#Model runs in Comfy but not in Invoke.

3 messages · Page 1 of 1 (latest)

hearty ermine
#

I'm trying to run this 2.x model but am getting floral patterns like the image attached. I was told I'm probably getting something in the config wrong so I've also attached the model config page and my prompt settings for good measure. The .yaml config file is attached but I was told to mark it as v-prediction but can't see that in the settings. Help would be amazing, thanks.

hard flickerBOT
#

Hi @hearty ermine. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

#

Hmm, I don't know enough to give you a confident answer yet. The information extracts provided do not contain specific details about the issue you're facing with the 2.x model or the floral patterns you're getting. They also do not include the attached image, model config page, prompt settings, or the .yaml config file you mentioned.

However, I can suggest that you ensure you're using the correct settings for your model in Invoke AI. Different models may require different configurations and may produce different results based on the images and content they're trained on, as mentioned in the Getting Started with Invoke (https://support.invoke.ai/support/solutions/articles/151000096602-getting-started-with-invoke) guide.

If you're still having trouble, it would be best to reach out to the Invoke AI support team. You can email them at [email protected] (https://support.invoke.ai/cdn-cgi/l/email-protection#25565055554a5751654c4b534a4e400b444c) or open a ticket in their help desk as mentioned in the Invoke AI support guide (https://support.invoke.ai/support/solutions/articles/151000096654-i-m-experiencing-technical-issues-with-the-platform-how-can-i-contact-support-for-help-). Be sure to provide a clear description of the issue you're facing, any error messages you've encountered, and any relevant screenshots to help them resolve your issue as quickly as possible.

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon: