#i got it going . i need a model now?

4 messages · Page 1 of 1 (latest)

amber nebula
#

i got it going . i need a model now? where do I get those?

sly prawnBOT
#

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

#

Yes, to generate images with InvokeAI, you will need to use a model. Models are the output of training a machine on understanding massive amounts of images, providing them with the capability to generate new images using just a text description of what you’d like to see.

There are various models available in Invoke AI, each with its strengths and unique capabilities. Some models are generalists, trained on a wide range of data, making them flexible and useful for a broad range of prompts. Other models are specialists, trained on a set of specific data, and they excel at generating images related to those topics.

You can download and manage models in two ways:

  1. Using the invokeai-model-install script which will download and install them for you. This script supports main models, ControlNet, LoRA, and Textual Inversion models.
# (install the model at the indicated URL)
invokeai-model-install --add <https://civitai.com/api/download/models/128713>
  1. Using the web interface (WebUI) which has a GUI for importing and managing models. You can open the InvokeAI Model Manager and navigate to Import Models. In the field labeled Location, type in the path to the model you wish to install. You may use a URL, HuggingFace repo id, or a path on your local disk.

InvokeAI comes with support for a good set of starter models. You'll find them listed in the master models file configs/INITIAL_MODELS.yaml in the InvokeAI root directory. The subset that is currently installed is found in configs/models.yaml.

You can also find more models online, including at <https://models.invoke.ai.>

Remember to familiarize yourself with the model terms by visiting the URLs in the table above. Some of these models carry additional license terms that limit their use in commercial applications or on public servers.