image editing applications without the need to fine-tune or invert the model: inpainting, outpainting, and mask-free editing. More results are available at https://muse-model.github.io

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 21 code samples: 18 from 5 repositories linked to this paper, 3 identical to code harvested from another paper's repository. Across all 21: 19 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 5 violated, 1 with no contract checked; 11 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 10 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 18 samples from 5 repositories, 16 ran (7 with no instrument failure; 9 where Syntology's instrument failed); 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 11 of the 19 samples that ran have no recorded date.

baaivision/muse-pytorch mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
huggingface/amused mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
huggingface/open-muse mentioned on GitHubjaxSyntology: 4 samples, 4 ran (4 instrument-failed) · 0 unverified report
Qiyuan-Ge/PaintMind pytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
lucidrains/muse-pytorch pytorchMITSyntology: 8 samples, 6 ran (2 instrument-failed) · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

21 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 5 violated, 1 with no contract checked; 11 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
5ran · violated contract
10ran · our draft was wrong
1ran; the contract check could not run
1ran
2unverified

Licence: 11 of the 21 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 5 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 4 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. 3 samples are listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

baaivision/muse-pytorch community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
LSimple train_t2i_discrete_muse.py ran · our draft was wrong MIT (permissive) · 35a0e57cdda9e212 · report fixture: signature x0:Tensor/2/int, nnet:callable/0/?, schedule:StandInSchedule/0/? · returned Tensor · level recorded 2026-09-22
add_gumbel_noise in 32 papers
census: 7 implementations from 12 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
libs/muse.py ran · our draft was wrong MIT (permissive) · 9ef9985f5609c318 · report fixture: signature t:Tensor/2/float, temperature:float/0/float, device:device/0/? · returned Tensor · level recorded 2026-09-22
huggingface/amused community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
encode_prompt in 54 papers training/train_amused.py ran · our draft was wrong no licence file found · pointer only · af6cdb4b6a4b5860 · report fixture: signature text_encoder:callable/0/?, input_ids:Tensor/2/int · returned tuple · level recorded 2026-09-22
tokenize_prompt in 23 papers training/train_amused.py ran · honoured contract no licence file found · pointer only · e63f8661cb0af2c8 · report fixture: signature tokenizer:callable/0/?, prompt:str/0/str · returned Tensor · level recorded 2026-09-22
huggingface/open-muse community (archive-listed) 4 samples, 4 ran (4 instrument-failed) · 0 unverified
make_attention_mask in 6 papers muse/modeling_transformer.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · e88526ab8fc3ebc4 · report fixture: signature query_input:Tensor/2/float, key_input:Tensor/2/float, pairwise_fn:callable/0/? · returned Tensor · level recorded, date not recorded
prob_mask_like in 16 papers muse/modeling_transformer.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran; the contract check could not run (RAISES) · metamorphic tier: deterministic licence of this copy not recorded · 162f6eae613812c6 · report fixture: signature shape:tuple/1/int, prob:float/0/float, device:NoneType/0/? · returned Tensor · level recorded, date not recorded
soft_target_cross_entropy training/train_maskgit_imagenet.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong fingerprinted licence of this copy not recorded · d8437c41cc2a860f · report fixture: signature logits:Tensor/3/float, targets:Tensor/2/int, soft_targets:Tensor/3/float · returned Tensor · level recorded, date not recorded
uniform in 58 papers muse/modeling_transformer.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · 66e51521e0875290 · report fixture: signature shape:tuple/1/int, min:int/0/int, max:int/0/int, device:NoneType/0/? · returned Tensor · level recorded, date not recorded
Qiyuan-Ge/PaintMind community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
default in 430 papers paintmind/generate.py ran · violated contract Apache-2.0 (permissive) · fbf9ec7be545688e · report fixture: signature val:NoneType/0/?, d:str/0/str · returned str · level recorded 2026-09-22
mask_schedule paintmind/generate.py ran · violated contract fingerprinted Apache-2.0 (permissive) · 4fd2dac3028a4e1f · report fixture: signature ratio:float/0/float · returned float64 · level recorded 2026-09-22
lucidrains/muse-pytorch community (archive-listed) 8 samples, 6 ran (2 instrument-failed) · 2 unverified
identity in 174 papers
census: 11 implementations from 39 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
muse_maskgit_pytorch/trainers.py ran · honoured contract MIT (permissive) · 7f1040f5e3991d5e · report fixture: signature t:Tensor/2/float, args:tuple/1/Tensor, kwargs:dict/0/? · returned Tensor · level recorded, date not recorded
default in 430 papers muse_maskgit_pytorch/muse_maskgit_pytorch.py ran · violated contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 60fff7c3c400d7ff · report fixture: signature val:int/0/int, d:int/0/int · returned int · level recorded, date not recorded
eval_decorator in 15 papers muse_maskgit_pytorch/muse_maskgit_pytorch.py ran · our draft was wrong MIT (permissive) · c16aee9490eb8729 · report fixture: signature fn:callable/0/? · returned function · level recorded, date not recorded
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
muse_maskgit_pytorch/attend.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · aa5486a3650902d8 · report fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded
find_index in 8 papers muse_maskgit_pytorch/trainers.py ran MIT (permissive) · 3474c6be94998255 · report fixture: signature arr:list/1/int, cond:callable/0/? · returned int · level recorded 2026-09-25
once in 16 papers muse_maskgit_pytorch/attend.py ran · our draft was wrong MIT (permissive) · 52e10a7d6b0fa036 · report fixture: signature fn:callable/0/? · returned function · level recorded 2026-09-22
get_model in 368 papers muse_maskgit_pytorch/t5.py unverified MIT (permissive) · feff9391629f5643 · report
get_tokenizer in 156 papers muse_maskgit_pytorch/t5.py unverified MIT (permissive) · cbdf413e88112af9 · report
Repository not located 3 samples, 3 ran (2 instrument-failed) · 0 unverified
3 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
chunk in 52 papers repository not located ran · our draft was wrong licence of this copy not recorded · 8241c0562bc710fd · report fixture: signature it:list/1/int, size:int/0/int · returned callable_iterator · level recorded, date not recorded
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
repository not located ran · violated contract licence of this copy not recorded · 608e364a9d2376a3 · report fixture: signature x:Tensor/1/int · returned bool · level recorded, date not recorded
flatten_omega_conf repository not located ran · our draft was wrong licence of this copy not recorded · ef8d9a0b717d3cb0 · report fixture: signature cfg:DictConfig/0/?, resolve:bool/0/bool · returned list · level recorded, date not recorded

Tasks

Image GenerationLanguage ModellingLarge Language ModelText to Image GenerationText-to-Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-to-Image Generation MS-COCO Muse-3B (zero-shot) FID 7.88 #2 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPECLIPDense ConnectionsDiffusionDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections