Comments (4)
I think they're mocking the sparks of AGI paper in Figure 13 (given the 🤨 emoji) 🙂.
I think many inpainting methods can already do these tasks. For instance, here's the example of using generative fill in photoshop, with 3 different generations:
![](https://private-user-images.githubusercontent.com/28768645/287871531-9f61d16a-9788-48b6-b1b3-8d7b9f938385.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.ec9Lkm74KJB8Qw2_92oRFB6_qVZ-TA1TNdO_-VHzcFY)
![](https://private-user-images.githubusercontent.com/28768645/287871604-156bfb5a-7549-4067-a638-8759068aa4a4.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.34OsKbUUoiHBPWYILoxwUS3UH6-4Dx4SXJbHF47OBSE)
![](https://private-user-images.githubusercontent.com/28768645/287871620-f598580e-abf7-4b37-8d83-4165fe1f3e96.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.E9ZxmcOhqCRhXmEB8da9u6hlIZUdtLPwmDtcDpE_iAI)
![](https://private-user-images.githubusercontent.com/28768645/287871637-0f53dc6a-e4c7-48aa-85bc-a8fadf9e7ba1.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.wt4jIzSDyqDwNN2j00NFYdYb08tXRRFw9RLKR4xdEc8)
Any inpainting method has to reason about its surroundings and fill in the blank based on context :)
from lvm.
Thank the authors for the great work!
The same question. Are there some IQ-testing-like images in the training dataset? If not, the performance is really amazing!
from lvm.
I think they're mocking the sparks of AGI paper in Figure 13 (given the 🤨 emoji) 🙂.
I think many inpainting methods can already do these tasks. For instance, here's the example of using generative fill in photoshop, with 3 different generations:
![]()
![]()
![]()
Any inpainting method has to reason about its surroundings and fill in the blank based on context :)
Great!Thanks for trying that! Could you please try more instances with Photoshop, e.g., the end image of the first row and third row?
from lvm.
Hi yes, this was a friendly joke and we'll check if we can do more interesting cases later. Thank you all for your kind support and interests, we really appreciate it.
Best,
Yutong
from lvm.
Related Issues (20)
- Thanks for Interesting work HOT 1
- All code HOT 9
- release training data HOT 2
- That's Amazing for the whole world! HOT 1
- Support! Hoping for the emergence of a real large vision model! HOT 1
- Hope for a bigger vision world! HOT 1
- Huggingface transformers support HOT 1
- Consider hosting the models and datasets in GitHub directly using XetData add-on HOT 1
- Question about [BOS] and [EOS] tokens HOT 1
- Inquiry Regarding Release Timeline for Code, Models, and Datasets HOT 2
- Questions about whether the LVM has certain transferability to unknown tasks
- question about the data
- Question about inference details
- About the released weights HOT 3
- About the plan to release the model HOT 3
- It has been silent for too long. WHY? HOT 1
- Question about image classification
- LVM HF Demo not working HOT 3
- can't load vqgan pretrianed weights HOT 2
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 lvm.