I've been looking for these upscale models " 100k [epoch 507, psnr 30.517, ssim 0.83536, lpips 0.031511] or 150k [epoch 760, psnr 31.331, ssim 0.84292, lpips 0.029] " and I can't find them, do you have a link to them?
couldn't get the model to load. just says this node is currently running indefinitely, but thank you though. because i am upscaling a game texture, I just wasted a whole heap of time thinking it needed the in game model the texture it was attached to.
But what about a sequence of images (.exr)? Won't it create artifacts or difference in frames? Or would I have to transform the Sequence into a video and then use ChaiNNer?
Many thanks for the very helpful video and your fantastic resource for comparing the different models! Do you have any suggestions regarding how to compensate for the over-defined sharp edges that can arise when upscaling a photograph? The best models I've tried produce an impressive sharpness and detail, but edges are usually too crisp and harsh, which can give an illustrated or cartoonish quality to the image.
Ah yeah for sure, you can find the model files here: drive.google.com/drive/folders/1iW4EHokEsrcIZ7He5g485kvmPKXGk1EV (the pth is the original trained file, the others are conversions).
hey, i was wondering if you could lend a helping hand. I did the installation step by step as you did, and everything seem to be working just fine. However, when it starts to upscale it never really saves in the chosen directory. It keeps on trying to upscale forever. Do you have any tips on how to fix it? Thanks!
Such a great tool, but everytime I want to use it I can't, and have to wait for it to update python for an hour or three. By ther time it's done i dont' even need it anymore. Am I doing something wrong?
I have error when i try upscale face as in your video.: An error occurred in a Upscale Face node: Failed to run Face Upscale. Input values: • Image: RGBA Image 4096x4096 • Model: Value of type 'nodes.impl.pytorch.architecture.face.codeformer.CodeFormer' • Upscaled Background: None • Output Scale: 1x • Weight: 0.7
![[Live] ศึกมหึมันส์มวยไทยสังเวียนเดือด เวทีมวยชั่วคราวสวนสยาม | จันทร์ 30 กันยายน 2567](http://i.ytimg.com/vi/pM1k6f7JXUc/mqdefault.jpg)
Wow... Outstanding work, congratulations! And thank you very much!
For now (April 2024) Gigapixel AI is still much better in upscaling and face restoring...
I've been looking for these upscale models " 100k [epoch 507, psnr 30.517, ssim 0.83536, lpips 0.031511] or 150k [epoch 760, psnr 31.331, ssim 0.84292, lpips 0.029] " and I can't find them, do you have a link to them?
couldn't get the model to load. just says this node is currently running indefinitely, but thank you though. because i am upscaling a game texture, I just wasted a whole heap of time thinking it needed the in game model the texture it was attached to.
But what about a sequence of images (.exr)? Won't it create artifacts or difference in frames? Or would I have to transform the Sequence into a video and then use ChaiNNer?
Is it weird that is taking so long to upscale a pic?
Wow, great video and resource, thanks so much for your time and effort
A wonderful job, Thank you very much, keep going you are amazing.
Many thanks for the very helpful video and your fantastic resource for comparing the different models! Do you have any suggestions regarding how to compensate for the over-defined sharp edges that can arise when upscaling a photograph? The best models I've tried produce an impressive sharpness and detail, but edges are usually too crisp and harsh, which can give an illustrated or cartoonish quality to the image.
Yes, morons are happy with that. They know only to learn from youtube. That is the reason west will die soon.
züri.jpg :DDDD
Video muito bom, parabens pelo trabalho!
Thanks. For the video upscale I couldn't find your trained model and result looks good. Can you give us a link?
Ah yeah for sure, you can find the model files here: drive.google.com/drive/folders/1iW4EHokEsrcIZ7He5g485kvmPKXGk1EV (the pth is the original trained file, the others are conversions).
This stuff is amazing! Thanks!
very good work, not only about work, also detailed about sources. Could u share your page link too.
hey, i was wondering if you could lend a helping hand. I did the installation step by step as you did, and everything seem to be working just fine. However, when it starts to upscale it never really saves in the chosen directory. It keeps on trying to upscale forever. Do you have any tips on how to fix it? Thanks!
Such a great tool, but everytime I want to use it I can't, and have to wait for it to update python for an hour or three. By ther time it's done i dont' even need it anymore. Am I doing something wrong?
I have error when i try upscale face as in your video.:
An error occurred in a Upscale Face node:
Failed to run Face Upscale.
Input values:
• Image: RGBA Image 4096x4096
• Model: Value of type 'nodes.impl.pytorch.architecture.face.codeformer.CodeFormer'
• Upscaled Background: None
• Output Scale: 1x
• Weight: 0.7
Most like the image is too large, in case anyone checks these comments.
what about how to run it in python or C++?
It runs on Pytorch, check the settings.
I can't find the SwinIR-L model
Thank you so much for your video, So good🙏🙏🙏🙏🙏🙏
As someone not experienced with node programs I really appreciate the detailed directions and pacing. Thank you!!
Thanks so much for all the work you did in putting the model comparison tools together too. That is pure gold!
thanks a lot for all the work and explanations
The update came out today, the program is great!
any info on that
Great stuff. Thank you so much
ha, it worked. thanks a bunch
nice video
sooooo burocratic
First Tutorial that goes over how to use Chainner from scratch. Thanks a lot for a job well done!