<ul><li>A study introduces a novel framework called Indirect Prompt Gradient Optimization (IPGO) for prompt-level fine-tuning in Text-to-Image Diffusion models.</li><li>IPGO enhances prompt embeddings by injecting continuously differentiable tokens at the beginning and end of the prompt embeddings, allowing for gradient-based optimization.</li><li>The results show that IPGO consistently outperforms cutting-edge benchmarks in terms of image aesthetics, image-text alignment, and human preferences.</li><li>IPGO is effective in enhancing image generation quality while requiring minimal training data and limited computational resources.</li></ul>

IPGO: Indirect Prompt Gradient Optimization on Text-to-Image Generative Models with High Data Efficiency

Discover more