zlacker

[return to "Imagen, a text-to-image diffusion model"]
◧
1. tomato+Ga[view] [source] 2022-05-23 21:51:10
>>kevema+(OP)
when will there be a "DALL-E for porn" ? or is this domain also claimed by Puritans and morality gate keepers? The most in demand text-to-image is use case is for porn.
◧◩
2. astran+AE[view] [source] 2022-05-24 01:41:15
>>tomato+Ga
Train it yourself. Danbooru is a publicly available explicit dataset.
◧◩◪
3. tomato+fG[view] [source] 2022-05-24 01:54:58
>>astran+AE
This is not something you can train on a regular AWS gpu-instance without racking up millions of dollars in bills to my knowledge. Dataset isn't an issue its a capex issue.
[go to top]