voltaML-fast-stable-diffusion
stable-diffusion-ui
voltaML-fast-stable-diffusion | stable-diffusion-ui | |
---|---|---|
14 | 249 | |
941 | 6,808 | |
2.0% | - | |
9.7 | 9.9 | |
about 2 months ago | 11 months ago | |
Python | JavaScript | |
GNU General Public License v3.0 only | GNU General Public License v3.0 or later |
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.
voltaML-fast-stable-diffusion
-
Show HN: Shortbread, a web app that helps you create AI comics in minutes
Also, VoltaML has a good reference GPU AITemplate SD 1.5 implementation:
https://github.com/VoltaML/voltaML-fast-stable-diffusion/tre...
The speed jump is massive on my desktop GPU, probably even more dramatic on cloud hardware, and it may support some things (weight swapping/lora swapping/resolution changing) better than JAX.
-
AI Hordeās AGPL3 hordelib receives DMCA take-down from hlky
This kind of drama is just sad.
I dont know if you are OP, but plenty of other UIs have interrogator code, like https://github.com/VoltaML/voltaML-fast-stable-diffusion/tre...
- What is the text-to-image AI tool?
-
WIP - TensorRT accelerated stable diffusion img2img from mobile camera over webrtc + whisper speech to text. Interdimensional cable is here! Code: https://github.com/venetanji/videosd
If you just want an accelerated ui, you can check https://github.com/ddPn08/Lsmith/ or https://github.com/VoltaML/voltaML-fast-stable-diffusion which also use the same origina nvidia code. These projects don't do img2img though, you can check in my repo for the img2img pipeline if you need. You need to compile the tensorrt engines for the models first. There are a few steps you can check in their script: export onnx, optimize onnx, compile engine for optimized onnx. I streamlined that a bit and I normally just run my compile.py in docker to build engines.
- 4090, 33 it/s, Windows 10
-
RTX 4090 12.5it/s ... can this be even faster?
Try https://github.com/VoltaML/voltaML-fast-stable-diffusion
- When will the 30 img per 1 second model happen?
-
Get in the robot, Harry
This one: VoltaML/voltaML-fast-stable-diffusion: Lightweight library to accelerate Stable-Diffusion, Dreambooth into fastest inference models with single line of code š„ š„ (github.com)
- Anyone tried this VoltaML fast stable diffusion. I thought they were gonna add support for automatic1111.
-
Me waiting for A1111 Depth2img to officially support custom depth maps.
You will be waiting a lot longer for this to be implemented: https://github.com/VoltaML/voltaML-fast-stable-diffusion
stable-diffusion-ui
-
Useful Links
CMDR2's 1-Click Installer
-
Best current stable diffusion UI app?
Hey so i'm currently using easydiffusion but its missing one feature i've been really wanting to play around with recently. Video, and i've heard from some others that its one of the easiest to install but least peformant and worse options you can get; so what do you guys suggest?
-
The softer side of self hosting: The aesthetics, logos
Or just use the CPU and it works, just takes a few minutes. stable diffusion cpu But don't let me stop you, I need one too.
-
So how is nvidia gpu experience these days?
No. CUDA is very straightforward. There is even a nice project that sets up Stable Diffusion for you. With basically no knowledge about AI i was able to get it to run. If i recall correctly i just needed to install one dependency manually, and i was provided with nice web gui for playing with it.
-
Models and samplersā¦
You could read the guide first: https://github.com/cmdr2/stable-diffusion-ui/wiki/UI-Overview or Start easy diffusion
-
Could someone please make my wife into a realistic sculpture/statue? Will tip $50 for a perfect one!
Thanks and your right there are loads, trying out this from GitHub
- What is the text-to-image AI tool?
-
Tip for a (kinda) newbie
Simplest start https://github.com/cmdr2/stable-diffusion-ui
-
SD privacy? Offline? Concerns?
First is Easy Diffusion, you need to be online just once to run the installer. It downloads several extra files. Let it finish and then make some test pictures. Exit everything (browser window and text window). Then anytime you want to run it, just turn off internet and run the batch file to start it up. No internet!
-
Need help installing SD on AMD!!
Yesterday I got Easy Diffusion to work (on Windows only), but it refuses to use the GPU and instead uses the CPU, which of course, takes nearly an hour to make a 512x512 image.
What are some alternatives?
stable-diffusion-webui - Stable Diffusion web UI
TensorRT - NVIDIAĀ® TensorRTā¢ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
ComfyUI - The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.
sd-extension-system-info - System and platform info and standardized benchmarking extension for SD.Next and WebUI
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
diffusionbee-stable-diffusion-ui - Diffusion Bee is the easiest way to run Stable Diffusion locally on your M1 Mac. Comes with a one-click installer. No dependencies or technical knowledge needed.
A1111-Web-UI-Installer - Complete installer for Automatic1111's infamous Stable Diffusion WebUI
AITemplate - AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
civitai - A repository of models, textual inversions, and more
depthmap2mask - Create masks out of depthmaps in img2img
SHARK - SHARK - High Performance Machine Learning Distribution