ainodes-engine VS lora

currently working on a pyqt node based app, qt has a lot of 3d power. XmYx/ainodes-engine (github.com)

1: git clone -b comfy-dev https://github.com/XmYx/ainodes-engine 2: cd ainodes-engine 3: setup_ainodes.bat then you can start ainodes the usual way, but also ComfyUI with run_comfyui.bat. If you install any custom node package for comfy using the comfy manager, those get imported into the desktop engine on next start. Compatibility is WIP, but most image and sampling nodes will work. (Disco Diffusion too) To install the Comfy Manager run the following from ainodes-engine folder: 1: cd src 2: cd ComfyUI 3: cd custom_nodes 4: git clone https://github.com/ltdrdata/ComfyUI-Manager.git

XmYx/ainodes-engine (github.com) patreon.com/deforum_ainodes

And take a look at the node engine if you are interested: https://github.com/XmYx/ainodes-engine

You can see some of our previous open source works at: XmYx/ainodes-engine (github.com)

Diffusion unet has an "extended" version nowadays that applies to the resnet part as well as the cross-attention: https://github.com/cloneofsimo/lora

Absolutely. But that doesn't matter because you only have to train it at scale, once. There are papers released already that show it's possible to update weights in small sections. You won't have to wait for the next monolithic LLM to drop to get up to date information. It will start to learn in bits and pieces.

No, it's a deep learning thing

Low Rank Adaptation of Large Language Models.

Recently, I have seen the LoRA technique (Low-Rank Adaptation of Large Language Models) as a popular method for fine-tuning LLMs and other models.

Enter LoRA, a method proposed for adapting pre-trained models to specific tasks[2]. By freezing pre-trained model weights and injecting trainable rank decomposition matrices into the transformer architecture, LoRA can reduce the number of trainable parameters and the GPU memory requirement, making the adaptation of LLMs for downstream tasks more feasible.

Open-source LLM projects have largely solved this using Low-Rank Adaptation of Large Language Models (LoRA): https://arxiv.org/abs/2106.09685

Apparently an RTX 4090 running overnight is sufficient to produce a fine-tuned model that can spit out new Harry Potter stories, or whatever...

Alpaca was trained for $600 ($100 for the smaller model) and offers outputs competitive with ChatGTP. https://arxiv.org/abs/2106.09685