intel-extension-for-tensorflow
stable-diffusion-tensorflow
intel-extension-for-tensorflow | stable-diffusion-tensorflow | |
---|---|---|
9 | 18 | |
302 | 1,569 | |
-0.3% | - | |
9.6 | 0.0 | |
11 days ago | 9 months ago | |
C++ | Python | |
GNU General Public License v3.0 or later | 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.
intel-extension-for-tensorflow
-
Watch out AMD: Intel Arc A580 could be the next great affordable GPU
Intel already has a working GPGPU stack, using oneAPI/SYCL.
They also have arguably pretty good OpenCL support, as well as downstream support for PyTorch and Tensorflow using their custom extensions https://github.com/intel/intel-extension-for-tensorflow and https://github.com/intel/intel-extension-for-pytorch which are actively developed and just recently brought up-to-date with upstream releases.
-
How do you allocate more than 4GB of memory for OpenCL in A770 16GB?
I tried Intel® Extension for PyTorch* v1.13.10+xpu and intel-extension-for-tensorflow
-
I'm really happy with the card although the Ti version offers much better performance
Yeah I recently stubbled on it when I was looking into buying a 16gb a770 and wondering what was possible now. GitHub Intel extension for tensorflow
-
Does anyone uses Intel Arc A770 GPU for machine learning? [D]
Intel publish extensions for PyTorch and Tensorflow. I’ve been working with PyTorch so I just needed to follow these instructions to get everything set up.
- Intel Extension for TensorFlow
- Intel Extension for TensorFlow Released
-
SD on intel arc?
Actually I was just on GitHub trying to submit issues related to me testing Intel's PyTorch and Tensorflow extensions when I saw this; it seems that someone has already ported SD over to the tensorflow framework and so you can probably start using intel's extension for tensorflow with it immediately; and according to this article you can use Intel's extension within WSL under windows as well. But unfortunately given how the guy whose issue I linked to has been facing pretty serious performance issues of inferencing taking many minutes longer than it should when using an A770 to do SD-related inferencing, you might be better off waiting for intel's extension for tensorflow versions 1.2 and greater or something like that, so that when it's your turn to use it, Intel has already ironed out most of the major bugs within the software :)
stable-diffusion-tensorflow
- Keras model SD or similar I can train from scratch?
-
Anyone attempted to convert stablediffusion tensorflow to tf lite?
was curious if someone attempted the conversion? I tried here https://github.com/divamgupta/stable-diffusion-tensorflow/issues/58 but having some input shapes error. First time trying the conversion here, would love to run it on a edge tpu.
-
Stable Diffusion Tensorflow to TF Lite
Checking here is someone tried to convert the tensorflow diffusion model into a tf lite?https://github.com/divamgupta/stable-diffusion-tensorflow/issues/58
-
SD on intel arc?
Actually I was just on GitHub trying to submit issues related to me testing Intel's PyTorch and Tensorflow extensions when I saw this; it seems that someone has already ported SD over to the tensorflow framework and so you can probably start using intel's extension for tensorflow with it immediately; and according to this article you can use Intel's extension within WSL under windows as well. But unfortunately given how the guy whose issue I linked to has been facing pretty serious performance issues of inferencing taking many minutes longer than it should when using an A770 to do SD-related inferencing, you might be better off waiting for intel's extension for tensorflow versions 1.2 and greater or something like that, so that when it's your turn to use it, Intel has already ironed out most of the major bugs within the software :)
-
Stable Diffusion with AMDGPU on WSL
tensorflow-stable-diffusion
-
Image2Image with AMD hardware?
# clone git clone https://github.com/divamgupta/stable-diffusion-tensorflow.git cd stable-diffusion-tensorflow # create venv python -m venv --prompt sdtf-windows-directml venv venv\Scripts\activate # verify venv is installed and activated pip --version # install deps pip install -r requirements.txt pip install tensorflow-directml-plugin # you should see DML debug output and at least one GPU python -c 'import tensorflow as tf; print(tf.config.list_physical_devices())' # run (show help) python text2image.py --help python text2image.py --prompt "a fluffy kitten"
-
I have no PC. Just DLed this for iOS
(Answers based on stable-diffusion open model) If you have a M1 processor: https://github.com/divamgupta/diffusionbee-stable-diffusion-ui (I've tested it) Or this claimed faster with TensorFlow: https://github.com/divamgupta/stable-diffusion-tensorflow
-
Keras Inpainting Colab
Added inpainting support to the original keras implementation: https://github.com/divamgupta/stable-diffusion-tensorflow Colab: https://colab.research.google.com/drive/1Bf-bNmAdtQhPcYNyC-guu0uTu9MYYfLu Github page: https://github.com/ShaunXZ/stable-diffusion-tensorflow
-
[N] Stable Diffusion reaches new record (with explanation + colab link)
I wonder if you mean 13 seconds per image because this implementation reports ~10s per image with mixed precision.
-
High-performance image generation using Stable Diffusion in KerasCV
On intel MacBookPro, CPU-only, the original one[1] using pytorch only utilized one core. A tensorflow implementation[2] with oneDNN support which utilized most of the cores ran at ~11sec/iteration. Another OpenVINO based implementation[3] ran at ~6.0sec/iteration.
[1] https://github.com/CompVis/stable-diffusion/
[2] https://github.com/divamgupta/stable-diffusion-tensorflow/
[3] https://github.com/bes-dev/stable_diffusion.openvino/
What are some alternatives?
intel-extension-for-pytorch - A Python package for extending the official PyTorch that can easily obtain performance on Intel platform
fast-stable-diffusion - fast-stable-diffusion + DreamBooth
FluidX3D - The fastest and most memory efficient lattice Boltzmann CFD software, running on all GPUs via OpenCL.
stable-diffusion-webui - Stable Diffusion web UI [Moved to: https://github.com/Sygil-Dev/sygil-webui]
OpenCL-Wrapper - OpenCL is the most powerful programming language ever created. Yet the OpenCL C++ bindings are cumbersome and the code overhead prevents many people from getting started. I created this lightweight OpenCL-Wrapper to greatly simplify OpenCL software development with C++ while keeping functionality and performance.
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.
compute-runtime - Intel® Graphics Compute Runtime for oneAPI Level Zero and OpenCL™ Driver
keras-cv - Industry-strength Computer Vision workflows with Keras
bitsandbytes - Accessible large language models via k-bit quantization for PyTorch.
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.
diffusers - 🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
stable-diffusion - Go to lstein/stable-diffusion for all the best stuff and a stable release. This repository is my testing ground and it's very likely that I've done something that will break it.