-
Does Swin_IR also work for colored JPEG images for JPEG_CAR problem? If yes, how to use it?
-
Also any tested U-net structure like scunet?
-
I edit the window batch file with the line: set COMMANDLINE_ARGS=--api, so that I could use the plugin but doesn't work. How could I fix it?
Here is the result after I add the command line
Instal…
-
**Describe the bug**
I'm using [this ONNX file](https://huggingface.co/rocca/swin-ir-onnx/resolve/main/003_realSR_BSRGAN_DFO_s64w8_SwinIR-M_x4_GAN.onnx) for [this browser-based SwinIR super-resolutio…
-
Need of feature :-
Will increase use of transformers in Computer Vision task, we need a way to efficient apply attention mechanism for images (unlike vision transformer which calculate attention for…
-
SD launched with DirectML, works and launches normally with this bug but inpainting doesn't work
> *** Error loading script: preprocessor_inpaint.py
>
> Traceback (most recent call last):
>…
-
Hi, I'm wondering why first train stage1 and stage2 model with codeformer degradation, and then train stage1 model with RealESRGAN degradation. Intuitively, it will cause input distribution shift of s…
-
Hi,
Thank you for the great research and the work.
I can do my testing with no problem using BasicSR as well. However, I was wondering if we can have the HAT-L model as a stand-alone script so …
-
(diffbir) E:\AI>python e:\ai\diffbir\inference.py --config E:\AI\DiffBIR\configs\model\cldm.yaml --ckpt E:\AI\DiffBIR\ckpt --reload_swinir --swinir_ckpt E:\AI\DiffBIR\ckpt --steps 50 --input E:\AI\Dif…
-
很棒的工作！
我有一个问题想请教一下。文章里提到：“During inference, we replace our trained restoration mod- ule with off-the-shelf task-specific restoration models: BSR- Net [73]2 for BSR, SwinIR [29]3 used in DifFace [67] …