runwayml / stable-diffusion

Latent Text-to-Image Diffusion

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Different from RUNWAY

jjl001 opened this issue · comments

Thanks for the contribution of the author.

When I use the same image and mask at runway and this project respectively, I got very different results.
prompt:
Face of a yellow cat, high resolution, sitting on a park bench
image:
desk
mask
desk_mask
Results of runway:
desk_runway
Results of github:
desk_github
It seem like prompt does not work.

I tested another example and got similar results.
prompt:
Face of a yellow cat, high resolution, sitting on a park bench
Image:
dog
mask:
dog_v2
Result:
00008

What should I do to make prompt work?