ROCm-docker
stable-diffusion
| ROCm-docker | stable-diffusion | |
|---|---|---|
| 3 | 20 | |
| 392 | 338 | |
| 1.0% | - | |
| 5.1 | 0.0 | |
| 23 days ago | over 1 year ago | |
| Shell | Jupyter Notebook | |
| MIT License | 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.
ROCm-docker
-
AMD Funded a Drop-In CUDA Implementation Built on ROCm: It's Open-Source
https://rocm.docs.amd.com/projects/install-on-linux/en/lates... links to ROCm/ROCm-docker: https://github.com/ROCm/ROCm-docker which is the source of docker.io/rocm/rocm-terminal: https://hub.docker.com/r/rocm/rocm-terminal :
docker run -it --device=/dev/kfd --device=/dev/dri --group-add video rocm/rocm-terminal -
Stable Diffusion PR optimizes VRAM, generate 576x1280 images with 6 GB VRAM
Not sure about the 6600, but there is a guide for Linux at least:
https://m.youtube.com/watch?v=d_CgaHyA_n4&feature=emb_logo
And this is somehow relevant (possibly), as I kept the link open.
https://github.com/RadeonOpenCompute/ROCm-docker/issues/38
-
It's working perfectly under Linux
As for the Docker image, I suppose you could compile the image (https://hub.docker.com/r/rocm/pytorch) by yourself using the sources (https://github.com/RadeonOpenCompute/ROCm-docker#building-images), which seems to be quite a bit of work. Better, you could just use an older tag of the upstream image, eg. rocm4.1.1_ubuntu18.04_py3.6_pytorch instead of rocm4.2_ubuntu18.04_py3.6_caffe2 or latest . Just make sure your container version matches your host ROCm version.
stable-diffusion
- [Machine Learning] [P] Exécutez une diffusion stable sur le GPU de votre M1 Mac
- High-performance image generation using Stable Diffusion in KerasCV
-
Charl-e: “Stable Diffusion on your Mac in 1 click”
SD on an Intel mac with Vega graphics runs pretty well though — I think it ran at something like ~3-5 iterations/s for me, which is decent. I ran either https://github.com/magnusviri/stable-diffusion or https://github.com/lstein/stable-diffusion which have MPS support
-
Stable Diffusion PR optimizes VRAM, generate 576x1280 images with 6 GB VRAM
https://github.com/magnusviri/stable-diffusion/commit/d0b168...
Copying this change fixed seeds on M1 for me.
-
Intel Mac User, How do I start?
You should be able to run it on a CPU. Maybe try this version. If MPS is supported on your Mac you can check this out.
-
[P] Run Stable Diffusion on your M1 Mac’s GPU
A group of open source hackers forked Stable Diffusion on GitHub and optimized the model to run on Apple's M1 chip, enabling images to be generated in ~ 15 seconds (512x512 pixels, 50 diffusion steps).
-
Run Stable Diffusion on Your M1 Mac’s GPU
Magnusviro [0], the original author of the SD M1 repo credited in this article, has merged his fork into the Lstein Stable Diffusion repo [1], and you can now run Lstein fork with M1 as of a few hours ago.
This adds a ton of functionality - GUI, Upscaling & Facial improvements, weighted subprompts etc.
This has been a big undertaking over the last few days, and I highly recommend checking it out.
[0] https://github.com/magnusviri/stable-diffusion
-
How are Mac people using Windows for A.I. stuff?
You can run it on an M1. Using a macbook M1 pro max with 32Gb I get 512x512 in about 50 seconds. use this branch https://github.com/magnusviri/stable-diffusion/tree/apple-mps-support
-
ResolvePackageNotFound
I had this error too, and I tried a ton of things to get cudatoolkit to install, without any luck. This fork has an environment-mac.yml file that actually got it working on my M1 Max: https://github.com/magnusviri/stable-diffusion/tree/apple-silicon-mps-support
-
If I set a seed value and re-run using the exact same settings, should I get the same image back each time?
But when I run it (locally, using the Mac M1 port), every time I run it creates a different image.
What are some alternatives?
awesome-kubernetes - A curated list for awesome kubernetes sources :ship::tada:
openvino - OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
AiDungeon2-Docker-ROCm - Runs an AIDungeon2 fork in Docker on AMD ROCm hardware.
stable-diffusion-webui-docker - Easy Docker setup for Stable Diffusion with user-friendly UI
ZLUDA - CUDA on AMD GPUs
stable-diffusion-webui - Stable Diffusion web UI [Moved to: https://github.com/sd-webui/stable-diffusion-webui]
docker-elk - The Elastic stack (ELK) powered by Docker and Compose.
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
Dokku - A docker-powered PaaS that helps you build and manage the lifecycle of applications
rocm-build - build scripts for ROCm
Docker-OSX - Run macOS VM in a Docker! Run near native OSX-KVM in Docker! X11 Forwarding! CI/CD for OS X Security Research! Docker mac Containers.
stable-diffusion - This version of CompVis/stable-diffusion features an interactive command-line script that combines text2img and img2img functionality in a "dream bot" style interface, a WebGUI, and multiple features and other enhancements. [Moved to: https://github.com/invoke-ai/InvokeAI]