Video Models
DUTO supports multiple AI models for video generation with varying capabilities. All video generation requests are processed through WaveSpeed as the primary provider.
Text-to-Video Models
Kling 2.6 Pro
Professional video with native audio
kwaivgi/kling-v2.6-pro/text-to-video| Attribute | Value |
|---|---|
| Quality | High |
| Speed | Medium |
| Duration | 5s, 10s |
| Audio | Yes (native) |
| Cost | 50 credits (5s), 90 credits (10s) |
| Provider | Kwaivgi |
Strengths:
- Native audio generation
- Excellent motion quality
- Longer duration support
- Good value
Best for:
- Music videos
- Professional projects
- Content with audio needs
- Longer clips
Veo 3
Google's premium video model
google/veo3| Attribute | Value |
|---|---|
| Quality | Excellent |
| Speed | Slow |
| Duration | 4s, 6s, 8s |
| Audio | Yes (native) |
| Cost | 70 credits |
| Provider |
Strengths:
- Highest quality output
- Native audio generation
- Excellent motion coherence
- Photorealistic results
Best for:
- Premium content
- Final deliverables
- When quality is paramount
- Content with audio needs
Veo 3 Fast
Faster Veo generation
google/veo3-fast| Attribute | Value |
|---|---|
| Quality | Very Good |
| Speed | Medium |
| Duration | 4s, 6s, 8s |
| Audio | Yes (native) |
| Cost | 60 credits |
| Provider |
Strengths:
- High quality, faster than Veo 3
- Native audio generation
- Good motion coherence
- Balanced quality/speed
Best for:
- Premium content with speed needs
- Client deliverables
- High-quality production
Sora
OpenAI's cinematic video model
openai/sora| Attribute | Value |
|---|---|
| Quality | Excellent |
| Speed | Slow |
| Audio | No |
| Provider | OpenAI (via WaveSpeed) |
Strengths:
- Cinematic quality
- Complex motion and narrative coherence
- Excellent camera work
Best for:
- Storytelling and dramatic scenes
- Complex camera work
- Premium production
Hailuo 02 Pro
High-quality Hailuo generation
minimax/hailuo-02/pro| Attribute | Value |
|---|---|
| Quality | High |
| Speed | Medium |
| Duration | 6s, 10s |
| Audio | No |
| Cost | 40-80 credits |
| Provider | MiniMax |
Strengths:
- Good quality for cost
- Resolution options
- Reliable results
- Flexible duration
Best for:
- Budget-conscious projects
- Standard quality needs
- Testing concepts
Hailuo 2.3 Standard
Standard Hailuo generation
minimax/hailuo-2.3/t2v-standard| Attribute | Value |
|---|---|
| Quality | Good |
| Speed | Fast |
| Duration | 6s, 10s |
| Audio | No |
| Cost | 35-55 credits |
| Provider | MiniMax |
Strengths:
- Fast generation
- Low cost
- Good quality
- Reliable
Best for:
- Rapid iteration
- Budget projects
- Testing concepts
Video 01
MiniMax video generation
minimax/video-01| Attribute | Value |
|---|---|
| Quality | Good |
| Speed | Medium |
| Duration | Variable |
| Audio | No |
| Cost | 60 credits |
| Provider | MiniMax |
Best for:
- General video generation
- Reliable results
Kling O1
Flexible video with camera control
kwaivgi/kling-video-o1/text-to-video| Attribute | Value |
|---|---|
| Quality | Good |
| Speed | Fast |
| Duration | 5s, 10s |
| Audio | No |
| Cost | 40-80 credits |
| Provider | Kwaivgi (via WaveSpeed) |
Strengths:
- Camera control support
- Good quality for cost
- 50% cheaper than Veo 3
Best for:
- Camera-heavy shots
- Character consistency
- Budget projects
Image-to-Video Models
Kling 2.6 Pro I2V
Professional image-to-video
kwaivgi/kling-v2.6-pro/image-to-video| Attribute | Value |
|---|---|
| Quality | High |
| Speed | Medium |
| Duration | 5s, 10s |
| Audio | Yes (native) |
| Cost | 45 credits (5s), 85 credits (10s) |
| Provider | Kwaivgi |
Strengths:
