Discover amazing ML apps made by the community.
Pyramid Flow is a training-efficient autoregressive video generation model based on Flow Matching, presented as Pyramidal Flow Matching for Efficient Video Generative Modeling. It was trained only on open-source datasets within 20.7k A100 GPU hours. The project page shows text-to-video generation at 1280x768 in 10-second and 5-second, 24fps clips, plus text-conditioned image-to-video.
Creates, edits or enhances video and animation with generative models.
A research project on high-resolution video synthesis with latent diffusion models. It pre-trains an image latent diffusion model, then adds a temporal dimension and fine-tunes on encoded image sequences to produce video. Applications include simulation of in-the-wild driving data and text-to-video creative content creation. Updaters are temporally aligned into video super-resolution models.
Sisif renders short AI videos from text prompts. It charges $1 per 5-second clip with no subscription, and the site says credits never expire. Clips carry no watermark, and the service offers portrait video plus a REST API with pay-per-call support for agents.
Creates, edits or enhances video and animation with generative models.
Gemini Omni Prompts is an independent, unofficial library of prompts for Gemini Omni, a multimodal generative model launched at Google I/O 2026. Prompts are adapted from official documentation and community testing, with cited sources and live video tests; the site states it is not affiliated with Google.
Community notes
Be the first to share how this project worked for you.
Sign in with a verified account to leave a review or join the discussion.
Sign in to reviewKeep exploring
Pyramid Flow is a training-efficient autoregressive video generation model based on Flow Matching, presented as Pyramidal Flow Matching for Efficient Video Generative Modeling. It was trained only on open-source datasets within 20.7k A100 GPU hours. The project page shows text-to-video generation at 1280x768 in 10-second and 5-second, 24fps clips, plus text-conditioned image-to-video.
Creates, edits or enhances video and animation with generative models.
A research project on high-resolution video synthesis with latent diffusion models. It pre-trains an image latent diffusion model, then adds a temporal dimension and fine-tunes on encoded image sequences to produce video. Applications include simulation of in-the-wild driving data and text-to-video creative content creation. Updaters are temporally aligned into video super-resolution models.
Sisif renders short AI videos from text prompts. It charges $1 per 5-second clip with no subscription, and the site says credits never expire. Clips carry no watermark, and the service offers portrait video plus a REST API with pay-per-call support for agents.
Creates, edits or enhances video and animation with generative models.
Gemini Omni Prompts is an independent, unofficial library of prompts for Gemini Omni, a multimodal generative model launched at Google I/O 2026. Prompts are adapted from official documentation and community testing, with cited sources and live video tests; the site states it is not affiliated with Google.
