Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding

🤖 Plain-English Summary

We present Imagen, a text-to-image diffusion model with an unprecedented degree of photorealism and a deep level of language understanding. With DrawBench, we compare Imagen with recent methods including VQ-GAN+CLIP, Latent Diffusion Models, and DALL-E 2, and find that human raters prefer Imagen over other models in side-by-side comparisons, both in terms of sample quality and image-text alignment.

🔑 Key Findings

• Imagen builds on the power of large transformer language models in understanding text and hinges on the strength of diffusion models in high-fidelity image generation.
• Our key discovery is that generic large language models (e.g.
• T5), pretrained on text-only corpora, are surprisingly effective at encoding text for image synthesis: increasing the size of the language model in Imagen boosts both sample fidelity and image-text alignment much more than increasing the size of the image diffusion model.

🔗 Related Resources