Shypd.aiThe largest open index of AI toolsAllegro is an open-source text-to-video model that generates high-quality videos up to 6 seconds at 15 FPS and 720p resolution from simple text input. It also offers a text-image-to-video variant.
Trending
About
Allegro is a powerful open-source text-to-video model capable of generating high-quality videos up to 6 seconds in length, at 15 frames per second (FPS) and 720p resolution, directly from text input. A variant, Allegro-TI2V, extends this functionality by allowing users to generate videos using text prompts combined with first-frame and optional last-frame image inputs. The project provides full code for inference, training, and fine-tuning, making it suitable for researchers and developers. It supports multi-card inference for faster processing and offers options for CPU offload to manage GPU memory usage. Allegro is integrated into Hugging Face's diffusers library, ensuring accessibility and ease of use for those familiar with the ecosystem.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
