Papers › InstanceDiffusion: Instance-level Control for Image Generation

InstanceDiffusion: Instance-level Control for Image Generation

5 Feb 2024CVPR 2024 1arXiv:2402.03290archive 2025-07-28

Xudong Wang, Trevor Darrell, Sai Saketh Rambhatla, Rohit Girdhar, Ishan Misra

Text-to-image diffusion models produce high quality images but do not offer control over individual instances in the image. We introduce InstanceDiffusion that adds precise instance-level control to text-to-image diffusion models. InstanceDiffusion supports free-form language conditions per instance and allows flexible ways to specify instance locations such as simple single points, scribbles, bounding boxes or intricate instance segmentation masks, and combinations thereof. We propose three major changes to text-to-image models that enable precise instance-level control. Our UniFusion block enables instance-level conditions for text-to-image models, the ScaleU block improves image fidelity, and our Multi-instance Sampler improves generations for multiple instances. InstanceDiffusion significantly surpasses specialized state-of-the-art models for each location condition. Notably, on the COCO dataset, we outperform previous state-of-the-art by 20.4% AP₅₀ᵇᵒˣ for box inputs, and 25.4% IoU for mask inputs.

PaperPDFConference PDFCodeCode 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 18 code samples harvested from 1 repository linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 2 violated, 6 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 17 ran (10 with no instrument failure; 7 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

frank-xwang/InstanceDiffusion officialmentioned on GitHubpytorchApache-2.0Syntology: 18 samples, 17 ran (7 instrument-failed) · 1 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

18 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 2 violated, 6 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
2ran · violated contract
5ran · our draft was wrong
2ran; the contract check could not run
6ran
1unverified

Licence: 0 of the 18 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 frank-xwang/InstanceDiffusion. “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.

frank-xwang/InstanceDiffusion official repository 18 samples, 17 ran (7 instrument-failed) · 1 unverified
batch_to_device in 18 papers dataset/jsondataset.py ran · our draft was wrong Apache-2.0 (permissive) · 6a31c83c41f11b71 · report fixture: signature batch:dict/0/?, device:str/0/str · returned dict · level recorded 2026-09-24
close_contour dataset/decode_item.py ran · violated contract fingerprinted Apache-2.0 (permissive) · 24680b34da633bbd · report fixture: signature contour:ndarray/2/float · returned ndarray · level recorded 2026-09-24
complete_mask inference.py ran · our draft was wrong Apache-2.0 (permissive) · 2fac02c349935452 · report fixture: signature has_mask:list/1/float, max_objs:int/0/int · returned Tensor · level recorded 2026-09-24
convert_coco_box eval_local.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 0226083d79fbec56 · report fixture: signature bbox:list/1/float, img_info:dict/0/? · returned list · level recorded 2026-09-24
create_ema utils/model.py ran · our draft was wrong Apache-2.0 (permissive) · 8336fe993ab97e1e · report fixture: signature model:callable/0/?, enable_ema:bool/0/bool · returned tuple · level recorded 2026-09-24
decode_base64_to_pillow dataset/decode_item.py ran · honoured contract Apache-2.0 (permissive) · 0ededb39dd4d5702 · report fixture: signature image_b64:str/0/str · returned Image · level recorded 2026-09-24
decode_tensor_from_string dataset/decode_item.py ran · honoured contract Apache-2.0 (permissive) · ad34702f4726aa2e · report fixture: signature arr_str:str/0/str, use_tensor:bool/0/bool · returned Tensor · level recorded 2026-09-24
draw_box in 16 papers dataset/base_dataset.py ran · our draft was wrong Apache-2.0 (permissive) · 8191ff51c4b074ff · report fixture: signature img:Image/0/?, boxes:list/1/list · returned Image · level recorded 2026-09-24
encode_tensor_as_string dataset-generation/submitit_automatic_label_ram_save_json.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 6de5057cb6ed75b0 · report fixture: signature arr:ndarray/2/float · returned str · level recorded 2026-09-24
get_clip_feature_text dataset-generation/submitit_automatic_label_ram_save_json.py ran Apache-2.0 (permissive) · 0d1f144ac0ae3d6b · report fixture: signature model:callable/0/?, processor:callable/0/?, input:str/0/str · returned Tensor · level recorded 2026-09-24
get_point_from_box eval_local.py ran · violated contract fingerprinted Apache-2.0 (permissive) · dbb0b3758a575e0e · report fixture: signature bbox:list/1/float · returned list · level recorded 2026-09-24
preprocess_text in 26 papers dataset-generation/submitit_automatic_label_ram_save_json.py ran Apache-2.0 (permissive) · cc40c350f2fdbdf0 · report fixture: signature processor:callable/0/?, input:str/0/str · returned dict · level recorded 2026-09-24
rescale_box inference.py ran Apache-2.0 (permissive) · 1b3923351aeaafb3 · report fixture: signature bbox:list/1/int, width:int/0/int, height:int/0/int · returned list · level recorded 2026-09-24
rescale_points eval_local.py ran Apache-2.0 (permissive) · 075b026765e25e3e · report fixture: signature point:list/1/int, width:int/0/int, height:int/0/int · returned list · level recorded 2026-09-24
sub_batch dataset/jsondataset.py ran Apache-2.0 (permissive) · c9b050c82d78f83d · report fixture: signature batch:dict/0/?, num:int/0/int · returned dict · level recorded 2026-09-24
to_valid dataset/base_dataset.py ran Apache-2.0 (permissive) · 08fa56c4d4f18a91 · report fixture: signature x0:int/0/int, y0:int/0/int, x1:int/0/int, y1:int/0/int, image_size:int/0/int, min_box_size:float/0/float · returned tuple · level recorded 2026-09-24
to_valid_scribbles dataset/base_dataset.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · ce28a1eb6ea4fde7 · report fixture: signature scribbles:list/1/int, image_size:int/0/int · returned list · level recorded 2026-09-24
load_ckpt in 31 papers utils/model.py unverified Apache-2.0 (permissive) · 37960ce701410505 · report

Tasks

Conditional Text-to-Image SynthesisImage GenerationInstance SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Conditional Text-to-Image Synthesis COCO-MIG Instance Diffusion (zero-shot) instance success rate 0.51 #3 of 5 Archive leaderboard report
Conditional Text-to-Image Synthesis COCO-MIG Instance Diffusion (zero-shot) mIoU 0.46 #3 of 5 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

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