Pith. sign in

REVIEW 2 cited by

FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition

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

arxiv 2405.13870 v1 pith:E4NIZA54 submitted 2024-05-22 cs.CV

classification cs.CV
keywords conceptsimagesimagecompositioncustomizationcustomizedfreecustominput
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Benefiting from large-scale pre-trained text-to-image (T2I) generative models, impressive progress has been achieved in customized image generation, which aims to generate user-specified concepts. Existing approaches have extensively focused on single-concept customization and still encounter challenges when it comes to complex scenarios that involve combining multiple concepts. These approaches often require retraining/fine-tuning using a few images, leading to time-consuming training processes and impeding their swift implementation. Furthermore, the reliance on multiple images to represent a singular concept increases the difficulty of customization. To this end, we propose FreeCustom, a novel tuning-free method to generate customized images of multi-concept composition based on reference concepts, using only one image per concept as input. Specifically, we introduce a new multi-reference self-attention (MRSA) mechanism and a weighted mask strategy that enables the generated image to access and focus more on the reference concepts. In addition, MRSA leverages our key finding that input concepts are better preserved when providing images with context interactions. Experiments show that our method's produced images are consistent with the given concepts and better aligned with the input text. Our method outperforms or performs on par with other training-based methods in terms of multi-concept composition and single-concept customization, but is simpler. Codes can be found at https://github.com/aim-uofa/FreeCustom.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Interact-Custom: Customized Human Object Interaction Image Generation

    cs.CV 2025-08 conditional novelty 6.0 of 10

    Interact-Custom generates customized human-object interaction images by first generating a foreground mask from the prompt and then using that mask to guide identity-preserving diffusion generation.

  2. Learning Zero-Shot Subject-Driven Video Generation Using 1% Compute

    cs.CV 2025-04 unverdicted novelty 6.0 of 10

    A zero-shot subject-driven video generation framework that decomposes the task into identity injection from 200K subject-image pairs and motion preservation from 4K arbitrary videos, trained in 288 A100 GPU hours on C...

Pith tools