#Am i using InvokeAI wrong?

18 messages · Page 1 of 1 (latest)

sacred bane
#

Hello, iam new on this ai generation stuff. currently i am following tutorial how to install it properly and install model that i want, i get it from civit.ai. but i didnt get the result like i want. i just changed model and prompts and try another scheduler. i kept getting bad images.

https://civitai.com/images/5452676 << model links

red talonBOT
#

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

#

It's great that you're exploring AI generation with InvokeAI. However, if you're not getting the results you want, there could be a few reasons for this.

Firstly, it's important to note that InvokeAI offers a significant amount of flexibility in the generative AI processing, and some settings can cause image qualities that aren’t quite what humans would expect. The AI is powerful, but ultimately relies on us for taste! So, it's possible that the settings you're using are not optimal for the results you want.

If you're using a model from Civit.ai, make sure you're downloading and installing it correctly. According to the documentation (https://invoke-ai.github.io/InvokeAI/installation/050_INSTALLING_MODELS/#installation), you can install models using the invokeai-model-install script or through the web interface (WebUI). If you're using the script, you can run invokeai-model-install --add **model URL] to add the model. However, note that Civit.ai seems to have changed their URLs a bit, so you might need to right click on "Download" to "copy link address" to get a working download link, as mentioned in this [GitHub issue** (https://github.com/invoke-ai/InvokeAI/issues/4152).

If you're still having issues, it might be helpful to reach out to the InvokeAI support team. You can email them at email protected], open a ticket in their help desk, or contact your dedicated account manager if you're an Enterprise Customer. 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 ([source (https://support.invoke.ai/support/solutions/articles/151000096654-i-m-experiencing-technical-issues-with-the-platform-how-can-i-contact-support-for-help-)).

#

@sacred bane kapa.ai is still learning and improving, please let us know how it did by reacting below

reef knoll
#

Looking at your settings, you're using an XL model at a resolution that's too small

#

You need to generate at 1024x1024 for XL models

sacred bane
#

my pc specs :
ryzen 5 5600x
rtx 4060 8gb
ram 32gb

reef knoll
#

you also probably want to switch to the euler scheduler.

sacred bane
#

i see, let me try

sacred bane
reef knoll
#

yeah

#

for the most part.

sacred bane
#

do i have to use nodes to generate good images ?

#

or i can just play the prompts

reef knoll
#

you can just play the prompts.

#

(it does all the nodes for you)

sacred bane
#

thanks for the advices, it helps a lot.