OpenArt: Create video transitions with Start and End frames
OpenArtDemo summary
The creator demonstrates how to use the 'Start Frame' and 'End Frame' feature in OpenArt with Google Veo 3.1 and Kling 2.5 to create a seamless transition between two different AI-generated scenes.
Step-by-step
- Generate or download an image to serve as your 'Start Frame'.
- Create and download a second image to serve as your 'End Frame'.
- Navigate to the Video section and select Image to Video.
- Select a model that supports start and end frames, such as Google Veo 3.1 or Kling 2.5.
- Upload your first image into the Start Frame slot.
- Upload your second image into the End Frame slot.
- Enter a simple prompt describing the transition between the two scenes.
- Click generate to create the video transition.
Options
- Use Google Veo 3.1
- Use Kling 2.5
- Use Luma Dream Machine (1 2.5)
Watch out for
- Not every video model supports the Start and End frame feature (e.g., Sora 2 does not have it).
- Luma 1.2.5 may not always end precisely on the provided end frame.
Tips
- Keep your transition prompts simple as it often works better for video generation.
- If the first result isn't perfect, try regenerating with the same settings to get a better result.
- Ensure your aspect ratio (e.g., widescreen) matches across your generated images and video settings.
Highlights
“that transition is sick”
All demos from “How to Start Making AI Videos in 2026”
- 5:060:57Generate AI image from PDF prompt in OpenArtThe creator demonstrates how to upload a PDF to ChatGPT to extract a prompt and then pastes it into OpenArt using the Nano Banana Pro model to generate a 4K image of a person on the moon.OpenArt· Text to Image
- 8:291:01Image-to-image generation with Seedream 4.5The creator uses a personal photo as a reference in OpenArt to generate a cinematic movie character floating in a bubble using the Seedream 4.5 model.OpenArt· Image to Image
- 15:322:48Create video transitions with Start and End framesCurrentThe creator demonstrates how to use the 'Start Frame' and 'End Frame' feature in OpenArt with Google Veo 3.1 and Kling 2.5 to create a seamless transition between two different AI-generated scenes.OpenArt· Image to Video
- Watch “How to Start Making AI Videos in 2026” →
Image to Video
7:141:34Animate images using Kling 2.5 in OpenArtThe creator demonstrates converting static images into video clips using the Kling 2.5 model within the OpenArt platform.Roboverse
5:460:18Animate static portraits with Kling 2.6The creator uses an image of a grandmother with cookies as a base for Kling 2.6 to animate a winking smile and camera interaction.Youri van Hofwegen- 8:070:40Image-to-video scene creation with Wan 2.6The user demonstrates animating a retro-futuristic diner image by adding a UFO fly-by using Wan 2.6.Youri van Hofwegen
- 11:270:31Start-to-end frame interpolation with SeaDance 1.5 ProA demonstration of providing both a starting and ending image to SeaDance 1.5 Pro to control a specific dance sequence.Youri van Hofwegen
- 14:230:36Room transition generation with Google Veo 3.1The creator uses a messy office start frame and a clean studio end frame to have Google Veo 3.1 generate a smooth room transformation transition.Youri van Hofwegen
- 15:322:48Create video transitions with Start and End framesCurrentThe creator demonstrates how to use the 'Start Frame' and 'End Frame' feature in OpenArt with Google Veo 3.1 and Kling 2.5 to create a seamless transition between two different AI-generated scenes.Dan Kieft
6:000:30Image-to-video generation with Google Veo 3The creator demonstrates uploading a high-quality image of a samurai into OpenArt and using it as a starting frame for a Google Veo 3 video generation.Roboverse
16:311:23Animate AI influencer with Kling V1.5 (V3)The user demonstrates converting a still image into a realistic video of the character waving and drinking from a cup using the V3 (Kling) model.Roboverse
4:581:08Image-to-video animation in OpenArtThe demonstration shows converting a static cyberpunk image into a video by adding motion prompts for flickering lights and camera movement using the Kling model.Thomas Creates
3:481:24Create video from multiple image referencesThe creator uses OpenArt's image generator to create three distinct assets (a woman, a statue, and a park) and then uses the 'elements' feature in Veo 3.1 to combine them into a single coherent video scene.Roboverse- 5:531:42Animate a brand logo using a starting frameThe video shows how to upload a generated image of an infinity logo as a starting frame and use a motion prompt to animate people moving within that specific shape while maintaining visual consistency.Roboverse
4:400:42Create fight scene from image with Wan 2.6The user uploads a Tekken 8 reference image and uses Wan 2.6 to animate a cinematic fight scene between two characters.Ai Chemy