DiffBIR

DiffBIR copied to clipboard

about how to show low quality image

1

I want to know how to use show_lq to display low quality image？ Thank you very much！ 

ocean1229-max

set w/o restoration module

1

DIffbir How to set up w/o restoration module training

lijain

Question in paper: For ablation study "Compare ControlNet and LAControlNet"

4

Hi, I have a question in paper. May I ask a question In the ablation study of "Compare ControlNet and LAControlNet". Figure7(c), the w/ ControlNet result is trained from scratch...

LokiXun

SR scale x1 with OOM: CUDA out of memory

4

I want to handle my photo(resolution 4080 × 3060), using RTX 4090, enabled Tiled, it failed! What should i do? Does DiffBIR support quantization ?

amanoooo

Training killed without error shorting after starting

1

I am training the model on two nodes each with 4 A100 GPUs with the batch size of 32. Shortly after starting the training, the process gets killed. Any clue...

CheruscanArminius

点击run以后没有生成结果图片，一直在loading, 没有日志更新

7

控制台  界面 

fusu192

Model downloading problems: HuggingFace connection error

21

When I tried to inference，this error happened.I don‘t know how to solve this problem. huggingface hub.utils.errors .LocalEntryNotFoundError: An error happened while trying to locate the file on the Hub and...

bjlybjb

Training set for BIR task

3

Hi, you choose the ImageNet for training. Did you select the images larger than 512-size before training or take all images into training set and resize them to 512-size? Thanks...

EternalEvan

how about Intel GPU support?

needhelb

Question on training Stage2 with Real-ESRGAN degradation

4

Hi, thanks for sharing the great work! I tried to follow the training process, but faced problems during training in the Stage 2 model. After filling the ```train_cldm.yaml``` file, I...

JaehaKim97