REVIEW 4 cited by
Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation
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
Signed reviews
read the original abstract
Prompt engineering is an effective but labor-intensive way to control text-to-image (T2I) generative models. Its time-intensive nature and complexity have spurred the development of algorithms for automated prompt generation. However, these methods often struggle with transferability across T2I models, require white-box access to the underlying model, or produce non-intuitive prompts. In this work, we introduce PRISM, an algorithm that automatically produces human-interpretable and transferable prompts that can effectively generate desired concepts given only black-box access to T2I models. Inspired by large language model (LLM) jailbreaking, PRISM leverages the in-context learning ability of LLMs to iteratively refine the candidate prompt distribution built upon the reference images. Our experiments demonstrate the versatility and effectiveness of PRISM in generating accurate prompts for objects, styles, and images across multiple T2I models, including Stable Diffusion, DALL-E, and Midjourney.
Forward citations
Cited by 4 Pith papers
-
Beyond Trial-and-Error: Agentic Optimization for Image-to-Video Adherence
An agentic two-stage optimizer (LLM-generated question scoring plus Bayesian hyperparameter search) improves image-to-video prompt adherence, winning human preference tests up to 69% over random search.
-
Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models
Implicit generative choices in diffusion models for ambiguous prompts are localized principally in self-attention layers, enabling a targeted ICM steering method that outperforms prior debiasing approaches.
-
AdaptaGen: Domain-Specific Image Generation through Hierarchical Semantic Optimization Framework
A three-stage pipeline of prompt optimization, LoRA adaptation, and T5 caption transformation is claimed to improve few-shot domain-specific image generation, with reported FID and CLIP gains over two baselines.
-
Antelope: Potent and Concealed Jailbreak Attack Strategy
Antelope finds short, inconspicuous suffix tokens by aligning prompt embeddings with reference image embeddings, achieving higher ASR than prior jailbreak attacks on Stable Diffusion and several defenses.
Discussion (0). Continue with ORCID to comment.