SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.07209 · 2024

MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance

arXiv · PDF · Open in the Atlas

Code that ran

7 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2406.07209.json · badge: /api/ran/2406.07209.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
MS-Diffusion/MS-Diffusion canonical (classifier label)
classifier basis: census
7 ran · 0 no recorded run
FunctionStatusWhere it lives
FeedForward Ran
ran; our contract draft was wrong, not the code
MS-Diffusion/MS-Diffusion/msdiffusion/models/projection.py
pointer only (licence: MIT); the stored copy get_code serves, from rainbowluocs/openomni, is pointer only (licence: NONE) · get_code("5105747c2711b1cb")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from rainbowluocs/openomni, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_eot_idx Ran
ran, honoured the contract we drafted
MS-Diffusion/MS-Diffusion/msdiffusion/utils.py
code served (permissive licence) · get_code("27c32a7bd4cb34f6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

class MockTokenizer:
    def encode(self, word):
        # Return a list of token ids
        # Length varies based on word to test the calculation
        if word == "hello":
            return [1, 2, 3]  # length 3
        elif word == "world":
            return [4, 5]  # length 2
        elif word == "test":
            return [6, 7, 8, 9]  # length 4
        else:
            return [10]  # length 1

tokenizer = MockTokenizer()
prompt = "hello world test"

ARGS = {
    "tokenizer": tokenizer,
    "prompt": prompt
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_phrase_idx Ran
ran; our contract draft was wrong, not the code
MS-Diffusion/MS-Diffusion/msdiffusion/utils.py
code served (permissive licence) · get_code("4df68058ed6a2d10")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import re

class MockTokenizer:
    def encode(self, word):
        # Return a list of token IDs with length based on word length
        # Using length + 2 to match the "- 2" operations in the function
        return list(range(len(word) + 2))

ARGS = {
    "tokenizer": MockTokenizer(),
    "phrase": "hello world",
    "prompt": "hello world foo bar hello world baz",
    "get_last_word": False,
    "num": 0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_word_idx Ran
ran, honoured the contract we drafted
MS-Diffusion/MS-Diffusion/msdiffusion/dataset/datagenerator.py
code served (permissive licence) · get_code("7b641c17c4887779")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import re

class MockTokenizer:
    def encode(self, text):
        # Simple mock: return a list with length proportional to word length
        # Adding some base tokens to simulate tokenizer behavior
        return ['<start>'] + list(text) + ['<end>']

tokenizer = MockTokenizer()
word = "hello"
prompt = "hello world this is a test"

ARGS = {
    "tokenizer": tokenizer,
    "word": word,
    "prompt": prompt
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
masked_mean Ran
ran; our contract draft was wrong, not the code
MS-Diffusion/MS-Diffusion/msdiffusion/models/projection.py
pointer only (licence: MIT); the stored copy get_code serves, from Minyeol/MIDAS, is pointer only (licence: NONE) · get_code("230588e8f1237737")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Minyeol/MIDAS, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

minmax_normalize Ran
ran; our contract draft was wrong, not the code
MS-Diffusion/MS-Diffusion/msdiffusion/models/attention_processor.py
code served (permissive licence) · get_code("423750878c152e2a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (2, 4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small batch of maps with shape (batch_size, height, width)
# Using distinct dimensions: batch=2, height=4, width=3
batch_maps = torch.randn(2, 4, 3)

ARGS = {
    "batch_maps": batch_maps
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
reshape_tensor Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
MS-Diffusion/MS-Diffusion/msdiffusion/models/projection.py
pointer only (licence: MIT); the stored copy get_code serves, from Minyeol/MIDAS, is pointer only (licence: NONE) · get_code("4cb2e2a2ca0bec9f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Minyeol/MIDAS, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 3 the same month, 3 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
FeedForward 47 other papers
16 dated earlier, 2 the same month, 28 later, 1 same year, order not determinable · 4 only as an assembly brick
2204.14198 (2022-04)
Flamingo: a Visual Language Model for Few-Shot Learning
2308.02463 (2023-08)
Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&amp;3D Medical Data
2308.06721 (2023-08)
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
and 44 more not named here
reshape_tensor 30 other papers
10 dated earlier, 1 the same month, 19 later
2308.06721 (2023-08)
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
2312.04461 (2023-12)
PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding
2312.16693 (2023-12)
I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models
and 27 more not named here
masked_mean 18 other papers
6 dated earlier, 1 the same month, 11 later
2308.06721 (2023-08)
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
2312.04461 (2023-12)
PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding
2312.16693 (2023-12)
I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models
and 15 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent advancements in text-to-image generation models have dramatically enhanced the generation of photorealistic images from textual prompts, leading to an increased interest in personalized text-to-image applications, particularly in multi-subject scenarios. However, these advances are hindered by two main challenges: firstly, the need to accurately maintain the details of each referenced subject in accordance with the textual descriptions; and secondly, the difficulty in achieving a cohesive representation of multiple subjects in a single image without introducing inconsistencies. To address these concerns, our research introduces the MS-Diffusion framework for layout-guided zero-shot image personalization with multi-subjects. This innovative approach integrates grounding tokens with the feature resampler to maintain detail fidelity among subjects. With the layout guidance, MS-Diffusion further improves the cross-attention to adapt to the multi-subject inputs, ensuring that each subject condition acts on specific areas. The proposed multi-subject cross-attention orchestrates harmonious inter-subject compositions while preserving the control of texts. Comprehensive quantitative and qualitative experiments affirm that this method surpasses existing models in both image and text fidelity, promoting the development of personalized text-to-image generation. The project page is https://MS-Diffusion.github.io.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.07209")
get_code_for_paper("2406.07209")
have("2406.07209")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2406.07209.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2406.07209.svg)](https://syntology.ai/paper/2406.07209)

Connect an agent — have() is free.