Paper Citation Record · LEDGER

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention

As of 15 August 2026, this Paper Citation Record lists 76 of 76 outbound references and 2 inbound Pith citation observations for arXiv:2411.19261.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2411.19261 v2

Coverage vector

measured 76 of 76 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T10:28:07.718327Z

measured 78 of 78 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-18T19:02:01.962726Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-18T19:02:48.668466Z

Reference resolution

76 of 76 outbound references displayed

verified exact0
verified fuzzy57
unresolved19
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 53c0b224-1058-400b-9893-73414e61ada5 · outbound

This paper cites an unresolved cited work.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T10:28:07.321078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2e488cd-e7b2-495c-b956-f25ab9be8aef · outbound

This paper cites Wasser- stein generative adversarial networks.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Wasser- stein generative adversarial networks

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.900847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 21a04ab4-092f-4195-8111-a7b71abda0f2 · outbound

This paper cites The chosen one: Consistent characters in text-to-image diffusion models.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention The chosen one: Consistent characters in text-to-image diffusion models

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.886446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0ac9ce18-b33f-44cb-adae-445ba8f2fd60 · outbound

This paper cites MasaCtrl: Tuning-free mu- tual self-attention control for consistent image synthesis and editing.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention MasaCtrl: Tuning-free mu- tual self-attention control for consistent image synthesis and editing

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.871482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 470e8c4b-5a7a-4534-aeec-5932dd256882 · outbound

This paper cites Character-centric story visualization via visual planning and token alignment.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Character-centric story visualization via visual planning and token alignment

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.856297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4191b648-8fa6-4009-a6fb-07b66464a15c · outbound

This paper cites PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T10:28:07.347203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be7d6101-da05-44d4-9bd2-0e516dced0e4 · outbound

This paper cites AnyDoor: Zero-shot object-level image customization.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention AnyDoor: Zero-shot object-level image customization

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.840730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 54804892-2456-440d-9b03-71e3244a4478 · outbound

This paper cites AutoStudio: Crafting Consistent Subjects in Multi-turn Interactive Image Generation.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention AutoStudio: Crafting Consistent Subjects in Multi-turn Interactive Image Generation

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T10:28:07.357591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32722c71-9b93-4bb9-be28-a1a748bf2e32 · outbound

This paper cites TheaterGen: Character Management with LLM for Consistent Multi-turn Image Generation.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention TheaterGen: Character Management with LLM for Consistent Multi-turn Image Generation

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T10:28:07.363152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84a4de94-b307-4022-a2b9-2468456b4d13 · outbound

This paper cites IDAdapter: Learning mixed features for tuning-free personalization of text-to-image mod- els.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention IDAdapter: Learning mixed features for tuning-free personalization of text-to-image mod- els

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.825152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0d2a07a2-ac15-481c-852c-def8fe177644 · outbound

This paper cites DreamSim: Learning new dimensions of human visual similarity using synthetic data.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention DreamSim: Learning new dimensions of human visual similarity using synthetic data

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.810335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e7585736-a511-46b4-a742-dd18ab443446 · outbound

This paper cites TeViS: Translating text synopses to video storyboards.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention TeViS: Translating text synopses to video storyboards

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.794929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c830d15b-3000-4d7e-bf39-956e72bf566f · outbound

This paper cites Improved training of Wasserstein GANs.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Improved training of Wasserstein GANs

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.779199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation cdae9647-4063-4df2-87fa-17cc2ff8ec95 · outbound

This paper cites Imagine this! scripts to composi- tions to videos.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Imagine this! scripts to composi- tions to videos

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.761630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 94af6647-2c5f-4ecb-a396-a25a154cdfda · outbound

This paper cites Learning profitable NFT image diffusions via multiple visual- policy guided reinforcement learning.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Learning profitable NFT image diffusions via multiple visual- policy guided reinforcement learning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.745907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7b00548a-cb16-425f-b357-bbfc2af197ab · outbound

This paper cites DreamStory: Open-domain story visualization by LLM-guided multi-subject consistent diffusion, 2024.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention DreamStory: Open-domain story visualization by LLM-guided multi-subject consistent diffusion, 2024

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.729939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 43c381bb-fd82-4aba-8663-73ce0b96865e · outbound

This paper cites Rotary position embedding for vision transformer.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Rotary position embedding for vision transformer

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.713425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0c136b2b-5331-43f5-8a46-b78ec9e03357 · outbound

This paper cites Classifier-free diffusion guidance.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Classifier-free diffusion guidance

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.695618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation bce6da0a-2ea0-46d8-b673-04be65d45e05 · outbound

