-
-
Notifications
You must be signed in to change notification settings - Fork 114
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Latent mode using 2 Lora -> Image quality error #42
Comments
Hello again. So you're saying that latent lora separation broke. Edit: Is it from before or after we fixed #32? |
#32 |
Alright. Can you try this version and see if it works correctly? |
https://github.com/Symbiomatrix/sd-webui-regional-prompter/tree/Ddim1 https://github.com/hako-mikan/sd-webui-regional-prompter/tree/b772bfec90670030e95df8ebdf509ade927f6ff5 Image quality errors occur in both versions |
Okay, so more likely caused by a webui version change. |
https://postimg.cc/gallery/2DQGVkh |
So if even basic settings aren't doing well, I guess it's something to do with the new lora application method. I can't upgrade to that version for now, perhaps you could try downgrading to the previous version, |
https://github.com/AUTOMATIC1111/stable-diffusion-webui/tree/a0d07fb5807ad55c8ccfdfc9a6d9ae3c62b9d211 |
Can you please add the debug printout for this as well? |
https://github.com/AUTOMATIC1111/stable-diffusion-webui/tree/a0d07fb5807ad55c8ccfdfc9a6d9ae3c62b9d211 |
I think I might finally have a breakthrough. I upgraded to the latest locon extension from my old one (I think it's the 04/03 version, 2e9a79533987e6b454c87705fc4e178febac4fe0), and I'm finally getting garbage, with the same settings. It's possible, seeing as some additional lora functions were overridden and that's pretty much the only difference between our debug printouts. Edit: But it might just be from omitting easynegative. Ugh. You don't happen to be missing that embedding, right? |
@Symbiomatrix |
@hako-mikan Since perfect replication might be impossible (due to various undocumented settings or extension overrides in play), I tried to test a less complex prompt: Observe: Migurdia one side (low weight), looks like a picasso whereas other side is unchanged. Migurdia both sides, completely off. Megumin on standard weight holding up quite well. In fact, even when the region is 1,0 this degradation occurs, so that might be something that can actually be compared on the tensor level. I hadn't thought of that before. EDIT: Correction, thanks to freebag having posted the full page, we do know his previous commit - it was indeed the the latest webui. |
disable test https://github.com/KohakuBlueleaf/a1111-sd-webui-locon/tree/2e9a79533987e6b454c87705fc4e178febac4fe0 |
@freebag668 Do you have any other loras beside migurdia? Do they show the same quality error in regional? |
other lora test 2girls, bento BREAK https://postimg.cc/gallery/VrDBNkm |
@freebag668 Okay, I think the results are at least somewhat similar. It's not as pronounced as migurdia, but definitely has a discernable effect. I wonder if xformers' nondeterminism might be causing slight variations; megumin looks significantly different (but then I'm probably not using the same lora as yours, so that might be the reason). |
https://civitai.com/models/23000 Is there anything else I can test? |
There are certainly cases where the quality is lower, but this has been the case for some time. I was able to reproduce the example I am giving in the ReadMe, but at the same time, applying LoRAs such as megumin produced images with quality issues. |
Are the following issues related to this? |
What happens if you use the settings you're having trouble with and only decreasing strength of LoRA? |
If you just turn off the extension, you can't get such a serious blurred result. If you reduce the weight of both to 0.5, the left side still has a similar bokeh but lighter. I'm going to try an older version of the extension. |
I reverted to the earliest extended version, no any improvement, you can test Latent Couple + Composable Lora. Based on my own testing, I think the problem lies with the checkpoints and the Lora model itself, changing any of them can see a significant improvement. |
https://postimg.cc/gallery/vs6yZq0 |
https://drive.google.com/file/d/1KzkMXpxL_rsBOAuBHyzqd3B7tYpnm1U_/view?usp=share_link https://postimg.cc/LhS1pmxj (2023-04-06) Latent mode is used The latest version displays all photo errors |
What extension is causing so much "up_model" output? I rolled back the extended version many times, until the Latent just added, and none of the similar results can be reproduced. You can go back to the old version through the extended commit history, and then feedback which version can get the effect you expected, otherwise it is difficult to locate the problem. |
That should be regional, on webui 25/3+ version. There's a ton of layers which loras affect. Not sure under which circumstances it's up_model or weight.
We know for certain which webui and regional version he had been using: webui was the latest, the commit is shown at the bottom of this image from the issue. And the extension version was right before and then after the lora fix PR. |
If I knew more about computers I could help, but I'm sorry I can't. |
I switched to the latest WebUI, and then used the same extension version as his (525741c), and got terrible results, and in my case the output was "weight", I believe there are other factors causing the difference. |
I forgotten deleting |
@Sakura-Luna It's an interesting difference, but likely a red herring. I asked freebag to copy his debug printouts earlier in this issue, and he still receives the up_model message along with the degradation. @hako-mikan Question: Would it make sense that running a single lora in base, with base ratio = 1, be different compared to regionless as well? Does the latent method alter the application that much? |
@Symbiomatrix |
@Symbiomatrix |
You mean, that in denoiser_callback only text_cond is flipped back via |
No. |
Ah, okay. I know that part - te_llist & u_llist's additional elements. So that's what it means. |
We can disable this feature. Surprisingly, my sample in README get terrible result. Sorry I'm sleepy(2:00 AM now in japan) |
LoRA settings regarding negative prompts have been added as an option. The default is off; turning it off seems to give better results when using LoRA such as megumin. |
https://postimg.cc/gallery/WjQNN9N disable LoRA in negative textencoder We tested the option with the option on and off https://civitai.com/models/33990 https://civitai.com/models/11866 |
That update was not released to fix your problem. Here is the extension version you used before, you can change the name to |
I got it |
Hello freebag. Sorry I'm late, but #120 should expand sakura's negative parameters to control individual loras, so you can mess around with those once merged. Wrote an explanation about it in known issues. |
https://postimg.cc/H8Wsc8RS
Images you created previously (Latent mode using 2 Lora)
https://postimg.cc/rd26VT0z
PNG INFO -> Send to txt2img
https://postimg.cc/FfzPXnG1
https://postimg.cc/jwrZndtn
Images created with the same setting
The color of the image is outputting strangely
https://postimg.cc/XZx3Lggn
https://postimg.cc/bSymTQ3f
The output of the image is weird even if you use a simple prompt
https://postimg.cc/m110vv0y
Extension Version
b32d8fe (Fri Apr 7 16:05:28 2023)
I format the windows and
I installed a new webui, but it's the same symptom
Is there a solution?
Thank you always for your hard work
The text was updated successfully, but these errors were encountered: