Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models

Given a pre-trained text-to-image diffusion model (e.g., Stable Diffusion) our method, Attend-and-Excite, guides the generative model to modify the cross-attention values during the image synthesis process to generate images that more faithfully depict the input text prompt. Stable Diffusion alone (top row) struggles to generate multiple objects (e.g., a horse and a dog). However, by incorporating Attend-and-Excite (bottom row) to strengthen the subject tokens (marked in blue), we achieve images that are more semantically faithful with respect to the input text prompts.

## Acknowledgements This code is builds on the code from the [diffusers](https://github.com/huggingface/diffusers) library as well as the [Prompt-to-Prompt](https://github.com/google/prompt-to-prompt/) codebase.