This paper cites Denoising dif- fusion probabilistic models.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Denoising dif- fusion probabilistic models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T10:28:07.416700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b1c6d71-b16f-444d-89ab-48180e8af0c7 · outbound

This paper cites LoRA: Low-rank adaptation of large language models.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention LoRA: Low-rank adaptation of large language models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.667785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 80a11c5b-5846-4a34-b5ea-7bd4c66c3068 · outbound

This paper cites How much po- sition information do convolutional neural networks encode? In ICLR, 2020.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention How much po- sition information do convolutional neural networks encode? In ICLR, 2020

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.650469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation db15c263-30fb-4ae8-b755-9a40c1115293 · outbound

This paper cites Position, padding and predic- tions: A deeper look at position information in cnns.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Position, padding and predic- tions: A deeper look at position information in cnns

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.634960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 140f2528-c6fa-4fc9-a38d-6b42acea6163 · outbound

This paper cites Identity decoupling for multi-subject personalization of text- to-image models, 2024.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Identity decoupling for multi-subject personalization of text- to-image models, 2024

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.619298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2974fada-9138-4740-adec-49abc56d9d41 · outbound

This paper cites InstantFamily: Masked Attention for Zero-shot Multi-ID Image Generation.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention InstantFamily: Masked Attention for Zero-shot Multi-ID Image Generation

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T10:28:07.443721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e859a29-fcf7-4b1a-8aa5-119ea2976ede · outbound

This paper cites Auto-Encoding Variational Bayes.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Auto-Encoding Variational Bayes

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-12T10:28:07.449411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5777e1b-e368-47c8-a9f2-28995cbac58c · outbound

This paper cites OMG: Occlusion-friendly personalized multi-concept generation in diffusion models.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention OMG: Occlusion-friendly personalized multi-concept generation in diffusion models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.603745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1079a4fb-5cb4-4901-8e4c-afa795112615 · outbound

This paper cites an unresolved cited work.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-12T10:28:08.588023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0ec4fa2f-1f49-4ee9-8531-36eb143831e5 · outbound

This paper cites Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion Models.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T10:28:07.466041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e13df5e3-f074-47db-97a9-0b2701bc7384 · outbound

This paper cites Playground v2.5: Three insights to- wards enhancing aesthetic quality in text-to-image generation,.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Playground v2.5: Three insights to- wards enhancing aesthetic quality in text-to-image generation,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-12T10:28:07.472631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e57f8b29-bf20-4930-8f33-68b85da30fdf · outbound

This paper cites BLIP-diffusion: Pre- trained subject representation for controllable text-to-image generation and editing.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention BLIP-diffusion: Pre- trained subject representation for controllable text-to-image generation and editing

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.561427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 090eb7e2-30b5-43d0-a239-206ab6539959 · outbound

This paper cites BLIP: bootstrapping language-image pre-training for unified vision- language understanding and generation.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention BLIP: bootstrapping language-image pre-training for unified vision- language understanding and generation

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.545501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation eb9dbcd5-dca6-406b-833a-6a8fe88503aa · outbound

This paper cites BLIP- 2: bootstrapping language-image pre-training with frozen image encoders and large language models.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention BLIP- 2: bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.531067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e7fb4caa-20e6-42d8-80dd-e6ed6c8b2a5d · outbound

This paper cites StoryGAN: A sequential conditional gan for story visu- alization.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention StoryGAN: A sequential conditional gan for story visu- alization

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.516017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 10958af1-df54-4b0b-ab9c-40073dd5a913 · outbound

This paper cites PhotoMaker: Customizing realistic human photos via stacked id embedding.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention PhotoMaker: Customizing realistic human photos via stacked id embedding

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.500584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 82769b12-fa4e-4305-8d3c-7a43c53d0907 · outbound

This paper cites Unveiling the mask of position-information pattern through the mist of im- age features.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Unveiling the mask of position-information pattern through the mist of im- age features

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.485826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 017cdda8-1a0c-4cd4-83b9-b14e58e07131 · outbound

This paper cites Intelligent grimm-open-ended visual storytelling via latent diffusion models.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Intelligent grimm-open-ended visual storytelling via latent diffusion models

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.470698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b37abf56-c867-445a-8b71-1bbf4d9045f7 · outbound

This paper cites One-Prompt-One-Story: Free-lunch consistent text-to-image generation using a single prompt.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention One-Prompt-One-Story: Free-lunch consistent text-to-image generation using a single prompt

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.455164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation fe9025c9-4597-4391-9c7d-a3f7b0004258 · outbound

This paper cites DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-12T10:28:07.521913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b150656f-f703-4892-a2f5-aa8d3c37b371 · outbound

