This one is minDALL-E. Earlier I had shown yous cog-view, and dall-e mini.
My prompt: 3 pikachu standng on red blocks lined up on the road under the sun, holding umbrellas, surrounded by electric towers Results: https://ibb.co/xDQT3f6 My prompt: pikachu riding a wave under clouds inside of a large jar on a table Results: https://ibb.co/jHjV7mf Remember, this one was only trained on 14 million text-image pairs. OpenAI's was trained on 250 million. And a good clean dataset of 250 million can feel like 500 million if you form your dataset the right way. So I believe there is a lot of easy room to grow here. ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T4ae89526c13077bd-Mdb1b4cc7ca597caf61676b60 Delivery options: https://agi.topicbox.com/groups/agi/subscription
