Pith. sign in

REVIEW 4 cited by

Encoder-based Domain Tuning for Fast Personalization of Text-to-Image 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

arxiv 2302.12228 v3 pith:LPCTXIIH submitted 2023-02-23 cs.CV cs.GRcs.LG

classification cs.CVcs.GRcs.LG
keywords conceptsdomainmodelpersonalizationtext-to-imagecomponentsconceptencoder-based
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Text-to-image personalization aims to teach a pre-trained diffusion model to reason about novel, user provided concepts, embedding them into new scenes guided by natural language prompts. However, current personalization approaches struggle with lengthy training times, high storage requirements or loss of identity. To overcome these limitations, we propose an encoder-based domain-tuning approach. Our key insight is that by underfitting on a large set of concepts from a given domain, we can improve generalization and create a model that is more amenable to quickly adding novel concepts from the same domain. Specifically, we employ two components: First, an encoder that takes as an input a single image of a target concept from a given domain, e.g. a specific face, and learns to map it into a word-embedding representing the concept. Second, a set of regularized weight-offsets for the text-to-image model that learn how to effectively ingest additional concepts. Together, these components are used to guide the learning of unseen concepts, allowing us to personalize a model using only a single image and as few as 5 training steps - accelerating personalization from dozens of minutes to seconds, while preserving quality.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning

    cs.CV 2023-07 unverdicted novelty 7.0 of 10

    A single motion module trained on videos adds temporally coherent animation to any personalized text-to-image model derived from the same base without additional tuning.

  2. Adversarial Concept Distillation for One-Step Diffusion Personalization

    cs.CV 2025-10 unverdicted novelty 6.0 of 10

    OPAD enables reliable high-quality personalization of one-step diffusion models via multi-step teacher distillation combined with adversarial alignment losses.

  3. InstantID: Zero-shot Identity-Preserving Generation in Seconds

    cs.CV 2024-01 unverdicted novelty 6.0 of 10

    InstantID enables zero-shot identity-preserving image generation from one facial image via a novel IdentityNet that combines strong semantic and weak spatial conditioning with text prompts in diffusion models.

  4. StorySync: Training-Free Subject Consistency in Text-to-Image Generation via Region Harmonization

    cs.CV 2025-07 unverdicted novelty 5.0 of 10

    A training-free inference-time pipeline uses masked cross-image attention sharing and region harmonization to keep subjects consistent across generated story images.

Pith tools