zlacker

[parent] [thread] 2 comments
1. GaggiX+(OP)[view] [source] 2022-05-24 00:29:55
Imagen takes text embeddings, OpenAI model takes image embeddings instead, this is the reason. There are other models that can generate text: latent diffusion trained on LAION-400M, GLIDE, DALL-E (1).
replies(1): >>ALittl+6b
2. ALittl+6b[view] [source] 2022-05-24 02:10:24
>>GaggiX+(OP)
My understanding of the terms text and image embeddings is that they are ways of representing text or images as vectors. But, I don't understand how that would help with the process of actually drawing the symbols for those letters.
replies(1): >>GaggiX+Az
◧◩
3. GaggiX+Az[view] [source] [discussion] 2022-05-24 06:45:09
>>ALittl+6b
If the model takes text embeddings/tokens as an input, it can create a connection between the caption and the text on the image (sometimes they are really similar).
[go to top]