Closed lllyasviel closed 1 year ago
(2) it seem that the previous "using only mid control for high-res" is broken of deleted?
I believe it was superseded by this PR: https://github.com/Mikubill/sd-webui-controlnet/pull/720
about (1) when global average pooling is True, the controlnet should be only put on the cfg conditional side, otherwise the shuffle wont work very well
This is without cfg-only
Rightnow I have to
so that it works
but this will mess up all other controlnets
so that we should have: when global average pooling is True, the controlnet should be only put on the cfg conditional side
(2) it seem that the previous "using only mid control for high-res" is broken of deleted?
I believe it was superseded by this PR: #720
cool then rightnow what is the best practice for high res. fix?
(6) oneflow needs dependency "pycocotools"
after 5bad033 it still does not work
cool thanks for the invite i will setup a development environment today
after 5bad033 it still does not work
It works for me, don't need to manually invert now. Usually after any extension update you'll need to hard restart the entire web UI to make sure all the modules are reloaded.
after another commit it begin to work now
right now the lineart works very well
ok i think the 2 lineart model and 3 lineart preprocessors are perfect now.
cool the 3 seg preprocessors are perfect
ok two remaining problems (1) the visualization of softedge_pidinet is inverted (2) global average pooling should be linked to cfg conditional side ControlNet
Can the Tile model work correctly now?
no. Tile and Inpainting needs more time. Perhaps I can also work on inpaint
Point (2) was addressed in a comment in the PR, I can agree with you it should probably be enabled automatically: https://github.com/Mikubill/sd-webui-controlnet/pull/742#issuecomment-1509875513
shuffle
requiresEnable CFG-Based guidance
to be enabled (in settings) for better result.
Can the Tile model work correctly now?
See above PR comment. Inpaint and Tile are not yet supported.
openpose is perfect
congratulations
no. Tile and Inpainting needs more time. Perhaps I can also work on inpaint
please let me know when inpaint is ready. my sam extension will connect to your inpaint. before that I'll try to connect to your semantic segmentation
normalbae is perfect
congratulations
Yes I also want to the Tile model for upscaling. I got everything ready for draw / redraw images tile by tile, and the only thing need is a model trained on tiles.
Great jobs!
hello where is the codes for preprocessor alias? I cannot find it
It would be great if a "force unload all controlNet preprocessors/models from VRAM" button exist.
It would be great if a "force unload all controlNet preprocessors/models from VRAM" button exist.
I don't know, but I provide a Free GPU button in my extension. You may try use that button to see if it can unload controlnet stuffs?
I don't know, but I provide a Free GPU button in my extension. You may try use that button to see if it can unload controlnet stuffs?
It unload... but only little amount. (preprocessor) test method:
update: guess mode rewritten, avg pool rewritten these are much more correct than before shuffle seed fixed now shuffle does not need more configs
update: guess mode rewritten, avg pool rewritten these are much more correct than before shuffle seed fixed now shuffle does not need more configs
Now you want me to change the branch to yours?
shuffle + canny iron man, high-quality, extremely detailed Negative prompt: long body, low resolution, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 12345, Size: 512x768, Model hash: e1441589a6, Model: v1-5-pruned, ControlNet-0 Enabled: True, ControlNet-0 Module: none, ControlNet-0 Model: control_v11e_sd15_shuffle [526bfdae], ControlNet-0 Weight: 1, ControlNet-0 Guidance Start: 0, ControlNet-0 Guidance End: 1, ControlNet-1 Enabled: True, ControlNet-1 Module: canny, ControlNet-1 Model: control_v11p_sd15_canny [d14c016b], ControlNet-1 Weight: 1, ControlNet-1 Guidance Start: 0, ControlNet-1 Guidance End: 1
canny
shuffle
result
this should be the first really useable style transfer
update: guess mode rewritten, avg pool rewritten these are much more correct than before shuffle seed fixed now shuffle does not need more configs
Now you want me to change the branch to yours?
you have a working branch?
update: guess mode rewritten, avg pool rewritten these are much more correct than before shuffle seed fixed now shuffle does not need more configs
Now you want me to change the branch to yours?
you have a working branch?
