-
Notifications
You must be signed in to change notification settings - Fork 6
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
Can you come up with a comfy ui version #14
Comments
+1 |
Hey, @zmwv823 It's great news that we have Ctrl lora nodes and appreciate that here you have compared them with CNs with 1.5 checkpoints. However, you have tested Ctrl lora only with Dreamshaper, why? Is it the only supported model? While you have used different checkpoint with normal CN with 1.5? Can you please do a comparison with same checkpoints so we have a even better idea. Otherwise it just seems normal like sd 1.5 CN. |
At beginning i forget to use the same checkpoint. Below is comparison to all sd1.5 controlnet models stored on my pc. |
How to get ctrlora's nodes |
|
|
ok,fine |
So you're going to publish it? @zmwv823 |
The official gradio interface is always wrong, I wish I could run it on comfy ui! |
The gradio demo can be modified to use comfy checkpoints、controlnet_models and comfyui_controlnet_aux (detection_models) models if u konw some python codes. Emmm, multi conditioning needs a lot modification on now codes, i'll consider publish it if all debug passed. |
ok thanks |
You can ask chatgpt, I always do it @zmwv823 |
Is it a problem with the checkpoints, and why do you come out with a poorly textured image @zmwv823 |
Maybe it's designed for 2 loras or lora_weight is too high or too much loras applied.U can try it by yourself, i opened a custom_node repo for this project: |
Okay, I'll try it. |
Waiting for it, since it's ldm based (it's beyond my knowledge), should be easy to adapt to comfy (ldm based). |
No description provided.
The text was updated successfully, but these errors were encountered: