The Sequence Scope: The Text-to-Image Synthesis Revolution

Weekly newsletter with over 120,000 subscribers that discusses impactful ML research papers, cool tech releases, the money in AI, and real-life implementations.

TheSequence

📝The Editorial: The Text-to-Image Synthesis Revolution

Next week, The Sequence will start a new series about text-to-image synthesis models. In the last year, this deep learning discipline has seen an astonishing level of progress. You probably heard about OpenAI DALL-E 2 but there are plenty of other impressive text-to-image generation models that have been created in the last few months. We have seen Google come up with models like Imagen and Parti, Meta has done amazing work with Make-A-Scene and OpenAI created GLIDE and, of course, DALL-E 2. All these models are pushing the boundaries of text-to-image synthesis in ways that challenge human imagination. However, the innovation is not only coming from the big AI labs but also from startups in the space…