Open daffatahtaa opened 6 months ago
additional screenshot
sorry for the delay; i see in your first screenshot that you've got a 384x pixel size for your reticle, and pretty much every sd1.5 model unfortunately collapses at resolutions that small... other than that, are you using an inpainting or traditional model? your first screenshot shows at least a level of coherence/blending in the top-left outpaint even if the subject matter is way off, so it seems to be at least "working" in the sense that webUI API is receiving the input image and expected parameters...
What happened?
the image generated won't outpaint
Steps to reproduce the problem
What should have happened?
the image generated on stop 4 should outpaint and match the image generated
Commit where the problem happens
latest
What platforms do you use to access openOutpaint?
Windows
What browsers do you use to access the UI ?
Microsoft Edge
Browser Extensions/Addons
AUTOMATIC1111 webUI Commandline Arguments
--xformers --skip-torch-cuda-test --no-half-vae --api
Additional information
No response