This paper cites Subject- Diffusion: Open domain personalized text-to-image gener- ation without test-time fine-tuning.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Subject- Diffusion: Open domain personalized text-to-image gener- ation without test-time fine-tuning

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.438469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0bd3a606-db96-4064-b3f1-1e1dd2ae42b7 · outbound

This paper cites AI illustrator: Translating raw descriptions into images by prompt-based cross-modal generation.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention AI illustrator: Translating raw descriptions into images by prompt-based cross-modal generation

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.423107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1c9d0833-af86-41fa-a69b-1a24fd456219 · outbound

This paper cites Integrating visuospa- tial, linguistic, and commonsense structure into story visual- ization.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Integrating visuospa- tial, linguistic, and commonsense structure into story visual- ization

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.407357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3a3b6bfc-9c32-4730-a2a9-2ecbcd3b2385 · outbound

This paper cites Im- proving generation and evaluation of visual stories via seman- tic consistency.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Im- proving generation and evaluation of visual stories via seman- tic consistency

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.391735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8e31393a-3c87-42d8-adfd-aaa56cd0f941 · outbound

This paper cites StoryDALL-E: Adapting pretrained text-to-image transform- ers for story continuation.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention StoryDALL-E: Adapting pretrained text-to-image transform- ers for story continuation

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.375865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation abd7752e-5937-4e09-9ddd-b0b19d132f7d · outbound

This paper cites Improved denoising diffusion probabilistic models.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Improved denoising diffusion probabilistic models

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.361091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 807fb1a4-54a6-46b7-b6ef-0eca8f40dc12 · outbound

This paper cites Synthesizing coherent story with auto-regressive latent diffusion models.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Synthesizing coherent story with auto-regressive latent diffusion models

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.346774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5515e56b-2a72-4cb2-adfd-22e59ce19975 · outbound

This paper cites PortraitBooth: A versatile portrait model for fast identity-preserved personalization.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention PortraitBooth: A versatile portrait model for fast identity-preserved personalization

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.332005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation dd169718-4788-401e-b5bc-004269fa7cef · outbound

This paper cites SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-12T10:28:07.577580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be80f2eb-5f3c-4ec5-98ce-0c05ec08bb2f · outbound

This paper cites Learning transferable visual models from natural language supervision.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Learning transferable visual models from natural language supervision

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.317237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b0df295b-97c3-4d2e-b66e-56998154c2a9 · outbound

This paper cites Make-a-Story: Visual memory conditioned consistent story generation.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Make-a-Story: Visual memory conditioned consistent story generation

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.302683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8b64795f-ab6c-422f-b28e-2cbb2fa90a70 · outbound

This paper cites Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-12T10:28:07.595466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b67d7295-ba24-42f1-9e55-403c2ccb7e72 · outbound

This paper cites Image-based video game asset generation and evaluation using deep learning: a systematic review of meth- ods and applications.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Image-based video game asset generation and evaluation using deep learning: a systematic review of meth- ods and applications

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.288204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5f5b9aa8-4db8-49ee-acf4-55e701654db0 · outbound

This paper cites High-resolution image syn- thesis with latent diffusion models.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention High-resolution image syn- thesis with latent diffusion models

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.273282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d498df8e-9a5c-44b9-8a51-f8766a691e87 · outbound

This paper cites U-net: Convolutional networks for biomedical image segmentation.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention U-net: Convolutional networks for biomedical image segmentation

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.258520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 44ba9f19-51b2-4338-9dd5-36a5419a9333 · outbound

This paper cites DreamBooth: Fine tuning text-to-image diffusion models for subject-driven gen- eration.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention DreamBooth: Fine tuning text-to-image diffusion models for subject-driven gen- eration

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.243752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 74a68153-adc6-4b97-be52-83170d8be1a4 · outbound

This paper cites LAION-5B: An open large-scale dataset for training next generation image-text models.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention LAION-5B: An open large-scale dataset for training next generation image-text models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-12T10:28:07.619388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d0c9ff2-7c45-4bc9-9bfa-55d870379e3e · outbound

This paper cites Denoising diffusion implicit models.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Denoising diffusion implicit models

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.229084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 90fdd870-b890-48ed-a0e0-9cc7ad095dc1 · outbound

This paper cites Score-based generative modeling through stochastic differential equations.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Score-based generative modeling through stochastic differential equations

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.214172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 23b63b59-7010-4746-a151-6b945db18211 · outbound

This paper cites Character-preserving coherent story visualization.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Character-preserving coherent story visualization

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.198902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 381de995-bb1c-4cb4-808d-41471e30febe · outbound

This paper cites Create your world: Lifelong text-to- image diffusion.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Create your world: Lifelong text-to- image diffusion

