Comments (4)
Since the queue executes commands sequentially, wouldn't it be more efficient to load models on-demand? That way people with a GPU with <8GB RAM in their GPU can load the bot.
from g-diffuser-bot.
The beta2 branch already reduces this down to just 2 pipelines as the inpainting pipeline is a superset of the functionality built into img2img. Technically, it is also a superset of the functionality of the txt2img pipeline and I intend to reduce the number of pipes down to just 1, at least until diffusers can get their act together with memory usage.
I am leaving this issue open to track the progress. Thank you.
from g-diffuser-bot.
I should also mention:
The model load time is very significant and can easily quadruple the generation time if you need to reload the model for each command. The workaround in beta2 is a) reducing the number of required pipes, and b) you can use the CLI to do single generation commands one at a time, and this will only use whatever model you need to actually complete your command, very similar to how the old CompVis code worked.
Lastly, in beta2 you have the option of using a pre-specified sub-selection of pipes in the config file, allowing you to save memory if you choose to forego the functionality in unneeded pipes. This will be important when more models / pipes are added to diffusers.
from g-diffuser-bot.
This is now complete with the integration of haffried's grpc server in the dev branch.
from g-diffuser-bot.
Related Issues (20)
- add annotation argument to sample params
- discord "gui" buttons for "riffing" any image the bot has attached
- add img2img and in/out-painting to the discord bot HOT 1
- clean-up root folder
- Model merge tool
- Re-add pre-sampler init noise for outpainting, use pixel shuffle technique for color spreading
- Use PNG EXIF data to mirror json argument data HOT 5
- Heartbeat blocked for more than 30 seconds, error. HOT 2
- Default to "prompt" when typing after /dream HOT 2
- Allow for DMing the bot
- Bot ignoring defaults for some options HOT 2
- Changing default_output_n also increases the minimum n HOT 1
- Seed shown in message is incorrect for n > 1 HOT 1
- Add support for using multiple gRPC servers simultaneously with discord bot or CLI HOT 1
- Seamless generation mode
- Discord bot commands unavailable on certain guilds / servers HOT 2
- Hey, I was wondering if it has deforum support. Can we use this bot for text2music and music2img stuff? HOT 3
- Adding a Guide for Linux / Colab / paperspace? HOT 2
- SD Models
- How to apply mask softness only on one side of the mask?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from g-diffuser-bot.