4 repository-uri
Synthesizing data based on learned distributions without external conditioning signals.
Distinct from Image Generation: Distinct from general Image Generation as it explicitly excludes text or label guidance
Explore 4 awesome GitHub repositories matching artificial intelligence & ml · Unconditional Generation. Refine with filters or upvote what's useful.
This is a PyTorch-based implementation of diffusion models for synthesizing photorealistic images and video. It provides a framework for text-to-image and text-to-video generation, as well as unconditional image synthesis. The system utilizes a cascading diffusion pipeline to produce high-resolution imagery by passing low-resolution outputs through a sequence of super-resolution models. It also includes capabilities for image inpainting, allowing the reconstruction of masked or missing regions of visual media guided by surrounding context and text prompts. The project includes tools for diff
Creates images without text guidance by relying on the learned distribution of training data.
mmagic is a multimodal training pipeline and framework for generative AI, focusing on visual synthesis and restoration. It provides the infrastructure to build and train models for tasks such as text-to-image and text-to-video generation, 3D-aware content synthesis, and high-fidelity image translation using diffusion models and generative adversarial networks. The project distinguishes itself through specialized capabilities for generative model personalization, including techniques for fine-tuning subjects and styles. It also supports advanced visual manipulations such as latent space interp
Creates realistic images from random noise using various Generative Adversarial Network architectures.
This is a classifier-guided diffusion framework for high-fidelity image generation. It implements a cascaded diffusion pipeline that chains a base diffusion model with a dedicated upsampler to progressively increase image resolution in stages, and uses classifier-guided diffusion sampling to steer the reverse diffusion process toward higher-quality outputs. The framework provides tools for training diffusion models from scratch using distributed processes with gradient accumulation, as well as training classifier models that provide gradient-based guidance during sampling. It supports both un
Generates images from a diffusion model that does not require class labels or a classifier.
Acest proiect este un framework de deep learning pentru super-rezoluția imaginilor AI și sinteza facială. Acesta oferă un upscaler de imagini bazat pe model de difuzie și un sintetizator generativ de imagini faciale capabil să transforme imaginile de rezoluție joasă în output-uri de înaltă rezoluție folosind ponderi de model pre-antrenate. Sistemul utilizează rafinarea iterativă prin difuzie și eșantionarea ghidată de rezoluție joasă pentru a restabili detaliile fine și claritatea. Suportă atât generarea necondiționată de imagini, unde imaginile sunt create de la zero, cât și îmbunătățirea ghidată a rezoluției pentru reconstrucția facială de înaltă fidelitate. Repository-ul include un pipeline de antrenare a modelului de difuzie cu antrenare distribuită multi-GPU și inițializarea ponderilor pre-antrenate. Acest mediu este susținut de urmărirea experimentelor modelului, logarea metricilor externe și reluarea modelului bazată pe checkpoint-uri.
Generates new images from scratch based on learned distributions without external guidance.