Everlyn-Labs/Everlyn-1

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

2892 stars · 486 forks observed · 2026-08-28

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

Everlyn-1 is an open autoregressive foundational video AI model from Everlyn Labs, accompanied by research on video compression/tokenization (Wasserstein-based vector quantization), efficient autoregressive image/video generation (EfficientARV), and hallucination reduction for multimodal LLMs (ANTRP/TAME). It targets generative video tasks such as animation, inpainting, outpainting, prediction, and interpolation.

Use cases

• generate videos from text or images with an open autoregressive model
• animate a still image into a video
• inpaint or outpaint missing regions in video frames
• predict future video frames or interpolate between frames
• tokenize and compress video for autoregressive generation
• reduce hallucinated objects in multimodal LLM outputs
• research efficient autoregressive video generation architectures

When to choose

• you need an open foundational video generation model you can study or fine-tune
• you are researching vector quantization or video tokenization for autoregressive models
• you want to experiment with joint image and video generation tasks
• you are working on hallucination mitigation in multimodal LLMs

When to avoid

• you need a polished production video-generation service with a stable API
• you require a permissive license for commercial use - no license is specified
• you lack GPU resources for training or running large generative models
• you need a turnkey text-to-video tool rather than research code

Facets

library · maturity experimental

machine-learning deep-learning llm-training video-processing image-processing nlp artificial-intelligence deep-learning large-language-models image-processing python video-generation autoregressive-model vector-quantization video-tokenization multimodal hallucination-reduction research-model video-prediction video-interpolation inpainting wasserstein-vq efficientarv antrp tame video natural-language-processing gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Everlyn-Labs/Everlyn-1")