lora
ComfyUI
lora | ComfyUI | |
---|---|---|
83 | 125 | |
6,642 | 33,914 | |
- | - | |
0.0 | 9.9 | |
about 2 months ago | 6 days ago | |
Jupyter Notebook | Python | |
Apache License 2.0 | GNU 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
ComfyUI
-
ComflowySpace: An open-source version of better ComfyUI
The non standard licensing puts me off in contributing or using this. It is frustrating how the phrase opensource has been diluted in the AI/ML community. ComfyUI has a GPL license [1] while this project uses this [2]. I honestly don't know where I stand since this is a legal document using non-standard phrasing to describe how the rights around the source code.
This is a project that uses a custom license with less rights provided than the ComfyUI project it self-describes as improving. Am not sure the title is reflective of the project.
[1] - https://github.com/comfyanonymous/ComfyUI/blob/master/LICENS...
-
Show HN: I made an app to use local AI as daily driver
* LLaVA model: I'll add more documentation. You are right Llava could not generate images. For image generation I don't have immediate plans, but checkout these projects for local image generation.
- https://diffusionbee.com/
- https://github.com/comfyanonymous/ComfyUI
- https://github.com/AUTOMATIC1111/stable-diffusion-webui
-
Show HN: ML Blocks – Deploy multimodal AI workflows without code
Check out ComfyUI for a much more advanced and open source version of this.
https://github.com/comfyanonymous/ComfyUI
-
Stable Code 3B: Coding on the Edge
I use Stable Diffusion family models for innovative art products.
On a small scale, you have to professionalize ComfyUI’s development. My PR to make it installable and to make a plugin ecosystem that makes sense should not be sitting unmerged (https://github.com/comfyanonymous/ComfyUI/pull/298).
On a medium scale, CLIP is holding you back. I would eagerly buy a 48GB card to accommodate a batch size 1, gradient checkpointed LoRA-trainable model with T5 for conditioning. I want PixArt-a or DeepFloyd/IF with the SDXL dataset and training. I get I can achieve so much with SDXL on 24GB, including just barely a fine tuning, I understand the engineering decisions here, but it’s too weak on prompts.
On a large scale, I’m willing to spend a little money up front. In those conditions you can be far more innovative, you don’t have to make everything for $0. Shane Carruth didn’t make Primer for $0. I’m sure you’ve seen this movie, you get how astoundingly good it is. But he still spent something. He spent only slightly more than an RTX 6000 Ada.
Innovators have budgets. It’s still worth releasing the most powerful possible model for expensive hardware, this is why everyone is talking about Mixtral, but it’s especially true of visual art.
-
Show HN: Comflowy – A ComfyUI Tutorial for Beginners
It's litegraph.js [1] and seems to be the only lib they include in /web [2] :
[1] https://github.com/jagenjo/litegraph.js
[2] https://github.com/comfyanonymous/ComfyUI/tree/master/web/li...
-
ComfyUI on Windows 7?
It's possibly you might get a later version of Comfy working, but I had no success with this method and the 1st Sept version of Comfy. The older versions are here under Assets... https://github.com/comfyanonymous/ComfyUI/releases
-
Seeking out an experienced and empathetic coding buddy.
That said, please do learn coding and don't get discouraged when somebody says to learn PyTorch or recommends using a Jupiter notebook with no further information on how to translate the skill into images. I would highly recommend some short term goals. Get your feet wet by taking apart the UIs. The comfy API documentation is here and the A1111 API documentation is here. There is a difference in completeness, welcome to programming. Writing nodes or plugins is also a good way to jump into this world. Custom wildcard logic might be very attractive to you if you aren't the type that want to deal with a nested file structure to simulate logic.
-
Need help installating ComfyUI
For example ComfyUI can simply be downloaded and run using the portable version (https://github.com/comfyanonymous/ComfyUI/releases/download/latest/ComfyUI_windows_portable_nvidia_cu121_or_cpu.7z) if your not comfortable using GIT etc.
-
Installing cumfyui manager on MacBook
https://github.com/comfyanonymous/ComfyUI scroll down to "Install"
- SAG (Self-Attention Guidance) for ComfyUI is here!
What are some alternatives?
stable-diffusion-webui - Stable Diffusion web UI
LyCORIS - Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion.
stable-diffusion-ui - Easiest 1-click way to install and use Stable Diffusion on your computer. Provides a browser UI for generating images from text prompts and images. Just enter your text prompt, and see the generated image. [Moved to: https://github.com/easydiffusion/easydiffusion]
sd_dreambooth_extension
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.
kohya-trainer - Adapted from https://note.com/kohya_ss/n/nbf7ce8d80f29 for easier cloning
sd-webui-controlnet - WebUI extension for ControlNet
ControlNet - Let us control diffusion models!
openOutpaint - local offline javascript and html canvas outpainting gizmo for stable diffusion webUI API 🐠
sd-webui-additional-networks
a1111-nevysha-comfy-ui - A collection of tweak to improve Auto1111 UI//UX [Moved to: https://github.com/Nevysha/Cozy-Nest]