First and Last Frame Video
Define the beginning and the end—let AI create the journey. This advanced generation mode allows you to upload a First Frame (Start) and a Last Frame (End). The AI analyzes both inputs and generates a coherent, physics-aware video clip that seamlessly bridges the two images. Perfect for morphing, storytelling, and controlled object manipulation.
Models with Keyframe Support
Not all models support dual-image input. WaveSpeed aggregates the best models that offer precise start and end frame conditioning.
1. Kling 1.6 (Keyframe Control)
High-Fidelity Interpolation2. Luma Dream Machine (Bridge Mode)
Creative MorphingFamous for its "Keyframe" feature, Luma generates highly creative transitions. It is particularly strong at morphing one object into another or changing the time of day smoothly. Best for product transitions, surreal effects, day-to-night sequences. Explore more open-source video models.
3. Wan 2.1 (Interpolation)
Video Extension & FillingWan 2.1 offers robust "in-betweening" capabilities, ensuring that the lighting and texture of the generated middle frames match both the start and end inputs perfectly. Best for realistic scenery changes, slow-motion gap filling. Also see Video Edit for post-production refinement.
The Generation Process
Achieve total control in four steps.
1
Upload Start Image
This will be frame 0 of your video. Choose a clear, high-resolution image that represents the beginning state.
2
Upload End Image
This will be the final frame (e.g., frame 120). For realistic results, ensure it is logically connected to the start image.
3
Add Prompt
Describe what happens in the middle (e.g., "The car drives forward," "The flower blooms," "The camera zooms out"). This guides the AI on how to connect the images.
4
Generate
The API processes the inputs and returns a video file that mathematically and visually connects your two keyframes. Available on WaveSpeed.
Q & A
What is First and Last Frame Video generation?
It is a video generation technique where the user provides both the starting image and the ending image. The AI's job is to generate the intermediate frames (interpolation) to create a video that starts exactly at image A and ends exactly at image B.
Why is this better than standard Image-to-Video?
Standard Image-to-Video only lets you control the start. The ending is unpredictable. First and Last Frame gives you "Goal-Oriented" control, ensuring the video ends exactly where you want it to, which is crucial for storytelling and editing.
Can the images be completely different?
Yes, but the result will be a "morph" or a surreal transition. For realistic video, the two images should be logically connected (e.g., same character in different poses, or same room with different lighting).
How long can the transition be?
Most models support 5 to 10 seconds of generation between frames. For longer sequences, you would generate multiple "bridges" (A to B, then B to C) and stitch them together.
Does the text prompt still matter?
Yes. The text prompt tells the AI the context of the change. If you have a Start Frame of a man standing and an End Frame of him sitting, the prompt "The man sits down slowly" helps the AI generate the correct motion.