sd-webui-colab VS tvm

(Added Aug. 28, 2022) Colab notebook Stable Diffusion WebUi - Altryne by altryne. GitHub repo. txt2img. img2img. inpainting. Gradio user interface. Uses sd-webui repo.

you can try the colab version of hlky repo: https://github.com/altryne/sd-webui-colab, easier to setup or a one cell colab version: https://github.com/pinilpypinilpy/sd-webui-colab-simplified, everything works in one cell

For those without GPU's / not a powerful enough one. You can start the hlky stable diffusion webui (yes, web ui) in Google Colab with this notebook[0].

It's simple and it works, using colab for processing but actually giving you a URL (ngrok-style) to open the pretty web ui in your browser.

I've been using that on-the-go when not at my PC and it's been working very well for me (after trying numerous other colab-dedicated repos, trying to fix them, and failing).

[0]: https://github.com/altryne/sd-webui-colab

The code is directly adapted from the Colab notebook repo based on the hlky GitHub repo. I really don't have much experience with coding and didn't change much of the code other than the paths specific to Kaggle.

I'm running SD-webui on google colab https://github.com/altryne/sd-webui-colab/ with a colab pro account and its awesome but it does crash with attempting larger images. Is anyone using a google colab pro+ account and able to process larger images?

Based off of https://github.com/altryne/sd-webui-colab and https://github.com/hlky/stable-diffusion

Yes. Web-llm is a wrapper of tvmjs: https://github.com/apache/tvm

Just wrappers all the way down

Yes, this is coming! Myself and others at OctoML and in the TVM community are actively working on multi-gpu support in the compiler and runtime. Here are some of the merged and active PRs on the multi-GPU (multi-device) roadmap:

Support in TVM’s graph IR (Relax) - https://github.com/apache/tvm/pull/15447

Would it make sense to have a backend support for OpenXLA, Apache TVM, Jittor or other similar to get free GPU, TPU and other accelerators for free ?

I have tried the iPhone app. It's fast. They're using Apache TVM which should allow better use of native accelerators on different devices. Like using metal on Apple and Vulcan or CUDA or whatever instead of just running the thing on the CPU like llama.cpp.

I was going to answer the same, I find the approach of machine learning compilers that directly compile models to host and device code better than having to bring a huge runtime. There are exciting projects in this area like TVM Unity, IREE [2], or torch.export [3]

[1] https://github.com/apache/tvm/tree/unity

[2] https://pytorch.org/get-started/pytorch-2.0/#inference-and-e...

[3] https://pytorch.org/get-started/pytorch-2.0/#inference-and-e...

Apache TVM home page: https://tvm.apache.org/

It's pretty clear its referring to the output of Apache TVM and Meta's Glow

As mentioned in sibling comments, Torch is indeed the glue in this implementation. Other glues are TVM[0] and ONNX[1]

These just cover the neural net though, and there is lots of surrounding code and pre-/post-processing that isn't covered by these systems.

For models on Replicate, we use Docker, packaged with Cog for this stuff.[2] Unfortunately Docker doesn't run natively on Mac, so if we want to use the Mac's GPU, we can't use Docker.

I wish there was a good container system for Mac. Even better if it were something that spanned both Mac and Linux. (Not as far-fetched as it seems... I used to work at Docker and spent a bit of time looking into this...)

[0] https://tvm.apache.org/

Or use TVM, the idea is to compile your model into code that you can load at runtime. Similar to onnxruntime, it only does DNN inference; so you need domain-specific code.