Papers › CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Models

CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Models

24 Apr 2024arXiv:2404.15677archive 2025-07-28

Qinghe Wang, Baolu Li, Xiaomin Li, Bing Cao, Liqian Ma, Huchuan Lu, Xu Jia

Recent advances in text-to-image models have opened new frontiers in human-centric generation. However, these models cannot be directly employed to generate images with consistent newly coined identities. In this work, we propose CharacterFactory, a framework that allows sampling new characters with consistent identities in the latent space of GANs for diffusion models. More specifically, we consider the word embeddings of celeb names as ground truths for the identity-consistent generation task and train a GAN model to learn the mapping from a latent space to the celeb embedding space. In addition, we design a context-consistent loss to ensure that the generated identity embeddings can produce identity-consistent images in various contexts. Remarkably, the whole model only takes 10 minutes for training, and can sample infinite characters end-to-end during inference. Extensive experiments demonstrate excellent performance of the proposed CharacterFactory on character creation in terms of identity consistency and editability. Furthermore, the generated characters can be seamlessly combined with the off-the-shelf image/video/3D diffusion models. We believe that the proposed CharacterFactory is an important step for identity-consistent character generation. Project page is available at: https://qinghew.github.io/CharacterFactory/.

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 9 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 7 ran (6 with no instrument failure; 1 where Syntology's instrument failed). 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

qinghew/CharacterFactory officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 9 samples, 7 ran (1 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

9 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 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.

1ran · our draft was wrong
6ran
2unverified

Licence: 1 of the 9 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 qinghew/CharacterFactory. “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.

qinghew/CharacterFactory official repository 9 samples, 7 ran (1 instrument-failed) · 2 unverified
add_noise_return_paras utils.py ran Apache-2.0 (permissive) · 93719d1ffaad162b · report fixture: signature self:MockScheduler/0/?, original_samples:Tensor/4/float, noise:Tensor/4/float, timesteps:Tensor/1/int · returned tuple · level recorded 2026-09-24
discriminator_r1_loss_accelerator utils.py ran Apache-2.0 (permissive) · 0738f543a73a1096 · report fixture: signature accelerator:MockAccelerator/0/?, real_pred:Tensor/2/float, real_w:Tensor/2/float · returned Tensor · level recorded 2026-09-24
embedding_forward models/celeb_embeddings.py ran Apache-2.0 (permissive) · 30c989755522dca7 · report fixture: signature self:callable/0/?, input_ids:Tensor/2/int, position_ids:NoneType/0/?, name_batch:str/0/str, inputs_embeds:NoneType/0/?, embedding_manager:callable/0/?, only_embedding:bool/0/bool, random_embeddings:Tensor/3/float, timesteps:Tensor/1/int · returned tuple · level recorded 2026-09-24
get_clip_token_for_string in 16 papers models/embedding_manager.py ran Apache-2.0 (permissive) · 2340eb21cf6c4ce5 · report fixture: signature tokenizer:callable/0/?, string:str/0/str · returned Tensor · level recorded 2026-09-24
get_embedding_for_clip_token in 13 papers models/embedding_manager.py ran Apache-2.0 (permissive) · 185e8742c689f316 · report fixture: signature embedder:callable/0/?, token:Tensor/1/int · returned Tensor · level recorded 2026-09-24
get_rep_pos models/id_embedding/helpers.py ran Apache-2.0 (permissive) · fd9206b7174f95ba · report fixture: signature tokenized:Tensor/2/int, rep_tokens:list/1/int · returned list · level recorded 2026-09-24
leaky_relu in 24 papers models/id_embedding/meta_net.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · c8ec5333f4bcb71f · report fixture: signature p:float/0/float · returned LeakyReLU · level recorded 2026-09-22
discriminator_r1_loss utils.py unverified Apache-2.0 (permissive) · c451f8fed3a37a6f · report
shift_tensor_dim0 models/id_embedding/helpers.py unverified Apache-2.0 (permissive) · 109f33b49ebd4274 · report

Tasks

Consistent Character GenerationWord Embeddings

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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