A Real-ESRGAN equipped Colab notebook for CLIP Guided Diffusion

Overview

#360Diffusion automatically upscales your CLIP Guided Diffusion outputs using Real-ESRGAN.

Latest Update: Alpha 1.61 [Main Branch] - 01/11/22

Note that 4096 files aren’t quite as pretty as 2048, and they’re massive in file size. 2048 is appealing in most cases. If you intend on upscaling to anything higher than 1024, I recommend using the 512 diffusion model found in the settings-

Credits & Acknowledgements

Prior release(s): Implemented Daniel Russ’s Perlin revisions, fixed init_bug, 4096 double-pass, VRAM fixes, practical debug_mode (set to higher skip_timestep)

All edits & feedback are welcome and appreciated~

Issues
  • Two errors in notebook

    Two errors in notebook

    Running the notebook as-is on colab pro, I get the following errors:

    Current upscale target is /content/drive/MyDrive/MyName/Diffusion/existential/existentialbatch0000_iteration0021_output0000_211217-112807_637275_out.png next_outscale is 2 usage: inference_realesrgan.py [-h] [-i INPUT] [-n MODEL_NAME] [-o OUTPUT] [-s OUTSCALE] [--suffix SUFFIX] [-t TILE] [--tile_pad TILE_PAD] [--pre_pad PRE_PAD] [--face_enhance] [--half] [--alpha_upsampler ALPHA_UPSAMPLER] [--ext EXT] inference_realesrgan.py: error: unrecognized arguments: --model_path /content/Real-ESRGAN/experiments/pretrained_models/RealESRGAN_x4plus.pth

    ERROR: CAN'T FIND UPSCALED FILE /content/drive/MyDrive/MyName/Diffusion/existential/existentialbatch0000_iteration0021_output0000_211217-112807_637275_out.png

    bug 
    opened by Ali762 3
  • 2022 Critical Fixes Tracking

    2022 Critical Fixes Tracking

    Critical tasks

    • [x] Revise depcrecated real-esrgan param 'model_path' (Referenced in #3)
    • [x] Update links if necessary - see this for reference
    • [ ] Revise project to point to direct to self-forked repos (longevity)
    documentation 
    opened by sadnow 1
  • Updated params for inference_realesrgan.py

    Updated params for inference_realesrgan.py

    The upscaler (inference_realesrgan.py) now uses a different param for the upscaling model (--model_name , just a name, instead of --model_path, the path to the pth file). I've updated the code to reflect this: without this fix, the colab can not upscale and save the generated image.

    opened by juanalonso 0
  • not really a issue more a question about seeds

    not really a issue more a question about seeds

    at the moment the seeds change per batch which is great if you have one initial image , is there a way to disable that so it does one seed throughout the whole batch run. The reason I ask is , at the moment I change my initial image per batch number ,so batch 0 / initial_img000.png || batch 1 initial_img_001.png and so on. I would love to have the seed consistant through the batch run so only the initial image changes for me.

    I hope this makes sense somehow haha.

    Thank you so much for your work!

    documentation question 
    opened by UglyStupidHonest 2
Owner
I have twisted and crawled and churned through the absurd in search of the truth but alas, this is all just paper flying in our faces.
null
Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data

Real-ESRGAN Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data Ported from https://github.com/xinntao/Real-ESRGAN Depend

Holy Wu 27 Jun 19, 2022
A Jupyter notebook to play with NVIDIA's StyleGAN3 and OpenAI's CLIP for a text-based guided image generation.

A Jupyter notebook to play with NVIDIA's StyleGAN3 and OpenAI's CLIP for a text-based guided image generation.

Eugenio Herrera 154 Jun 13, 2022
Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration.

Real-ESRGAN Colab Demo for Real-ESRGAN . Portable Windows executable file. You can find more information here. Real-ESRGAN aims at developing Practica

Xintao 12k Jun 30, 2022
PyTorch implementation of a Real-ESRGAN model trained on custom dataset

Real-ESRGAN PyTorch implementation of a Real-ESRGAN model trained on custom dataset. This model shows better results on faces compared to the original

Sber AI 85 Jun 29, 2022
My usage of Real-ESRGAN to upscale anime, some test and results in the test_img folder

anime upscaler My usage of Real-ESRGAN to upscale anime, I hope to use this on a proper GPU cuz doing this on CPU is completely shit ?? , I even tried

Shangar Muhunthan 11 Jun 7, 2022
Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.

Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.

Nerdy Rodent 2k Jul 2, 2022
Traditional deepdream with VQGAN+CLIP and optical flow. Ready to use in Google Colab

VQGAN-CLIP-Video cat.mp4 policeman.mp4 schoolboy.mp4 forsenBOG.mp4

null 22 May 19, 2022
Minimal diffusion models - Minimal code and simple experiments to play with Denoising Diffusion Probabilistic Models (DDPMs)

Minimal code and simple experiments to play with Denoising Diffusion Probabilist

Rithesh Kumar 15 May 25, 2022
Pytorch-diffusion - A basic PyTorch implementation of 'Denoising Diffusion Probabilistic Models'

PyTorch implementation of 'Denoising Diffusion Probabilistic Models' This reposi

Arthur Juliani 42 Jun 21, 2022
FuseDream: Training-Free Text-to-Image Generationwith Improved CLIP+GAN Space OptimizationFuseDream: Training-Free Text-to-Image Generationwith Improved CLIP+GAN Space Optimization

FuseDream This repo contains code for our paper (paper link): FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimizat

XCL 178 Jun 16, 2022
CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP

CLIP-GEN [简体中文][English] 本项目在萤火二号集群上用 PyTorch 实现了论文 《CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP》。 CLIP-GEN 是一个 Language-F

null 40 Jun 28, 2022
Official codebase for running the small, filtered-data GLIDE model from GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models.

GLIDE This is the official codebase for running the small, filtered-data GLIDE model from GLIDE: Towards Photorealistic Image Generation and Editing w

OpenAI 2.5k Jun 29, 2022
Generating images from caption and vice versa via CLIP-Guided Generative Latent Space Search

CLIP-GLaSS Repository for the paper Generating images from caption and vice versa via CLIP-Guided Generative Latent Space Search An in-browser demo is

Federico Galatolo 168 Jul 1, 2022
Code for 'Self-Guided and Cross-Guided Learning for Few-shot segmentation. (CVPR' 2021)'

SCL Introduction Code for 'Self-Guided and Cross-Guided Learning for Few-shot segmentation. (CVPR' 2021)' We evaluated our approach using two baseline

null 32 Apr 15, 2022
Try out deep learning models online on Google Colab

Try out deep learning models online on Google Colab

Erdene-Ochir Tuguldur 1.4k Jul 1, 2022
Monitor your ML jobs on mobile devices📱, especially for Google Colab / Kaggle

TF Watcher TF Watcher is a simple to use Python package and web app which allows you to monitor ?? your Machine Learning training or testing process o

Rishit Dagli 50 Jun 14, 2022
S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration (CVPR 2021)

S2-BNN (Self-supervised Binary Neural Networks Using Distillation Loss) This is the official pytorch implementation of our paper: "S2-BNN: Bridging th

Zhiqiang Shen 47 Jun 12, 2022
Code for "Diffusion is All You Need for Learning on Surfaces"

Source code for "Diffusion is All You Need for Learning on Surfaces", by Nicholas Sharp Souhaib Attaiki Keenan Crane Maks Ovsjanikov NOTE: the linked

Nick Sharp 188 Jun 24, 2022