sd-extension-system-info
AITemplate
sd-extension-system-info | AITemplate | |
---|---|---|
51 | 37 | |
258 | 4,455 | |
- | 0.7% | |
9.3 | 8.7 | |
3 months ago | 6 days ago | |
Python | Python | |
MIT License | Apache License 2.0 |
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-extension-system-info
- RTX 4070 vs rx 7800 xt
-
AMD for AI
I've been using both SD and various LLM on linux without any issue and have done so for months. Windows support is also starting to roll out slowly, with koboldcpp-rocm recently giving me 20-25+t/s for a13B even on windows. you can see what SD performance is like on sites like these. those numbers roughly match what i get on my RX6800 as well (8t/s).
-
Stable Diffusion in pure C/C++
That seems a lot worse than a 2060 SUPER with PyTorch in A1111.
https://vladmandic.github.io/sd-extension-system-info/pages/... (search for 2060 SUPER)
-
Iterations per second benchmarking question
But usually A1111 users use benchmark on this extension https://github.com/vladmandic/sd-extension-system-info
-
Best AMD SD Guide for 2023?
AMD SD = Setup Diaster? it was quite troublesome googling the few linux/amdgpu/rocm/sd vers/configs/params posts online. Also the whole PC may hang during generation which is bad for the harddisk. Your card is way more powerful so may not hang like mine. People are getting 8it/s https://vladmandic.github.io/sd-extension-system-info/pages/benchmark.html
-
Which one is better? Nvidia Tesla M40 vs Nvidia Tesla P4?
According to system info benchmark, M40 is like 1-2 it/s and P4 is barely better than that.
- Video card price/performance ratio
-
--medvram. Should I remove this flag? Running 3090
Anyway to properly "benchmark" the impacts different switches on your image generation speed, it is better to use the benchmarking utility from extension https://github.com/vladmandic/sd-extension-system-info (it also creates a very handy table of results from other users at https://vladmandic.github.io/sd-extension-system-info/pages/benchmark.html for you to compare with.
-
Searching for install guide for top performance setup on WSL2 (Automatic1111)
I can see that the top performance benchmark results on SD WebUI Benchmark Data (using RTX 4090), are obtained through WSL2 running Automatic1111 on a Linux dist and Python 3.10.11, along with PyTorch 2.1.0.dev+cu121 (like benchmark id: 4126)
-
Advice for Optimization on an RTX 8000
You should be able to compare based on the published benchmarks, just replicate the settings based on what's reported https://vladmandic.github.io/sd-extension-system-info/pages/benchmark.html
AITemplate
-
Show HN: Shortbread, a web app that helps you create AI comics in minutes
VoltaML is a relatively vanilla diffusers-based backend, so its not a hairy monster to hack like you may have seen with SAI-based UIs.
The AITTemplate code is a lightly modified version of Facebook's example, code, to get rid of small issues like VRAM spikes: https://github.com/facebookincubator/AITemplate/tree/main/ex...
InvokeAI is also diffusers based, but they seem to mess with the pipeline a bit more.
And anyway, all that may be a better reference for interesting features rather than a backend to try and adopt.
-
List of all the ways to improve performance for stable diffusion.
let me know if you discover any more ways to improve SD. I am currently looking into facebooks AITemplate : https://github.com/facebookincubator/AITemplate
- [R] AITemplate Python to AMD compiler {META}
-
Nearly 2x speedup for SD rendering using AITemplate
Link to AITemplate itself: https://github.com/facebookincubator/AITemplate
- Render a neural network into CUDA/HIP code
- Render neural network into CUDA/HIP code
- AITemplate: 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.
- A1111 vs Olive vs AITemplate.
What are some alternatives?
automatic - SD.Next: Advanced Implementation of Stable Diffusion and other Diffusion-based generative image models
stable-diffusion-webui - Stable Diffusion web UI
tomesd - Speed up Stable Diffusion with this one simple trick!
nebuly - The user analytics platform for LLMs
voltaML-fast-stable-diffusion - Beautiful and Easy to use Stable Diffusion WebUI
xformers - Hackable and optimized Transformers building blocks, supporting a composable construction.
stable-diffusion-webui-directml - Stable Diffusion web UI
voltaML - ⚡VoltaML is a lightweight library to convert and run your ML/DL deep learning models in high performance inference runtimes like TensorRT, TorchScript, ONNX and TVM.
scribble-diffusion - Turn your rough sketch into a refined image using AI
stable-diffusion-tensorflow - Stable Diffusion in TensorFlow / Keras
HIP - HIP: C++ Heterogeneous-Compute Interface for Portability
rocm-gfx803