lora
ainodes-pyside
lora | ainodes-pyside | |
---|---|---|
83 | 11 | |
6,642 | 92 | |
- | - | |
0.0 | 3.8 | |
about 2 months ago | about 1 year ago | |
Jupyter Notebook | Python | |
Apache License 2.0 | GNU Lesser General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
lora
-
You can now train a 70B language model at home
Diffusion unet has an "extended" version nowadays that applies to the resnet part as well as the cross-attention: https://github.com/cloneofsimo/lora
-
How it feels right now
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.
-
LoRA tuning in julia
No, it's a deep learning thing
-
What does Lora mean?
Low Rank Adaptation of Large Language Models.
-
[D] An ELI5 explanation for LoRA - Low-Rank Adaptation.
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.
-
Combining LoRA, Retro, and Large Language Models for Efficient Knowledge Retrieval and Retention
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.
-
100K Context Windows
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...
-
President Biden meets with AI CEOs at the White House amid ethical criticism
Alpaca was trained for $600 ($100 for the smaller model) and offers outputs competitive with ChatGTP. https://arxiv.org/abs/2106.09685
- LoRA: Low-Rank Adaptation of Large Language Models
- LORA: Low-Rank Adaptation of Large Language Models
ainodes-pyside
-
My pixel art specific AI model just got an upgrade!
really cool model, just tested it with live webcam diffusion. dope. https://github.com/XmYx/ainodes-pyside
- LORA Dreambooth WEB UI - fine-tune Stable diffusion models twice as faster than Dreambooth method, smaller model sizes 3-4 MBs
-
Deforum Stable Diffusion 3d Animation "Failed finding central directory"
You can try using this gui for deforum: https://github.com/XmYx/ainodes-pyside/tree/main
- aiNodes Outpaint Demo
- aiNodes now has VAE, TI, Aesthetic Gradients, and Hypernetworks.
-
InvokeAI 2.2 Release - The Unified Canvas
i have a few ideas, which ive implemented in our desktop app, check its outpaint, the gui is not as neat, but its a desktop app with deforum and hypernetworks, plus video playback on the canvas. https://github.com/XmYx/ainodes-pyside
-
aiNodes - SD 2.0 with 6Gb - canvas optimization - video playback
Preparing for inpaint/outpaint/upscaler based video editing. https://github.com/XmYx/ainodes-pyside https://www.patreon.com/ainodes Thanks to all of you!!
- aiNodes Desktop GUI keeps getting updated - now supports v2, and soon a remote API too.
-
aiNodes alpha update - plugins, and low-mem support
Please find our first update live at https://github.com/XmYx/ainodes-pyside/commit/6739df29c55656b93348bfd254d5187e89b48c8d
-
aiNodes alpha release (no nodes yet)
Thanks for your patience, while our installer is not in a good place (i.e. It doesnt work), the environment is easy enough to create, then the app is fun enough to run that we would like to present you aiNodes 0.1 alpha (nodes disabled for now for stabliity reasons). Please get your copy at: https://github.com/XmYx/ainodes-pyside
What are some alternatives?
stable-diffusion-webui - Stable Diffusion web UI
LoRA - Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
LyCORIS - Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion.
InvokeAI - InvokeAI is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, supports terminal use through a CLI, and serves as the foundation for multiple commercial products.
sd_dreambooth_extension
pytorch-forecasting - Time series forecasting with PyTorch
kohya-trainer - Adapted from https://note.com/kohya_ss/n/nbf7ce8d80f29 for easier cloning
ControlNet - Let us control diffusion models!
Algorithmic-Video-Suggestion-LIB - Algorithmic Video Suggestion LIB is a software tool that suggests videos to users based on their past viewing habits and preferences. It uses advanced technology to analyze the user's viewing data and make smart predictions about what videos they would like to watch next.
sd-webui-additional-networks
airunner - Stable Diffusion and LLMs offline on your own hardware