Comments (4)
For images smaller than 512, we resize them to a resolution of 512 and then perform restoration. For images larger than 512, we directly use them as input to DiffBIR, relying on DiffBIR's generalization ability for restoration. However, this approach imposes significant demands on GPU memory😢😢😢 , so we do indeed require a patch-based restoration method. Currently, our primary focus is on improving the restoration performance of DiffBIR at a resolution around 512, so it may be some time before we incorporate a patch-based sampling strategy.
from diffbir.
Thank you very much for your answer. If possible, please notify me once it's implemented.
Thanks again for your outstanding work.
from diffbir.
Hello! We have integrated mixture of diffusers, please have a try😄!
from diffbir.
Excellent work; although I've already implemented a similar feature myself, what you offer is more powerful. I will try to integrate it into my code.
Thank you very much for your work!
from diffbir.
Related Issues (20)
- 使用更大规模的数据训练,会有更好的效果吗? HOT 16
- about how to show low quality image HOT 1
- set w/o restoration module HOT 1
- Can this network do the work of image deblurring? HOT 1
- 为什么要用在低清图上finetune的encoder? HOT 2
- AMD GPU support?
- 请问如何使用 diffbir v2 中的训练结果进行测试呢 HOT 1
- 使用tiled对大图像执行SR时失败了 HOT 1
- 第二张图芯片的那个是怎么跑出来的?我跑不下来这个效果 HOT 3
- 有关测试需要的显存问题 HOT 1
- How to train DiffBIR for face retouching? HOT 5
- 爆显存的问题
- optimizer selection HOT 6
- 有关restoration module的问题 HOT 1
- !!! Exception during processing!!! [Errno 2] No such file or directory
- About the Training Time HOT 1
- only train and infer stage 2 model HOT 1
- about feature modulation. HOT 2
- onnx
- Training problem
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 diffbir.