This is the Linux app named Guided Diffusion whose latest release can be downloaded as guided-diffusionsourcecode.tar.gz. It can be run online in the free hosting provider OnWorks for workstations.
Download and run online this app named Guided Diffusion with OnWorks for free.
Follow these instructions in order to run this app:
- 1. Downloaded this application in your PC.
- 2. Enter in our file manager https://www.onworks.net/myfiles.php?username=XXXXX with the username that you want.
- 3. Upload this application in such filemanager.
- 4. Start the OnWorks Linux online or Windows online emulator or MACOS online emulator from this website.
- 5. From the OnWorks Linux OS you have just started, goto our file manager https://www.onworks.net/myfiles.php?username=XXXXX with the username that you want.
- 6. Download the application, install it and run it.
SCREENSHOTS
Ad
Guided Diffusion
DESCRIPTION
The guided-diffusion repository is centered on diffusion models for image synthesis, with a focus on classifier guidance and improvements over earlier diffusion frameworks. It is derived from OpenAI’s improved-diffusion work, enhanced to include guided generation where a classifier (or other guidance mechanism) can steer sampling toward desired classes or attributes. The code provides model definitions (UNet, diffusion schedules), sampling and training scripts, and utilities for guidance and evaluation. A key insight is that combining diffusion sampling with classifier gradients allows fine control over the generated images, trading off diversity vs fidelity. The repository includes scripts such as image_train.py, image_sample.py, and classifier_train.py to train diffusion models, generate samples, and train guiding classifiers. It also ships with precomputed evaluation batches and baseline comparisons to support reproducible benchmarking of new models.
Features
- Diffusion model architecture (UNet, noise schedules, training utilities)
- Classifier-guided sampling: combining diffusion with classifier gradients
- Scripts for training models (image_train.py), sampling (image_sample.py), and classifier training
- Precomputed evaluation batches and baseline metrics for reproducibility
- Modular code enabling new guidance modalities or architectural tweaks
- Branching from improved-diffusion with enhancements in guided generation
Programming Language
Python
Categories
This is an application that can also be fetched from https://sourceforge.net/projects/guided-diffusion.mirror/. It has been hosted in OnWorks in order to be run online in an easiest way from one of our free Operative Systems.
