stable-diffusion-webui-forge
stable-diffusion-webui-forge copied to clipboard
[Feature Request]: Restore Multi-inputs for Instant-LoRA workflows
Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits
What would your feature do ?
From Discussions
Multi-inputs is removed. You now need to enable multiple IP-Adapter units to achieve effect of previous multi-inputs We will add this back if there is a strong demand on that.
Yes, please! I was so stoked to see it added, and bummed to see it's now gone again. It's super important for IP Adapter "Instant LoRA" type workflows, and a whole lot faster than adding 2-4 different duplicate ControlNets to do the same thing.
Proposed workflow
Restore the "Multi-Inputs" functionality.
Additional information
No response
Is there any method to manually re-activate it?
No, it was removed. You'd have to look at the multi-input commits from the previous extension, and then rework the code to this codebase. The workaround for now is to make multiple controlnets, and put one image in each. It's just rather slow and cumbersome by comparison, setting up 2 or 3 or 4 duplicate controlnets.
Since @huchenlei has self-assigned this, fingers crossed he's on it. 🎉👍 (thanks!)