-
Notifications
You must be signed in to change notification settings - Fork 5.6k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
add a "Community Scripts" section #7358
Conversation
cc @stevhliu @sayakpaul I'm not super good at this but I really just want to start to collect them:) |
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
… into commiunity-scrippt
examples/community/README.md
Outdated
## Example usages | ||
|
||
### IP Adapter Negative Noise | ||
|
||
Diffusers pipelines are fully integrated with IP-Adapter, which allows you to prompt the diffusion model with an image. However, it does not support negative image prompts the same way it supports negative text prompts: it does not accept a `negative_ip_adapter_adapter` argument; when you pass an `ip_adapter_image,` it will create a zero-filled tensor as a negative image. This script shows you how to create a negative noise from `ip_adapter_image` and use it to significantly improve the generation quality while preserving the composition of images. | ||
|
||
[cubiq](https://github.com/cubiq) initially developed this feature in his [repository](https://github.com/cubiq/ComfyUI_IPAdapter_plus). The community script was contributed by [asomoza](https://github.com/Somoza). You can find more details about this experimentation [this discussion](https://github.com/huggingface/diffusers/discussions/7167) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
How about providing a teaser along with results. Let's maybe not include code because the scripts themselves will provide them.
Also, WDYT about having a separate README_community_scripts.md
to keep the current README a little less cluttered and easy to follow?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
➕ 1 for having a separate README.md
for the community scripts!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@sayakpaul
addressed the separate README part!
But I left the codes there for now because I did not make a separate .py
file for each - I feel like these are just tips and tricks that would be used with some other things so it might be easier in md
format so user can just copy-paste it
it's not ideal because they are a bit long so feel free to help improve it with a PR if you have good ideas!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Great idea! I think as we start to collect more of these crowdsourced tips/tricks, it'll be easier to plan some better docs around them 😄
examples/community/README.md
Outdated
## Example usages | ||
|
||
### IP Adapter Negative Noise | ||
|
||
Diffusers pipelines are fully integrated with IP-Adapter, which allows you to prompt the diffusion model with an image. However, it does not support negative image prompts the same way it supports negative text prompts: it does not accept a `negative_ip_adapter_adapter` argument; when you pass an `ip_adapter_image,` it will create a zero-filled tensor as a negative image. This script shows you how to create a negative noise from `ip_adapter_image` and use it to significantly improve the generation quality while preserving the composition of images. | ||
|
||
[cubiq](https://github.com/cubiq) initially developed this feature in his [repository](https://github.com/cubiq/ComfyUI_IPAdapter_plus). The community script was contributed by [asomoza](https://github.com/Somoza). You can find more details about this experimentation [this discussion](https://github.com/huggingface/diffusers/discussions/7167) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
➕ 1 for having a separate README.md
for the community scripts!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks! 🤗
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* add * add tiling * fix * fix * fix * give community script its own readme * Update examples/community/README_community_scripts.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update examples/community/README_community_scripts.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update examples/community/README_community_scripts.md Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com> * Update examples/community/README_community_scripts.md --------- Co-authored-by: Alexis Rolland <alexis.rolland@ubisoft.com> Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Currently, our community folder only consists of community pipelines. However, there are tons of tips and tricks you can use with diffusers without having to make a pipeline for them.
I'm adding a "Community Scripts" section to the community folder README so we can start collecting these scripts:) We will follow the same general principle as how we currently maintain community pipelines:
Moving forward, we will also be starting to select some of the tricks and tips from this section and polish them into tutorials in our docs; but this should be the first place where we collect such scripts