REVIEW 6 cited by
Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Adding Object into images based on text instructions is a challenging task in semantic image editing, requiring a balance between preserving the original scene and seamlessly integrating the new object in a fitting location. Despite extensive efforts, existing models often struggle with this balance, particularly with finding a natural location for adding an object in complex scenes. We introduce Add-it, a training-free approach that extends diffusion models' attention mechanisms to incorporate information from three key sources: the scene image, the text prompt, and the generated image itself. Our weighted extended-attention mechanism maintains structural consistency and fine details while ensuring natural object placement. Without task-specific fine-tuning, Add-it achieves state-of-the-art results on both real and generated image insertion benchmarks, including our newly constructed "Additing Affordance Benchmark" for evaluating object placement plausibility, outperforming supervised methods. Human evaluations show that Add-it is preferred in over 80% of cases, and it also demonstrates improvements in various automated metrics.
Forward citations
Cited by 6 Pith papers
-
InsertAnywhere: Geometrically Grounded and Optics-Aware Video Object Insertion
InsertAnywhere inserts a reference object into arbitrary videos by reconstructing 4D geometry to propagate a user-given placement across frames and fine-tuning video diffusion on ROSE++, a removal-to-insertion dataset...
-
FreeCus: Free Lunch Subject-driven Customization in Diffusion Transformers
FreeCus is a training-free method that combines pivotal attention sharing, reversed noise shifting, and MLLM captions to personalize Flux.1 text-to-image generation from a single reference image.
-
Controllable Coupled Image Generation via Diffusion Models
A cross-attention control method that couples backgrounds across multiple generated images by blending LLM-extracted background and entity prompts with a time-varying weight optimized for background similarity and tex...
-
FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation
FlowMo reduces temporal artifacts in video generation by guiding the denoising process to lower the maximum patch-wise variance of consecutive-frame differences in the latent space.
-
LMP: Leveraging Motion Prior in Zero-Shot Video Generation with Diffusion Transformer
LMP transfers motion from a reference video to newly generated videos in text-to-video and image-to-video settings without training, using attention maps in a frozen diffusion transformer.
-
StorySync: Training-Free Subject Consistency in Text-to-Image Generation via Region Harmonization
A training-free inference-time pipeline uses masked cross-image attention sharing and region harmonization to keep subjects consistent across generated story images.
Discussion (0). Continue with ORCID to comment.