This is the Windows 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 any OS OnWorks online emulator from this website, but better Windows online emulator.
- 5. From the OnWorks Windows 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 and install it.
- 7. Download Wine from your Linux distributions software repositories. Once installed, you can then double-click the app to run them with Wine. You can also try PlayOnLinux, a fancy interface over Wine that will help you install popular Windows programs and games.
Wine is a way to run Windows software on Linux, but with no Windows required. Wine is an open-source Windows compatibility layer that can run Windows programs directly on any Linux desktop. Essentially, Wine is trying to re-implement enough of Windows from scratch so that it can run all those Windows applications without actually needing Windows.
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.
