Skip to content

Thank you :) Wanted to show you my SRFormer_light model :) #10

Closed

Description

@Phhofm

Thank you for this network :)
I just wanted to show real quick that I have trained a (4x) SRFormer_light model for anime super-resolution with real degradation (compression, noise, blur), and created visual outputs which can be compared to a SwinIR_light (=small) model I have trained on the same dataset with the same config (so same losses, gt_size, batch size, both from scratch meaning no pretrain). Just one visual comparison (more outputs in the link below) of Input, SwinIR_light and SRFormer_light:

grafik

More visual outputs can be found here and the trained SRFormer_light model file can be found here

Activity

  1. changed the title [-]Self-trained model[/-] [+]Thank you :) Wanted to show you my SRFormer_light model :)[/+] on Jun 13, 2023
  2. Z-YuPeng commented on Jun 14, 2023

    @Z-YuPeng
    Collaborator

    Greatful! The model you trained demonstrates the performance of SRFormer in anime SR. I want to express my sincere gratitude for your work.

  3. Phhofm commented on Jun 30, 2023

    @Phhofm
    Author

    PS I think SRFormer is impressive and its results are growing on me. I trained/finetuned another model (not lightweight but an SRFormer base model) and I think the results are very good even when compared with HAT-L (which is a bigger and slower arch/model, trained with the same config). It is trained with otf jpg compression and blur. Here are results compared with Real-ESRGAN (RRDBNet) and HAT-S and HAT-L

    https://imgsli.com/MTg5MDY3/0/3
    https://imgsli.com/MTg5MDYy/0/3
    https://imgsli.com/MTg5MDY1/0/3

    The model files (pth and onnx conversions in the onnx folder) with training info can be found here

    seeufer
    bibli
    dearalice

  4. Z-YuPeng commented on Jul 20, 2023

    @Z-YuPeng
    Collaborator

    SRFormer is accepted by ICCV 2023, We will enrich our repo recently and provide more demos, and we will add a link in our repo about the third-party model you trained so that people can learn more about SRFormer!

  5. Feynman1999 commented on Jul 25, 2023

    @Feynman1999
    Contributor

    PS I think SRFormer is impressive and its results are growing on me. I trained/finetuned another model (not lightweight but an SRFormer base model) and I think the results are very good even when compared with HAT-L (which is a bigger and slower arch/model, trained with the same config). It is trained with otf jpg compression and blur. Here are results compared with Real-ESRGAN (RRDBNet) and HAT-S and HAT-L

    https://imgsli.com/MTg5MDY3/0/3 https://imgsli.com/MTg5MDYy/0/3 https://imgsli.com/MTg5MDY1/0/3

    The model files (pth and onnx conversions in the onnx folder) with training info can be found here

    seeufer bibli dearalice

    excelent work! can you share some info about your training dataset? that's helpful to me !

  6. terrainer commented on Jul 29, 2023

    @terrainer

    PS I think SRFormer is impressive and its results are growing on me. I trained/finetuned another model (not lightweight but an SRFormer base model) and I think the results are very good even when compared with HAT-L (which is a bigger and slower arch/model, trained with the same config). It is trained with otf jpg compression and blur. Here are results compared with Real-ESRGAN (RRDBNet) and HAT-S and HAT-L
    https://imgsli.com/MTg5MDY3/0/3 https://imgsli.com/MTg5MDYy/0/3 https://imgsli.com/MTg5MDY1/0/3
    The model files (pth and onnx conversions in the onnx folder) with training info can be found here
    seeufer bibli dearalice

    excelent work! can you share some info about your training dataset? that's helpful to me !

    The dataset used for the anime pretrain is HFA2K_LUDVAE, available in the #dataset-releases channel of the Enhance Everything! Discord server.

    The realistic dataset is Nomos8K, also in that Discord server.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions