Hierarchical Text-Conditional Image Generation with CLIP Latents
This work addresses the challenge of text-to-image generation for AI and creative applications, offering a novel approach that enhances diversity and control, though it builds incrementally on existing CLIP and diffusion model techniques.
The authors tackled the problem of generating diverse and photorealistic images from text by leveraging CLIP's image embeddings, achieving improved image diversity with minimal loss in photorealism and caption similarity. They demonstrated that their method enables zero-shot language-guided image manipulations and produces high-quality samples efficiently using diffusion models.
Contrastive models like CLIP have been shown to learn robust representations of images that capture both semantics and style. To leverage these representations for image generation, we propose a two-stage model: a prior that generates a CLIP image embedding given a text caption, and a decoder that generates an image conditioned on the image embedding. We show that explicitly generating image representations improves image diversity with minimal loss in photorealism and caption similarity. Our decoders conditioned on image representations can also produce variations of an image that preserve both its semantics and style, while varying the non-essential details absent from the image representation. Moreover, the joint embedding space of CLIP enables language-guided image manipulations in a zero-shot fashion. We use diffusion models for the decoder and experiment with both autoregressive and diffusion models for the prior, finding that the latter are computationally more efficient and produce higher-quality samples.