StAlKeR7779
StAlKeR7779
Note: this branch based on #3548, not on main While find out what needs to be done to implement onnx, found that I can do draft of it pretty quickly,...
Just draft with thoughts. Remove angle brackets from variables as this is format for prompt, not trigger itself(IMHO). Remove angle brackets from frontend list, so now you can navigate TI...
Delete `--karras-max` argument as it's no longer used. Mark regex strings, as without it there special characters may interfere. Fix - in some places there tuples instead of values itself....
Rewrite lora to be applied by model patching as it gives us benefits: 1) On model execution calculates result only on model weight, while with hooks we need to calculate...
## Summary Current attention processor implements only `torch-sdp` attention type, so when any ip-adapter or regional prompt used, we override model to run `torch-sdp` attention. New attention processor combines 4...
## Summary Initial implementation of overrides in modular backend, should be used in inpaint and tiled extensions(also in preview extension after preview event rewrite). Created PR now just to have...
## Summary Rewriting of generation backend. At this moment backend rewritten to new architecture, but from user perspective nothing should change as backend converts arguments silently. Later in major update...
## Summary Changes preview event the way, that it accepts image instead of latents. This allow to use custom latents preview logic, for example - flux or use taesd for...