Papers › PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions

PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions

23 Sep 2024arXiv:2409.15278archive 2025-07-28

Weifeng Lin, Xinyu Wei, Renrui Zhang, Le Zhuo, Shitian Zhao, Siyuan Huang, Junlin Xie, Yu Qiao, Peng Gao, Hongsheng Li

This paper presents a versatile image-to-image visual assistant, PixWizard, designed for image generation, manipulation, and translation based on free-from language instructions. To this end, we tackle a variety of vision tasks into a unified image-text-to-image generation framework and curate an Omni Pixel-to-Pixel Instruction-Tuning Dataset. By constructing detailed instruction templates in natural language, we comprehensively include a large set of diverse vision tasks such as text-to-image generation, image restoration, image grounding, dense image prediction, image editing, controllable generation, inpainting/outpainting, and more. Furthermore, we adopt Diffusion Transformers (DiT) as our foundation model and extend its capabilities with a flexible any resolution mechanism, enabling the model to dynamically process images based on the aspect ratio of the input, closely aligning with human perceptual processes. The model also incorporates structure-aware and semantic-aware guidance to facilitate effective fusion of information from the input image. Our experiments demonstrate that PixWizard not only shows impressive generative and understanding abilities for images with diverse resolutions but also exhibits promising generalization capabilities with unseen tasks and human instructions. The code and related resources are available at https://github.com/AFeng-x/PixWizard

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2409.15278")

Code

Syntology Ran 15 of 17 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 2 ran · violated contract; 4 ran · our draft was wrong; 9 ran with no contract checked.

By repository: official repository: 17 samples from 1 repository, 15 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

afeng-x/pixwizard officialmentioned in papermentioned on GitHubpytorchMIT 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

17 samples harvested; 15 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · violated contract
4ran · our draft was wrong
9ran
2unverified

Licence: 0 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from afeng-x/pixwizard. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

MultiHot_Gumbel_Softmax afeng-x/pixwizard/models/model.py official repository ran MIT (permissive) · 49688b7f4b1c6d3d · report
add_options afeng-x/pixwizard/entry_point.py official repository ran · our draft was wrong MIT (permissive) · 2a92f0d95dce3ea2 · report
always afeng-x/pixwizard/models/clip/x_transformer.py official repository ran · our draft was wrong MIT (permissive) · fe5dd5258046898c · report
center_crop afeng-x/pixwizard/imgproc.py official repository ran MIT (permissive) · ed9eb205e6768a44 · report
center_crop_arr afeng-x/pixwizard/imgproc.py official repository ran · our draft was wrong MIT (permissive) · ea73360d2d5d9224 · report
default afeng-x/pixwizard/models/clip/x_transformer.py official repository ran · violated contract MIT (permissive) · 424012cb37b31172 · report
encode_prompt afeng-x/pixwizard/sample_pixwizard.py official repository ran MIT (permissive) · a36c1723b0978202 · report
exists afeng-x/pixwizard/models/clip/x_transformer.py official repository ran · violated contract MIT (permissive) · aa5486a3650902d8 · report
expand_t_like_x afeng-x/pixwizard/transport/path.py official repository ran MIT (permissive) · 1c00a422b396fa8b · report
find_closest_size afeng-x/pixwizard/sample_pixwizard.py official repository ran MIT (permissive) · 6bcc66e5235c74ae · report
isimage afeng-x/pixwizard/models/clip/util.py official repository ran MIT (permissive) · b1368330cf0f5642 · report
ismap afeng-x/pixwizard/models/clip/util.py official repository ran MIT (permissive) · d72762b700feee6f · report
modulate afeng-x/pixwizard/models/model.py official repository ran fingerprinted MIT (permissive) · 128eb60a7316f121 · report
var_center_crop afeng-x/pixwizard/imgproc.py official repository ran MIT (permissive) · 7318f2abbfa63f83 · report
zero_module afeng-x/pixwizard/models/clip/modules.py official repository ran · our draft was wrong MIT (permissive) · 129b804760b3115f · report
log_txt_as_img afeng-x/pixwizard/models/clip/util.py official repository unverified MIT (permissive) · f9bd2e83191afad1 · report
none_or_str afeng-x/pixwizard/sample_pixwizard.py official repository unverified MIT (permissive) · 2fc6fdb85f13dc41 · report

Tasks

Image GenerationImage RestorationText to Image GenerationText-to-Image Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DiffusionSET

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