safetensors
Safe-and-Stable-Ckpt2Safetensors-Conversion-Tool-GUI
safetensors | Safe-and-Stable-Ckpt2Safetensors-Conversion-Tool-GUI | |
---|---|---|
31 | 24 | |
2,472 | 387 | |
4.0% | - | |
8.2 | 0.8 | |
2 days ago | about 1 year ago | |
Python | Python | |
Apache License 2.0 | MIT License |
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.
safetensors
-
Llamafile lets you distribute and run LLMs with a single file
The ML field is doing work in that area: https://github.com/huggingface/safetensors
-
Hugging Face raises $235M from investors including Salesforce and Nvidia
FYI the file format, safetensors, was proposed, developed and maintained by HF, and involved people from groups such as Eleuther and Stability for external security audits.
https://github.com/huggingface/safetensors https://huggingface.co/blog/safetensors-security-audit
-
I Made Stable Diffusion XL Smarter by Finetuning It on Bad AI-Generated Images
Thank you for note on this. I had not heard there were already trojan horse malware being slipped into tensor files as python scripts. Apparently torch pickle uses eval on the tensor file with no filter.
Heard surprisingly little commentary on this topic. The full explanation of how Safetensors are "Safe" can be found from the developer at: https://github.com/huggingface/safetensors/discussions/111
- Pickle safety in Python
-
What makes .safetensors files safe?
Here the developer goes into some detail about what kinds of protections .safetensor files have : https://github.com/huggingface/safetensors/discussions/111
-
Security PSA: huggingface models are code. not just data.
Use the safetensors format, which allows safe persistence and loading of models for common libraries - TensorFlow, PyTorch, JAX, etc. We went through external audits in the last few months (blog post). The current direction will be to have this as the default format.
- What's your favorite model. Right now I'm really enjoying dreamshaper.
- Lora, ggml, safetensors, hf, etc. Is there a glossary and guide on which model to choose?
-
Stability AI Launches the First of Its StableLM Suite of Language Models
I've been diving in lately and while it's not efficient, the only way to do manage is to create a new conda/mamba environment, or a custom Docker image for all the conflicting packages.
For safety and speed, you should prefer the safetensor format: https://huggingface.co/docs/safetensors/speed
If you know what you are doing you can do your own conversions: https://github.com/huggingface/safetensors or for safety, https://huggingface.co/spaces/diffusers/convert
-
CKPT to Safetensors
GitHub - huggingface/safetensors: Simple, safe way to store and distribute tensors
Safe-and-Stable-Ckpt2Safetensors-Conversion-Tool-GUI
- ⚠️WARNING⚠️ never open a .ckpt file without knowing exactly what's inside (especially SDXL)
- I've added Kandinsky 2.1 to my website. It's free and actually fast! (Link in the comments)
- Flexible-Diffusion. My first experiment with finetuning. A broad model with better general aesthetics and coherence for different styles! Scroll for 1.5 vs FlexibleDiffusion grids. (BTW, PublicPrompts.art is back!!!)
-
One way to get ride of the pickles, now and safely
Or just use this. https://github.com/diStyApps/Safe-and-Stable-Ckpt2Safetensors-Conversion-Tool-GUI
-
Can someone ELI5 how to update Automatic1111 to use safetensors for non-developers?
Alternately, this neat little gui can do it too. It does take up an additional gigabyte (due to dependencies), but it's fairly easy to use and can convert back to ckpt if needed.
- Safe & Stable - Ckpt2Safetensors Conversion Tool-GUI v0.1.0: New Update, Now with the Ability to Convert Back to ckpt.
What are some alternatives?
stable-diffusion-webui - Stable Diffusion web UI
Stable-Diffusion-Pickle-Scanner-GUI - Pickle Scanner GUI
llama.cpp - LLM inference in C/C++
Merge-Stable-Diffusion-models-without-distortion-gui - gui for Merge-Stable-Diffusion-models-without-distortion-gui
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-webui-model-converter - model convert extension for stable-diffusion-webui. supports convert fp16/bf16 no-ema/ema-only safetensors
stable-diffusion-webui-model-toolkit - A Multipurpose toolkit for managing, editing and creating models.
EveryDream-trainer - General fine tuning for Stable Diffusion
alpaca_lora_4bit
stable-diffusion-webui-model-toolkit - A Multipurpose toolkit for managing, editing and creating models. [Moved to: https://github.com/arenasys/stable-diffusion-webui-model-toolkit]