Now I'm on the ctrlnet 1.1 branch
soem other attempts
the style
iron man, high-quality, extremely detailed
Negative prompt: long body, low resolution, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality
Steps: 50, Sampler: Euler a, CFG scale: 7, Seed: 12345, Size: 512x768, Model hash: e1441589a6, Model: v1-5-pruned, ControlNet-0 Enabled: True, ControlNet-0 Module: shuffle, ControlNet-0 Model: control_v11e_sd15_shuffle [526bfdae], ControlNet-0 Weight: 1, ControlNet-0 Guidance Start: 0, ControlNet-0 Guidance End: 1, ControlNet-1 Enabled: True, ControlNet-1 Module: canny, ControlNet-1 Model: control_v11p_sd15_canny [d14c016b], ControlNet-1 Weight: 1, ControlNet-1 Guidance Start: 0, ControlNet-1 Guidance End: 1
update: guess mode rewritten, avg pool rewritten these are much more correct than before shuffle seed fixed now shuffle does not need more configs
Now you want me to change the branch to yours?
you have a working branch?
Now I'm on the ctrlnet 1.1 branch
it is ok. u may take a look at my implementation and see if you want to fix any bug
oh my god this style transfer is really killing
@Mikubill I do not know how clip vision works. it seems already broken before my first commit. help needed
Amazing work.
I’m also working for some new ideas in v2v and it seems to be good. Let’s change the game :)
I do not know how clip vision works. it seems already broken before my first commit. help needed
Can you make a manga model? I have a problem with the screenton, when inverted (or high sensitivity of the anotator) it causes inode artifacts
Sorry for the crooked table (I haven't figured out the markdown yet)
![]() |
![]() |
|||
![]() |
![]() |
![]() |
||
![]() |
![]() |
I do not know how clip vision works. it seems already broken before my first commit. help needed
Can you make a manga model? I have a problem with the screenton, when inverted (or high sensitivity of the anotator) it causes inode artifacts
what is it?
I do not know how clip vision works. it seems already broken before my first commit. help needed
Can you make a manga model? I have a problem with the screenton, when inverted (or high sensitivity of the anotator) it causes inode artifacts
what is it?
On the 6th photo, the original is taken from the manga. At 4,5,7 the results of the anotator's work. The fact is that he is extremely bad at translating the manga screenton into the line version. 1,2,3 photos show the results of "coloring"
update:
clip vision fixed
Hi everyone! I'm getting an unexpected keys error when trying to use fp16 v1.1 models. The full version works fine. How can I fix that?
Error after the update, can anyone help?
update and restart everything completely
I updated and completely rebooted everything, it didn't work, annotator works, generation doesn't work
can you see "cdcfa706"?
yes
then close the console and browser completely and the restart and it should work
Finally, a strange mistake hmm, thank you!
Ironically, the 3rd point is the first to be added, with this shuffle model, while no native batch was implemented whatsoever. Happy and sad face.jpg
soem other attempts ... iron man, high-quality, extremely detailed Negative prompt: long body, low resolution, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality Steps: 50, Sampler: Euler a, CFG scale: 7, Seed: 12345, Size: 512x768, Model hash: e1441589a6, Model: v1-5-pruned, ControlNet-0 Enabled: True, ControlNet-0 Module: shuffle, ControlNet-0 Model: control_v11e_sd15_shuffle [526bfdae], ControlNet-0 Weight: 1, ControlNet-0 Guidance Start: 0, ControlNet-0 Guidance End: 1, ControlNet-1 Enabled: True, ControlNet-1 Module: canny, ControlNet-1 Model: control_v11p_sd15_canny [d14c016b], ControlNet-1 Weight: 1, ControlNet-1 Guidance Start: 0, ControlNet-1 Guidance End: 1
Using your settings, I'm not getting similar images with Shuffle, the background is always a swirly mess. Or when using Shuffle by itself, I see that the output directly matches the flow that the annotator preview show.
@throttlekitty make sure that your yaml file names and model file names are same
That set me in the right direction, thanks. The extension places yaml files in its own models folder, but reads from webui\models\controlnet. I needed to have the yaml files in the same folder. It could also be that my webui\models\ is a symlink from another drive?
We will use this repo to track some discussions for updating to ControlNet 1.1.