Comments (3)
If you mean at 64 / 77 tokens, then yes. The "infinite prompt" thing is an extension in automatic1111 and such that splits longer prompts and feeds them into the model in stages.
from shark.
Shark should currently detect and build a different unet if you go over 64 / 77 token, one that supports a longer prompts, and uses that. (I think up to 512 tokens? The .vmfb files get unet512
in the naming rather than just unet
, but I'm not super sure of how it works).
It doesn't use that unet by default as that one creates somewhat different images to the 64 / 77 version with the same seed even when a longer prompt isn't needed.
from shark.
That's odd. I'm guessing I'm going over most of the time without knowing it. Looking at my built .vmfbs most are using unet512. At the same time I've had it error out saying the model could only handle 64/77 tokens when the prompt was nowhere near 512 tokens, so I'm not sure. I think this only happened when I had a really long negative prompt, so it's possible only the positive prompt is checked to see which it should use? I searched the codebase for related terms and saw quite a bit about unet512 upconvert in the chat models but not in diffusers.
from shark.
Related Issues (20)
- Warnings after today's update
- Crash/error on 'stock' test gen HOT 2
- fail to convert qwen llama model to MLIR and vmfb.
- Need to restart in between generations of higher resolution images HOT 1
- RESOURCE_EXHAUSTED when trying to use hires fix
- SDXL Error
- Sharkify Model UnetModel.forward() Arguments Error
- Input image masks on Image2Image does not seem to do anything HOT 1
- SHARK won't start or run without internet
- Error while installing rx570 don't know if it is because of the card or software issue please fix it
- LoRA models not showing up in dropdown
- System interrupts gets very high CPU followed by complete computer shutdown HOT 3
- Document for the compilation flow ?
- Enable llama2 benchmarking with Turbine HOT 1
- FP8 Support HOT 10
- (Shark-1.0) setup_venv.ps1 specifies a torch-mlir version that has dropped off the end of package index
- RuntimeError: duplicate registrations HOT 3
- Gradio Button has no attr "label"
- Gradio JSON has no option interactive
- problem with Torch-mlir on Ubuntu, latest en previous Shark version
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 shark.