Q: When do we use cond_scale!=1.0 in forward_with_cond_scale()?

lucidrains / DALLE2-pytorch

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

MIT License

11.03k stars 1.07k forks source link

Q: When do we use cond_scale!=1.0 in forward_with_cond_scale()? #36

Closed xiankgx closed 2 years ago

xiankgx commented 2 years ago

When do we use cond_scale!=1.0 in forward_with_cond_scale()?

lucidrains commented 2 years ago

@xiankgx you do it at the last step

images = dalle2(
    ['cute puppy chasing after a squirrel'],
    cond_scale = 2. # classifier free guidance strength (> 1 would strengthen the condition)
)