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 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="2402.03290")

Code

Syntology Ran 17 of 18 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 17 ran with no contract checked.

By repository: official repository: 18 samples from 1 repository, 17 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

frank-xwang/InstanceDiffusion officialmentioned on GitHubpytorchApache-2.0 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; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

17ran
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. “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.

batch_to_device frank-xwang/InstanceDiffusion/dataset/jsondataset.py official repository ran Apache-2.0 (permissive) · 6a31c83c41f11b71 · report
close_contour frank-xwang/InstanceDiffusion/dataset/decode_item.py official repository ran fingerprinted Apache-2.0 (permissive) · 24680b34da633bbd · report
complete_mask frank-xwang/InstanceDiffusion/inference.py official repository ran Apache-2.0 (permissive) · 2fac02c349935452 · report
convert_coco_box frank-xwang/InstanceDiffusion/eval_local.py official repository ran Apache-2.0 (permissive) · 0226083d79fbec56 · report
create_ema frank-xwang/InstanceDiffusion/utils/model.py official repository ran Apache-2.0 (permissive) · 8336fe993ab97e1e · report
decode_base64_to_pillow frank-xwang/InstanceDiffusion/dataset/decode_item.py official repository ran Apache-2.0 (permissive) · 0ededb39dd4d5702 · report
decode_tensor_from_string frank-xwang/InstanceDiffusion/dataset/decode_item.py official repository ran Apache-2.0 (permissive) · ad34702f4726aa2e · report
draw_box frank-xwang/InstanceDiffusion/dataset/base_dataset.py official repository ran Apache-2.0 (permissive) · 8191ff51c4b074ff · report
encode_tensor_as_string frank-xwang/InstanceDiffusion/dataset-generation/submitit_automatic_label_ram_save_json.py official repository ran Apache-2.0 (permissive) · 6de5057cb6ed75b0 · report
get_clip_feature_text frank-xwang/InstanceDiffusion/dataset-generation/submitit_automatic_label_ram_save_json.py official repository ran Apache-2.0 (permissive) · 0d1f144ac0ae3d6b · report
get_point_from_box frank-xwang/InstanceDiffusion/eval_local.py official repository ran fingerprinted Apache-2.0 (permissive) · dbb0b3758a575e0e · report
preprocess_text frank-xwang/InstanceDiffusion/dataset-generation/submitit_automatic_label_ram_save_json.py official repository ran Apache-2.0 (permissive) · cc40c350f2fdbdf0 · report
rescale_box frank-xwang/InstanceDiffusion/inference.py official repository ran Apache-2.0 (permissive) · 1b3923351aeaafb3 · report
rescale_points frank-xwang/InstanceDiffusion/eval_local.py official repository ran Apache-2.0 (permissive) · 075b026765e25e3e · report
sub_batch frank-xwang/InstanceDiffusion/dataset/jsondataset.py official repository ran Apache-2.0 (permissive) · c9b050c82d78f83d · report
to_valid frank-xwang/InstanceDiffusion/dataset/base_dataset.py official repository ran Apache-2.0 (permissive) · 08fa56c4d4f18a91 · report
to_valid_scribbles frank-xwang/InstanceDiffusion/dataset/base_dataset.py official repository ran fingerprinted Apache-2.0 (permissive) · ce28a1eb6ea4fde7 · report
load_ckpt frank-xwang/InstanceDiffusion/utils/model.py official repository 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