Use an AI to generate prompts and ComfUI to generate the images. Connect Ollama (as AI) to ComfUI.

There are two workflows:

Ollama-Promt_Load_Ckpt this version uses a Ckpt - Loader.

Ollama-Promt_UNet+GGUF this version can switch between GGUF and UNet Loader.

--> Start the Ollama program before you start the workflow.

----> How to Ollama <----

here you get Ollama : https://ollama.com/

install OllamaSetup.exe

Move Ollama Models to a diffrent device.

OllamaSetup.exe /DIR=D:\ollama_Models

run in terminal

Open Environment Variables:

Press Win + X and select System.

In the System window, click on Advanced system settings on the left sidebar.

In the System Properties window, click on the Environment Variables... button.

Create a New Environment Variable:

In the Environment Variables window, look for the System variables section and click on New....

Enter OLLAMA_MODELS for the Variable name.

Enter the path where you want to save the model files for the Variable value (e.g., D:\OllamaModels).

Click OK to save the new environment variable.

Restart Ollama:

Quit Ollama if it's running.

Restart Ollama to ensure it recognizes the new environment variable.

Verify the New Location:

Download a new model and check if it is saved in the new directory (e.g., D:\OllamaModels\models\blobs).

run in terminal!

Model i used:

ollama run command-r

https://ollama.com/library/command-r

ollama run dolphin-mixtral

https://ollama.com/library/dolphin-mixtral

ollama run dolphin-mistral

https://ollama.com/library/dolphin-mistral

ollama run llama3.2-vision

https://ollama.com/library/llama3.2-vision

mistral-nemo

https://ollama.com/library/mistral-nemo

run in terminal

------> Remove Models from Ollama <-------

ollama rm (model_name)

run in terminal