support cpu, pip install #80
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
illeatmyhat
force-pushed
the
main
branch
6 times, most recently
from
4268ddd to
9b14b52
Compare
added 2 commits
August 25, 2022 19:48
|
This isn't a bad start IMO, but need to make ipex optional somehow. I'd also like to see device be configurable. Maybe with a "--device=cpu' or 'cuda' command line argument. |
|
This is a dead repo. Real, honest efforts towards hardware compatibility and usability should be devoted to getting a compiled binary distributed with Vulkan Kompute as the runtime backend. |
I will work on this. I like the idea. |
whimbree
added a commit
to whimbree/stable-diffusion
that referenced
this pull request
Sep 17, 2022
* optimizedSD * addedd argparse * Added support for multiple images * cleaned repo * cleaned repo * cleaned repo * Removed Deepcopy stuff * added batched inference * Optimized for lesser VRAM * Added Mixed Precision support * added img2img * path length error * Delete src directory * removed default seed * added support of specifying image seed * Added gradio interface * polished gradio app * added weighted prompts * fixed gradio windows bug * added support for specifying GPU and CPU * added turbo for faster inference * Format code, rewrite README Format code to be easier to understand, completely rewrite README to be more professional and user friendly, fixed typos etc. * Updated Readme * fix command * Add optional format argument for JPG output (CompVis#80) * Add --format argument to optimized_txt2img.py * Add --format argument to optimized_img2img.py * Add explanation of --format argument to README * added logging and jpg * added inpainting * Fixed typos * added plms for txt2img * Dockerize optimizedSD (CompVis#97) * fixed txt2img ddim error * Create FUNDING.yml * Update attention.py * inpaint gradio mask mode fixed (cherry picked from commit ddde264) * adapts memory-efficient attention to unet_bs larger than 1 * further improvements on memory-efficient attention * puts back changes to inpaint_gradio.py * updated README * Update README.md * added license * Update README.md Corrected "Telsa" into "Tesla" * Use modern method to enable GPU access. * fixing bugs that using gpus other than cuda:0 * added samplers for txt2img * added missing samplers file * Update inpaint_gradio.py (CompVis#157) Add mask_image, Co-authored-by: gruyade <> Co-authored-by: basujindal <bjbasujidnal@gmail.com> Co-authored-by: Basu Jindal <42815171+basujindal@users.noreply.github.com> Co-authored-by: Maika <karen.poffenhosen@gmail.com> Co-authored-by: Mimaki SiON <sion.git@pn.dojin.com> Co-authored-by: Conway <yawnoc@pm.me> Co-authored-by: Sasha Kotlyar <arktronic@users.noreply.github.com> Co-authored-by: Viacheslav Ivannikov <44505718+neonsecret@users.noreply.github.com> Co-authored-by: bironsecret <44505718+bironsecret@users.noreply.github.com> Co-authored-by: ryudrigo <ryudrigo@protonmail.com> Co-authored-by: Noobest Noob <easonxie106@gmail.com> Co-authored-by: Awth Wathje <awthwathje@gmail.com> Co-authored-by: Kieran Liu <xiaojiang_liu@apple.com> Co-authored-by: gruyade <113286260+gruyade@users.noreply.github.com>
enzymezoo-code
added a commit
to enzymezoo-code/stable-diffusion
that referenced
this pull request
Oct 1, 2022
Fix speed issues
ScrewTSW
pushed a commit
to ScrewTSW/stable-diffusion
that referenced
this pull request
Oct 4, 2022
* Add --format argument to optimized_txt2img.py * Add --format argument to optimized_img2img.py * Add explanation of --format argument to README
|
Hi what is the state here? I have an laptop with only Intel cpu/gpu and would like to use the project... I'm also using nixos and when CPU or what ever all support is integrated I would like to package it for nixos. |
|
could these repo help to integrate these feature? https://github.com/ModeratePrawn/stable-diffusion-cpu |
|
plz don't abandon the idea of making this work on integrated intel gpu's. |
weolix
approved these changes
Jul 26, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uses modified changes from #47 to implement CPU support.
Adds
pyproject.tomlso that the project can be pip installed.