Closed blueraincoatli closed 2 months ago
Yes for images you need a multi-modal model LlaMA3 is just for text here is a link for a LLaVa1.6 ollama run llava:7b-v1.6-mistral-q5_0
you can also see all the available models here on this list the bigger they are the better quality you get but also take more resources like vram etc.. https://ollama.com/library/llava if you click on the latest dropdown you can check them up
It works after I get the llava switch the model in the IF-AI node, thank you very much!
Thank you, I will close the issue then
After running the command "ollama run llava" the model is automatically downloaded to the C drive, do I need to move the model to a certain folder, my node does not recognize the model! thanks
no if ollama is running it should see the model if you open your terminal and type ollama list
and llava is listed it should be also in comfy is the same command. so if llama service is running comfy should see it
no if ollama is running it should see the model if you open your terminal and type
ollama list
and llava is listed it should be also in comfy is the same command. so if llama service is running comfy should see it
thanks,I'm going to reinstall 0.1.25, I had the latest version installed previously
No the very last version works fine I have been using it they fix that issue
No the very last version works fine I have been using it they fix that issue
Sorry to interrupt again, I reinstalled 0.1.25 and still can't load ollama's model, and the reply given by claude3 doesn't seem to help!
if you are in the same computer try writing 127.0.0.1 as base ip instead of localhost could you give it a try please
in your username in your computer locate that file open it see any message with source=routes to check if that is your base_ip
if you are in the same computer try writing 127.0.0.1 as base ip instead of localhost could you give it a try please
its worked for me, thanks so much, I found this file and it's exactly what you said
nice thanks, glad it works now
I load a image to IF chat prompt image input, and ask for describing the picture, but the response is not correct,, it seems that the node does't get the image.![微信截图_20240424200216](https://github.com/if-ai/ComfyUI-IF_AI_tools/assets/142435478/95c26444-78cf-48a2-829c-223f0fa3d71e)