Bring a still image to life with AI-powered animation. Set a first frame — and optionally a last frame — and LTX-2.5 fills in the motion and the matching soundtrack.
The white horse tosses its head and walks forward through the meadow, its long mane lifting and settling with each stride. Morning mist parts around its legs and drifts across the frame. The low sun flares softly through…The white horse tosses its head and walks forward through the meadow, its long mane lifting and settling with each stride. Morning mist parts around its legs and drifts across the frame. The low sun flares softly through the haze as the camera drifts back to keep pace. Grass ripples in a light breeze. Hooves thud softly on damp earth, birds call in the distance, and wind moves through the grass.
Kling 4.0
External
External models are models provided by external partners. They may have different limits and processing times.
Animate a still image into a video with sound. The image sets the framing and style, the prompt describes the motion and audio, and an optional last frame decides where the shot ends.
The storm slowly passes: the waves calm down, the clouds part and night falls while the lighthouse beam starts to sweep across the sea. Slow push in. Wind fading to the sound of calm water.The storm slowly passes: the waves calm down, the clouds part and night falls while the lighthouse beam starts to sweep across the sea. Slow push in. Wind fading to the sound of calm water.
Seedance 2.5
External
External models are models provided by external partners. They may have different limits and processing times.
Animate a still image into a video with sound. The image sets the framing and style, the prompt describes the motion and audio, and an optional last frame fixes where the shot ends.
Huge waves crash against the rocks and spray over the base of the lighthouse while its beam begins to sweep across the sea. The camera slowly pushes in. Roaring surf, howling wind and a distant foghorn.Huge waves crash against the rocks and spray over the base of the lighthouse while its beam begins to sweep across the sea. The camera slowly pushes in. Roaring surf, howling wind and a distant foghorn.
MiniMax H3 33B Turbo INT8
New
768p at 24 fps. 96–360 frames (4–15 sec). One image as first or last frame, or two for first-and-last-frame control. Aspect ratio inherited from the input image. Native 32 kHz stereo audio.
For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.
integrated_multimodal_description: [Shot 1] Live-action, cinematic, a low handheld medium shot preserves th…For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.
integrated_multimodal_description: [Shot 1] Live-action, cinematic, a low handheld medium shot preserves the blond young child's identity, white short-sleeved T-shirt, blue shorts, centered position, and the tall sunlit field established in <Picture 1>. Warm dawn backlight outlines the child's hair as the camera tracks backward at a lively pace, maintaining the frontal composition while the child runs toward it along the narrow path. The child's steps quicken, both arms gradually spread wide, and an open-mouthed laugh continues as grass heads brush against the child's legs. The child bends both knees, springs forward over a dense tuft of grass with arms fully outstretched, then lands and keeps running toward the retreating camera. Tall grass sways in the breeze around the path, drifting clouds move slowly across the pale blue sky, and the rising sun remains low behind the child, casting long golden highlights across the field. Gentle handheld movement responds naturally to each stride without losing the child's face or clothing details.
overall_soundscape: Quick footfalls press through grass beneath the child's bright laughter and light breathing. Tall stems rustle and brush against clothing while a gentle breeze moves across the open field, with a soft thump as the child lands from the jump.
non_diegetic_music: N/A
LTX-2.3 22B
Up to 1024×1024 resolution. 49–241 frames at 24 fps (2–10 sec). First-frame and last-frame conditioning. Single-step distilled inference (INT8). Audio generation included.
A professional young man speaking directly to the camera in a studio setting, his lips moving naturally in sync with the speech, subtle head movements and eyebrow expressions while talking, soft studio lighting, neutral…A professional young man speaking directly to the camera in a studio setting, his lips moving naturally in sync with the speech, subtle head movements and eyebrow expressions while talking, soft studio lighting, neutral grey background, shallow depth of field, corporate presentation style, smooth steady camera
LTX-Video 13B
Up to 768×768 resolution. 30–120 frames at 30fps (1–4 sec). Text-to-video and image-to-video modes. Single-step distilled inference.