FM_nodes

A collection of ComfyUI nodes.

Click name to jump to workflow

1. WFEN Face Restore. Paper: Efficient Face Super-Resolution via Wavelet-based Feature Enhancement Network
2. RealViformer - Paper: Investigating Attention for Real-World Video Super-Resolution
3. ProPIH. Paper: Progressive Painterly Image Harmonization from Low-level Styles to High-level Styles
4. CoLIE. Paper: Fast Context-Based Low-Light Image Enhancement via Neural Implicit Representations
5. VFIMamba. Paper: Video Frame Interpolation with State Space Models
6. ConvIR Revitalizing Convolutional Network for Image Restoration

Workflows

WFEN

Download the model here and place it in models/wfen/WFEN.pth.

workflow_wfen_facecrop.json

RealViformer

Download the model here and place it in models/realviformer/weights.pth.

workflow_realviformer.json

(Not a workflow-embedded image)

https://github.com/user-attachments/assets/e89003c0-7be5-4263-b281-fd609807cea1

RealViFormer upscale example

ProPIH

Download the vgg_normalised.pth model in the Installation section and latest_net_G.pth in the Train/Test section

models/propih/vgg_normalised.pth
models/propih/latest_net_G.pth

workflow_propih.json

CoLIE

No model needed to be downloaded. Lower loss_mean seems to result in brighter images. Node works with image and batched/video.

workflow_colie_lowlight.json

VFIMamba

Download the models from the huggingface page

models/vfimamba/VFIMamba_S.pkl
models/vfimamba/VFIMamba.pkl

You will need to install mamba-ssm, which does not have a prebuilt Windows binary. You will need:

1. triton. Prebuilt for Python 3.10 and 3.11 can be found here: https://github.com/triton-lang/triton/issues/2881 - https://huggingface.co/madbuda/triton-windows-builds/tree/main
2. causal-conv1d. Follow this post: https://github.com/NVlabs/MambaVision/issues/14#issuecomment-2232581078
3. mamba-ssm. Follow this tutorial: https://blog.csdn.net/yyywxk/article/details/140420538. Fork that followed all the steps: https://github.com/FuouM/mamba-windows-build

I've built mamba-ssm for Python 3.11, torch 2.3.0+cu121, which can be obtained here: https://huggingface.co/FuouM/mamba-ssm-windows-builds/tree/main

To install, pip install [].whl

workflow_vfi_mamba.json

(Not a workflow-embedded image)

https://github.com/user-attachments/assets/be263cc3-a104-4262-899b-242e9802719e

VFIMamba Example (top: Original, bottom: 5X, 20FPS)

ConvIR