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.182146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7685712b-774f-49c7-be18-e63d0f090644 · outbound

This paper cites Kolors: Effective training of diffusion model for photorealistic text-to-image synthesis.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Kolors: Effective training of diffusion model for photorealistic text-to-image synthesis

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.166519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 96df95cd-1245-414f-87b3-80a463face34 · outbound

This paper cites Training-free consistent text-to-image generation.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Training-free consistent text-to-image generation

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.151065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ab8d6ba0-95b1-4fa8-bba7-14cc15b3d988 · outbound

This paper cites Storytelling and visualization: An extended survey.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Storytelling and visualization: An extended survey

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.134910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 862525d9-af51-4ace-8ce6-4da3dfa51e69 · outbound

This paper cites OneActor: Consistent subject generation via cluster- conditioned guidance.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention OneActor: Consistent subject generation via cluster- conditioned guidance

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.117464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 203d4ee9-6bf2-441b-9a17-d75a069808db · outbound

This paper cites Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-12T10:28:07.661616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66804eb6-e3dd-47ca-bf06-e2e071bdd6bc · outbound

This paper cites MS-Diffusion: Multi-subject zero-shot image personalization with layout guidance.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention MS-Diffusion: Multi-subject zero-shot image personalization with layout guidance

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.101186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation daf98722-cd0c-42e9-93f3-6dac30f9014c · outbound

This paper cites High-fidelity person-centric subject-to-image synthesis.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention High-fidelity person-centric subject-to-image synthesis

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.084878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3f658e01-5f1f-4c48-b7cb-ad10ab983199 · outbound

This paper cites IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-12T10:28:07.676143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f00ae2b5-4797-48ed-9fe7-e4f47e89202f · outbound

This paper cites LaPE: Layer- adaptive position embedding for vision transformers with independent layer normalization.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention LaPE: Layer- adaptive position embedding for vision transformers with independent layer normalization

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.069198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 76cc6391-fd9f-4025-975c-68283e1c4d54 · outbound

This paper cites Jedi: Joint- image diffusion models for finetuning-free personalized text- to-image generation.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Jedi: Joint- image diffusion models for finetuning-free personalized text- to-image generation

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.053421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation bd496979-f4a0-4b62-9cda-9fe562df1274 · outbound

This paper cites Adding conditional control to text-to-image diffusion models.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Adding conditional control to text-to-image diffusion models

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-12T10:28:07.690224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7aa28bc7-1e24-4ba0-8f18-eebe3205cfc4 · outbound

This paper cites SSR-Encoder: Encoding selective subject representation for subject-driven generation.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention SSR-Encoder: Encoding selective subject representation for subject-driven generation

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.027108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7baced54-881e-49ff-b4c5-31d629b7dcdb · outbound

This paper cites Pia: Your personalized image animator via plug-and-play modules in text-to-image models.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Pia: Your personalized image animator via plug-and-play modules in text-to-image models

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:08.011126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0fe040ef-7167-49f7-8572-68b89b99dafe · outbound

This paper cites StoryDiffusion: Consistent self-attention for long-range image and video generation.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention StoryDiffusion: Consistent self-attention for long-range image and video generation

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:07.995307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7525eb89-5a21-4d38-9fa4-107b828a168c · outbound

This paper cites StoryMaker: Towards Holistic Consistent Characters in Text-to-image Generation.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention StoryMaker: Towards Holistic Consistent Characters in Text-to-image Generation

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-12T10:28:07.708293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ffd4618-790e-4808-9a76-08dd23462869 · outbound

This paper cites MultiBooth: Towards Generating All Your Concepts in an Image from Text.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention MultiBooth: Towards Generating All Your Concepts in an Image from Text

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-12T10:28:07.713436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c467bf39-ddd1-4c36-ab22-4cb1a6c0a8fd · outbound

This paper cites Moviefactory: Automatic movie creation from text using large generative models for language and images.

Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention Moviefactory: Automatic movie creation from text using large generative models for language and images

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:28:07.979560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

Observation e2f81323-d273-46c3-8e60-651f0e556f76 · inbound

TaleDiffusion: Multi-Character Story Generation with Dialogue Rendering cites this paper.

TaleDiffusion: Multi-Character Story Generation with Dialogue Rendering Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-18T19:02:48.671374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 73519a3b-ca54-42ce-a7e0-83694f02dd09 · inbound

ContextDrag: Precise Drag-Based Image Editing via Context-Preserving Token Injection and Position-Aligned Attention cites this paper.

ContextDrag: Precise Drag-Based Image Editing via Context-Preserving Token Injection and Position-Aligned Attention Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-17T00:08:43.688488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.