sd-gui
fastsdcpu
| sd-gui | fastsdcpu | |
|---|---|---|
| 8 | 6 | |
| 229 | 905 | |
| - | - | |
| 0.0 | 9.5 | |
| over 1 year ago | 9 days ago | |
| Python | Python | |
| MIT License | 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.
sd-gui
- I have a problem — I keep making new GUIs for Stable Diffusion 😛
-
Stable Diffusion GUIs for Apple Silicon
My own GUI: I wrote multiple versions of this GUI and it works on not just macOS but under Linux and Windows too. Again, this requires installing Python and setting up dependencies. There’s a detailed doc with instructions on the GitHub repo I linked to, but might not be your cup of tea/coffee 😛
-
Stable Diffusion GUI for Apple Silicon
% git clone https://github.com/FahimF/sd-gui.git Cloning into 'sd-gui'... remote: Enumerating objects: 45, done. remote: Counting objects: 100% (45/45), done. remote: Compressing objects: 100% (29/29), done. remote: Total 45 (delta 22), reused 36 (delta 13), pack-reused 0 Unpacking objects: 100% (45/45), done.
fastsdcpu
-
FastSD CPU beta 21 - SDXL Turbo OpenVINO support (2.5 seconds on CPU)
Release : https://github.com/rupeshs/fastsdcpu/releases/tag/v1.0.0-beta.21
-
Krita AI Diffusion
Too bad I don't have the Hardware to run it. Anyone had success with stable diffusion on Steam Deck ? The only thing that works for me is https://github.com/rupeshs/fastsdcpu , but it takes 1m per 512x512 image and is LCM
-
$95 AMD CPU Becomes 16GB GPU to Run AI Software
> one minute and 50 seconds to generate a 512 x 512-pixel image with the default setting of 50 steps
A little over 2s/iter? That is... Not great.
It is slower than CPU diffusion: https://github.com/rupeshs/fastsdcpu
Stable Diffusion in particular doesn't need much VRAM anyway. I get that many people are stuck on lower end computers, but ~4GB is not an unreasonable requirement.
- FLaNK Stack Weekly for 30 Oct 2023
- Generate images in one second on your Mac using a latent consistency model
- rupeshs/fastsdcpu: Fast stable diffusion CPU
What are some alternatives?
Real-ESRGAN - Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
Deep-Learning-Ultra - Open source Deep Learning Containers (DLCs) are a set of Docker images for training and serving models in PyTorch, OpenCV (compiled for GPU), TensorFlow 2 for GPU, PyG and NVIDIA RAPIDS
stable-diffusion - Stable Diffusion basic web UI implemented with ONE python file
safetensors_util - Utility for Safetensors Files
UnstableFusion - A Stable Diffusion desktop frontend with inpainting, img2img and more!
qlora - QLoRA: Efficient Finetuning of Quantized LLMs
persepolis - Persepolis Download Manager is a GUI for aria2.
latent-consistency-model - Run Latent Consistency Models on your Mac
vidcutter - A modern yet simple multi-platform video cutter and joiner.
stablediffusion-infinity - Outpainting with Stable Diffusion on an infinite canvas
stable-diffusion - A latent text-to-image diffusion model
jupyter-notebook-package - A Kurtosis package for Python data engineers, deploying a Jupyter notebook along with a configurable set of databases, and a visualization tool (Streamlit)