In research for the AI Walk & Create we looked for tools to generate videos from images. Inspired by Animate the Met by Machine Cinema, watch this video to get an idea of what we want to accomplish. The major problem we ran into were country restrictions, as not all apps are available in the EU.
Here are two platforms, that seem to support multiple models and seem to work in every country:
- Freepik: Supports multiple models. Has a free plan (almost no credits) and paid plans start at €10/month. Cheaper plans when bought through website.
- Higgsfield: Platform that supports muliple models. Didn't find an iPhone-app.
Apps:
- Kling AI: Known for highly realistic human motion and physics. Registration only with Google or Apple possible, even when going through their website.
- Hailuo AI / Wan: Text and image into video generator
- OpenAI Sora 2: Their app is as of early 2026 not available in the EU but the model - for exmaple on Freepik.
- Google Flow: AI creative studio by Google with a solid free plan, using Veo as the model for video creation.
- Seedance2 App supports its core model Seedance best, but has also Kling, Sora, Grok & Veo available (as well as Nano Banano & Seedream for imgage generation)
Models & dedicated apps:
- Google Veo 3 Google’s latest high-end cinematic video model.
- Sora 2
- PixVerse V5
- Kling AI
- Hailuo
- Seedance 2, a text-to-video model created by ByteDance in 2025 used for realistic clips.
- Wan
- Genmo/Mochi
- LTX-Video
- Marey
How to use them?
- Generate start and end frame in an image generator or in real life and let the AI transition from one to another
- describe what the image should contain.
Apps that will disappear:
