Flux.1 LoRA Training Tests - Llava Captioning

I finally managed to re-create the issue :) ComfyUI recently changed up to CUDA 12.4 and I think it's llama_index using that old URL. llama-cpp-python doesn't look to be needed anyway, so it will run fine without it. They've also just made a few updates - https://github.com/heshengtao/comfyui_LLM_party/issues/82

Nerdy Rodent

Is this solved? I run into the same problem. Installing llama-cpp-python... Looking in indexes: https://jllllll.github.io/llama-cpp-python-cuBLAS-wheels/AVX2/cu124 ERROR: Could not find a version that satisfies the requirement llama-cpp-python (from versions: none) ERROR: No matching distribution found for llama-cpp-python

Zenith Wu

Yes. Very useful 👍

Guillaume C.

It's Comfyui_yanc - https://github.com/ALatentPlace/ComfyUI_yanc

Nerdy Rodent

Robert CODRON

Before it says "failed to import" the errors will be shown. Something like "can't do this", or "that thing failed" type messages. Another option is to make another comfy environment, install manager, then install llm party

Nerdy Rodent

I have checked the github but nothing there was helpful. No errors, just says “failed to import” Let me get back to the pc and see if there was anything else.

SouthbayJay

Have you checked the github issues? Also, any error messages at startup will provide information as to what's wrong with your environment

Nerdy Rodent

I wish I could use all these workflows with the LLM Part nodes but for the life of me I can't get them to install. It's a huge bummer..

SouthbayJay

May have to wait a while for whatever configuration you have, perhaps, if it's related to this one - https://github.com/abetlen/llama-cpp-python/issues/1682 ?

Nerdy Rodent

Not tried those, nope. Something to look at then - thanks! :)

Nerdy Rodent

Little off topics but have you tried Griptape nodes? They're a great set of custom nodes for working with different tools like LLMs, a little more streamlined for getting image captions IMO and linking multi prompt functions. And they support, OpenAI, Claude, Ollama, Florence2, and OpenAI endpoint style models. Thanks for the workflows, keep up the good work.

Daniel Aleshinloye

I have trouble installing LLM Party, hope someone here happens to know the solution. Installing llama-cpp-python... Looking in indexes: https://jllllll.github.io/llama-cpp-python-cuBLAS-wheels/AVX2/cu124 ERROR: Could not find a version that satisfies the requirement llama-cpp-python (from versions: none) ERROR: No matching distribution found for llama-cpp-python The version seems to only go up to cu122.

Arjan Speelman

I've been pretty impressed with llava captioning so far. 512 tokens, 1000 steps, 8e-5 and it's already got the details!

Nerdy Rodent

I've been playing with use kijai's Florence2 node and using cogflorence 2.1 - large with good results.

Andro.Meta