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.
Suivez ces instructions pour exécuter cette application :
- 1. Téléchargé cette application sur votre PC.
- 2. Entrez dans notre gestionnaire de fichiers https://www.onworks.net/myfiles.php?username=XXXXX avec le nom d'utilisateur que vous voulez.
- 3. Téléchargez cette application dans ce gestionnaire de fichiers.
- 4. Démarrez l'émulateur en ligne OnWorks Linux ou Windows en ligne ou l'émulateur en ligne MACOS à partir de ce site Web.
- 5. Depuis le système d'exploitation OnWorks Linux que vous venez de démarrer, accédez à notre gestionnaire de fichiers https://www.onworks.net/myfiles.php?username=XXXXX avec le nom d'utilisateur que vous souhaitez.
- 6. Téléchargez l'application, installez-la et exécutez-la.
CAPTURES D'ÉCRAN
Ad
Diffusion guidée
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.
Caractéristiques
- 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
Langage de programmation
Python
Catégories
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.
