afiaka87 / laionide-v4

GLIDE-text2im w/ humans and experimental style prompts.

Demo API Examples Versions (b21cbe27)

Examples

View more examples

Run time and cost

Predictions run on Nvidia T4 GPU hardware. Predictions typically complete within 95 seconds. The predict time for this model varies significantly based on the inputs.

Laionide (version 4)

(v3) - Direct comparison to OpenAI’s model using COCO captions

Note - this checkpoint was an experiment in adding “dataset tags” with classifier free guidance in finetuning. Unfortunately, some of the outputs’ quality is inferior to Laionide-v3. You may have better luck when using laionide-v3

Shout out to stability.ai for donating the compute to laion needed for this to be possible.