Instruct pix2pix (controlnet version) works significantly better through X-adapter?

showlab / X-Adapter

[CVPR 2024] X-Adapter: Adding Universal Compatibility of Plugins for Upgraded Diffusion Model

https://showlab.github.io/X-Adapter/

Apache License 2.0

743 stars 44 forks source link

Instruct pix2pix (controlnet version) works significantly better through X-adapter? #4

Open maxpolaczuk opened 11 months ago

maxpolaczuk commented 11 months ago

Incredible work on this research!

I noticed that the Instruct pix2pix (controlnet version) through X-adapters looks like it understood the instruction much better than 1.5 (and produced significantly better image). Is this generally true, or was that a cherry-picked example?

Do you have more examples of Instruct pix2pix comparisons through your adapter vs base 1.5?