Ltx Video V097 I2V 720p

Ltx Video V097 I2V 720p

Playground

Generate 720p videos from text prompts and images with LTX Video-0.9.7 for consistent, high-quality image-to-video results. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

LTX-Video v0.97 I2V 720p — wavespeed-ai/ltx-video-v097/i2v-720p

LTX-Video v0.97 I2V 720p generates short videos from a single reference image plus a text prompt. Upload an image to anchor the subject and composition, then describe motion, camera movement, lighting, and style to animate the scene. This model is well-suited for cinematic image animation, stylized shots (e.g., oil painting, illustration), and smooth camera moves at 720p.

Key capabilities

• Image-to-video generation anchored to a reference image (720p output)
• Prompt-driven motion and camera direction (push-in, pan, orbit, tilt)
• Supports negative_prompt to reduce artifacts (blur, jitter, distortion)
• Strong for stylized animation (painting/illustration looks) and cinematic lighting beats

Use cases

• Animate portraits and artworks with subtle motion and cinematic camera moves
• Turn a single keyframe into a short story beat for trailers and storyboards
• Create stylized clips (oil painting, anime, illustration) while preserving composition
• Generate multiple variations by changing seed and prompt details
• Rapid prototyping of mood, lighting, and camera language before higher-cost runs

Pricing

Inputs

• image (required): reference image (subject/composition anchor)
• prompt (required): motion + scene direction
• negative_prompt (optional): what to avoid (blurry, jittery, distorted, etc.)

Parameters

• prompt: describe subject, action, scene, camera, style
• negative_prompt: optional “avoid list”
• image: input image (upload or URL)
• size: output resolution (1280×720)
• seed: random seed (set for reproducible results)

Prompting guide (I2V)

Write prompts like a director’s brief:

• Subject: who/what is on screen
• Motion: subtle expression changes, breathing, cloth movement, particles
• Camera: slow push-in, gentle orbit, rack focus, steady pan
• Lighting/style: chiaroscuro, golden hour, neon, painterly brushwork
• Constraints: keep identity/composition consistent with the reference

Example prompts

• A classical oil painting portrait. Slow camera push-in toward the subject’s face, subtle breathing motion, gentle flicker in candlelight, soft volumetric haze, cinematic chiaroscuro lighting.
• A serene landscape painting. Wind moves the trees slightly, clouds drift slowly, camera pans across the scene, painterly style preserved, smooth motion.
• A fashion portrait. Hair sways lightly, subject turns their head slightly, camera slow orbit, soft studio lighting, realistic texture.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/ltx-video-v097/i2v-720p" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "size": "1280*720"
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"