AI models on Craze
Every video, image, voice, music and sound model Craze can direct, with what each one makes and what it costs.
Every video, image, voice, music and sound model Craze can direct, with what each one makes and what it costs.
Starts at$0.169 per second of audio
ByteDance's advanced digital human model that animates photos into expressive full-body avatars with complex gestures and emotional nuance.
OmniHuman 1.5 doesn't just follow phonemes or acoustic contours.
Hands are where most avatar models fail.
OmniHuman 1.5 generates natural camera movement and shot composition, not just close-ups.
Photographs, AI-generated renders, animated characters, stylized art.
Craze creatively jams, researches and plans with you.
Craze generates anything imaginable. Video, audio, music, motion graphics and more.
Craze watches your footage and builds a final cut. With a real editor if you need it.
Every model here runs on every Craze plan, including Free, and Craze can use a different one for each shot.
| OmniHuman 1.5ByteDance | Seedance 2.5ByteDance Seed Team | Seedance 2.0ByteDance Seed Team | Seedance 2.0 FastByteDance Seed Team | |
|---|---|---|---|---|
| Makes | Text + Audio + Image to video | Text + Image + Video + Audio to video | Text + Image + Video + Audio to video | Text + Image + Video + Audio to video |
| Quality | Up to 1080p | Up to 1080p | Up to 4K | Up to 720p |
| Length | — | Up to 30s per clip | Up to 15s per clip | Up to 15s per clip |
| Sound | — | Generated with the picture | Generated with the picture | Generated with the picture |
| From | $0.169 per second of audio | $0.114 per second of video | $0.075 per second of video | $0.06 per second of video |
| Task | Inputs | Resolution | Aspect ratios | Sound |
|---|---|---|---|---|
| Talking photo | Audio, First frame | 720p, 1080p | Follows the input | None |
$0/ month
$19/ month
$59/ month
$199/ month
OmniHuman 1.5 represents a shift in digital human generation. It isn't just moving lips or tilting heads. The model bridges a language model and a diffusion transformer to generate performance with emotional depth. Characters read the emotional intent of audio and respond with nuanced expressions and gestures.
OmniHuman 1.5 doesn't just follow phonemes or acoustic contours. It reads the emotional content of the audio and generates performance that matches. A sad line gets downturned expressions and subdued gestures. An excited delivery gets open posture and expansive hand motion.
Hands are where most avatar models fail. OmniHuman 1.5 generates hand motion that corresponds to what's being said. Fingers stay coordinated with the body. Hands stay at natural scales. Gestures develop naturally across long speeches.
OmniHuman 1.5 generates natural camera movement and shot composition, not just close-ups. A character can shift position, turn, and move through space in the frame, creating cinematic presence.
Photographs, AI-generated renders, animated characters, stylized art. OmniHuman 1.5 generalizes well across different source material. The model doesn't require live-action training data bias.
OmniHuman 1.5 is a transform model: provide one photo and one audio track, and Craze generates the animated performance.
OmniHuman 1.5 works well on photos where the subject is clearly visible and facing somewhat toward the camera. Photos don't need to be professional; phone photos and artistic renders both work.
The bridge between a multimodal language model and a diffusion transformer gives OmniHuman 1.5 a unique capability: it understands semantic meaning in the audio, not just phonetics. That's why it generates emotional nuance that matches intent, and why complex gesture and body language develop naturally across longer speeches. A character doesn't just move in response to sound; it performs in response to meaning.
OmniHuman 1.5 is priced by the length of your audio at $0.169 per second of audio. A 30-second clip costs half as much as a 60-second one. Pricing scales linearly with audio duration. Calculate exact costs on this page.
Photo source, resolution, and video format don't affect the price. Only the duration of the audio matters.
Kling Avatar 2 Pro and Kling Avatar 2 offer simpler animation for shorter videos. VEED Fabric 1.0 is faster and cheaper, and takes up to 5 minutes of audio. OmniHuman 1.5 excels when you need emotional complexity, expressive gesture, or cinematic quality.
Create cinematic digital humans for shorts, web series, and indie films. OmniHuman 1.5's emotional intelligence and camera work create characters that feel present in scenes, not just animated faces.
Animate brand mascots or spokesperson characters with nuanced performance. Complex gestures and emotional expression create engagement that static avatars don't achieve.
Game developers and XR creators can use OmniHuman 1.5 to generate NPC performances or interactive characters with natural dialogue and gesture.
Podcasters and audio creators can add high-end video performances to their audio content. Complex hand motion and emotional nuance make videos engaging to watch, not just listen to.
Educational institutions can create instructor avatars with genuine emotional presence for online learning. Complex gesture and expression make education feel personal and engaging.
Indie filmmakers and web series creators can use OmniHuman 1.5 to generate character performances that feel present and emotionally grounded. The model's understanding of emotional content means a character feels like they're responding to the moment, not just playing back animation.
Actors, musicians, and performers can create video content from audio without needing cameras or multiple takes. One good audio performance becomes video with nuanced gesture and expression.
Describe what you want the way you would brief an editor, and Craze plans the shots and writes the OmniHuman 1.5 prompts for you. Every Craze plan, including Free, runs OmniHuman 1.5 and every other media model, and Craze can use a different one for each job. Each video lands on an editable timeline with your cuts, captions and music, ready to export as MP4. Generations come out of your plan's monthly credits, from $0.169 per second of audio, with top-ups when you need more.
Film and narrative production: Create cinematic digital humans for shorts, web series, and indie films. Commercial and advertising: Animate brand mascots or spokesperson characters with nuanced performance. Interactive and immersive experiences: Game developers and XR creators can use OmniHuman 1.5 to generate NPC performances or interactive characters with natural dialogue and gesture. Podcast and interview video production: Podcasters and audio creators can add high-end video performances to their audio content.
OmniHuman 1.5 is a digital human model from ByteDance that animates a single photo into a video. It generates realistic facial expressions, upper body movement, hand gestures, and full-body performance to match audio.
OmniHuman 1.5 costs $0.169 per second of audio on Craze. Longer videos cost more. Use the cost calculator on this page for exact estimates.
every Craze plan, including Free include OmniHuman 1.5. Your plan provides monthly credits for digital human generation.
Craze runs OmniHuman 1.5 on up to 60 seconds of audio at 720p, and up to 30 seconds at 1080p. The video runs as long as the audio. For a longer piece, split the audio into sections and join the clips in the Craze editor.
OmniHuman 1.5 bridges a multimodal language model and a diffusion transformer, generating complex emotional expression, nuanced hand movement, and dynamic camera work that other avatar models don't capture.
One photo of the subject and one audio track. A short text prompt is optional and can steer gesture, framing, or camera movement.
Any audio works: voice recordings, text-to-speech, music, or generated speech. The model reads emotional tone and generates performance that matches the audio content.
Yes. OmniHuman 1.5 generalizes well to animated characters, stylized renders, and artistic works, not just photographs of real people.
ByteDance Seed Team
From $0.114 per second of video
ByteDance Seed Team
From $0.075 per second of video
ByteDance Seed Team
From $0.06 per second of video
