PopNow
Multimodel image, video and audio studio with API and paid credit packs without a subscription; operation costs, capabilities and rights vary by model.

Text-to-video playground with limited monthly free credits and paid plans, plus the separately available open-source Mochi model.
Genmo develops video models and offers a web playground for generating clips from text descriptions. Its open-source Mochi model can also be run and customized separately from the hosted service.
Creators can explore a short scene or motion concept, while researchers can investigate an open video model. Generated motion is not guaranteed physical simulation or evidence of a real event.
Create an account, describe the scene and movement, review the output and download clips you want to keep. The official FAQ currently describes text-to-video and lists image input as forthcoming, so image animation should not be presented as available. Local model use requires suitable computing resources and technical setup.
The free plan includes limited monthly fuel, with paid plans providing additional credits and features. Do not rely on the old daily-credit claim. Check current plan and usage terms before committing, and distinguish the Mochi code release from hosted-service allowances.
Multimodel image, video and audio studio with API and paid credit packs without a subscription; operation costs, capabilities and rights vary by model.
Text to Video generates clips and images from prompts or supported inputs using multiple models. Paid credit-based plans include starter access; costs, length, quality and conditions depend on model and settings.
Two-photo AI video generator using a preset zombie story; registration is free but generation is paid, with identity, rights and output checks required.