NVlabs/imaginaire

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

4082 stars · 446 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

NVIDIA's PyTorch library containing optimized implementations of image and video synthesis methods, including GAN-based image-to-image translation models like pix2pixHD, SPADE, UNIT, MUNIT, and FUNIT. It provides tutorials and a model zoo for training and running these generative models.

Use cases

• translate semantic label maps into photorealistic images
• train pix2pixHD or SPADE for high-resolution image synthesis
• perform unsupervised image-to-image translation between domains
• generate images in unseen styles with few-shot learning
• reproduce NVIDIA GAN research papers in PyTorch
• run image and video synthesis models on GPUs

When to choose

• you want reference PyTorch implementations of NVIDIA's GAN translation models
• you need high-resolution image-to-image translation with semantic layouts
• you are doing research on image or video synthesis

When to avoid

• you need a general-purpose computer vision toolkit rather than generative synthesis models
• you require a permissive open-source license for commercial use
• you need actively maintained code with recent updates

Facets

library · maturity maintenance

machine-learning image-processing video-processing deep-learning deep-learning computer-vision image-processing machine-learning python pytorch gan image-to-image-translation video-synthesis generative-models nvidia gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="NVlabs/imaginaire")