Imagen: Text-to-Image Diffusion Models

Imagen unprecedented photorealism deep level of language understanding unprecedented photorealism deep level of language understanding Google Research, Brain Team We present Imagen, a text-to-image diffusion model with an unprecedented degree of photorealism and a deep level of language understanding. 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. Imagen achieves a new state-of-the-art FID score of 7.27 on the COCO dataset, without ever training on COCO, and human raters find Imagen samples to be on par with the COCO data itself in image-text alignment. To assess text-to-image models in greater depth, we introduce DrawBench, a comprehensive and challenging benchmark for text-to-image models. 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. Research Paper DrawBench More from the Imagen family: Imagen Video Imagen Editor A brain riding a rocketship heading towards the moon. A brain riding a rocketship heading towards the moon. A dragon fruit wearing karate belt in the snow. A dragon fruit wearing karate belt in the snow. A small cactus wearing a straw hat and neon sunglasses in the Sahara desert. A small cactus wearing a straw hat and neon sunglasses in the Sahara desert. A photo of a Corgi dog riding a bike in Times Square. It is wearing sunglasses and a beach hat. A photo of a Corgi dog riding a bike in Times...