Multimodality · 2022
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding (Imagen)
Showed that conditioning an image-diffusion model on a large frozen text encoder yields high-fidelity, well-aligned text-to-image generation, highlighting the text encoder as the key lever.
Editorial record
Plain-language summary
Imagen pairs a frozen T5-XXL language-model text encoder with a cascade of diffusion models and finds that scaling the text encoder improves image-text alignment more than scaling the image model. It reached strong photorealism and prompt fidelity on standard evaluations. It clarified the role of language understanding in text-to-image systems.
Knowledge graph
Relationships
Descendants
Depends onEvidence: Direct
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (T5)
Imagen conditions image diffusion on a frozen T5 text encoder
P-532
Parallel developmentEvidence: Strongly supported
Latent Diffusion (Stable Diffusion) / Diffusion Transformers (DiT)
Imagen and Latent Diffusion are parallel text-to-image diffusion systems
P-532
Source record
Provenance
- Record ID
- P-532
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
- https://arxiv.org/abs/2205.11487
- arXiv:2205.11487
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.