- Native audio support
- High quality motion
- Good image adherence
- Longer duration
Best for:
- Animating storyboards
- Premium content
- Audio-included videos
Veo 3 Fast I2V
Fast Veo image-to-video
google/veo3-fast/image-to-video| Attribute | Value |
|---|---|
| Quality | Very Good |
| Speed | Medium |
| Duration | 4s, 6s, 8s |
| Audio | Yes (native) |
| Cost | 55 credits |
| Provider |
Strengths:
- High quality I2V
- Native audio
- Good motion
- Balanced speed
Best for:
- Premium I2V with audio
- Storyboard animation
Veo 3.1 Reference
Multi-image reference video
google/veo3.1/reference-to-video| Attribute | Value |
|---|---|
| Quality | Excellent |
| Speed | Medium |
| Duration | Variable |
| Audio | Yes (native) |
| Cost | 60 credits |
| Provider |
Strengths:
- Multiple image support
- Native audio
- Excellent quality
- Reference-based
Best for:
- Multi-shot reference
- Character consistency
- Complex scenes
Wan 2.5
Flexible Alibaba model
alibaba/wan-2.5/image-to-video| Attribute | Value |
|---|---|
| Quality | Good |
| Speed | Fast |
| Duration | 3-10s |
| Audio | No |
| Cost | 40 credits |
| Provider | Alibaba |
Strengths:
- Wide duration range
- Good quality
- Fast generation
- Cost-effective
Best for:
- Custom duration
- Budget projects
- Rapid iteration
Wan 2.2 Spicy
Enhanced Wan model
wavespeed-ai/wan-2.2-spicy/image-to-video| Attribute | Value |
|---|---|
| Quality | Good |
| Speed | Fast |
| Duration | 5s, 8s |
| Audio | No |
| Cost | 35-55 credits |
| Provider | WaveSpeed AI |
Strengths:
- Enhanced motion
- Fast generation
- Good quality
- Lower cost
Best for:
- Dynamic content
- Budget animation
- Quick turnaround
Hailuo 2.3 I2V
Hailuo image-to-video options
minimax/hailuo-2.3/i2v-pro minimax/hailuo-2.3/i2v-fast minimax/hailuo-2.3/i2v-standard| Attribute | Pro | Fast | Standard |
|---|---|---|---|
| Quality | High | Good | Good |
| Speed | Medium | Fast | Fast |
| Duration | 6s, 10s | 6s, 10s | 6s, 10s |
| Cost | 35-55 credits | 30-50 credits | 30-50 credits |
Best for:
- Budget I2V
- Quick animation
- Standard quality
Hailuo 02 Fast
Latest Hailuo fast model
minimax/hailuo-02/fast| Attribute | Value |
|---|---|
| Quality | Good |
| Speed | Fast |
| Duration | 6s, 10s |
| Cost | 30-50 credits |
| Provider | MiniMax |
Best for:
- Quick iterations
- Budget projects
Waver 1.0
ByteDance smooth motion
bytedance/waver-1.0| Attribute | Value |
|---|---|
| Quality | High |
| Speed | Medium |
| Duration | 5-10s |
| Audio | No |
| Cost | 50 credits |
| Provider | ByteDance |
Strengths:
- Smooth motion
- Natural movement
- Balanced quality
- Good for products
Best for:
- Product demos
- Smooth animations
- General purpose
Kling O1 I2V
Kling O1 image-to-video
kwaivgi/kling-video-o1/image-to-video| Attribute | Value |
|---|---|
| Quality | Good |
| Speed | Fast |
| Duration | 5s, 10s |
| Audio | No |
| Cost | 40-80 credits |
| Provider | Kwaivgi (via WaveSpeed) |
Strengths:
- Flexible options
- Camera control
- Negative prompts
- Last-frame reference
Best for:
- Custom duration shots
- Sequenced content
Kling O1 Reference
Multi-image reference
kwaivgi/kling-video-o1/reference-to-video| Attribute | Value |
|---|---|
| Quality | Good |
| Speed | Fast |
| Duration | 3-10s |
| Audio | No |
| Cost | 40-80 credits |
| Provider | Kwaivgi |
Strengths:
- Multiple image support
- Character consistency
- Reference-based
Best for:
- Multi-character scenes
- Consistency needs
Seedance Pro
ByteDance Seedance model
bytedance/seedance-v1-pro-i2v-480p| Attribute | Value |
|---|---|
| Quality | Good |
| Speed | Medium |
| Duration | 5-10s |
| Audio | No |
| Cost | Variable |
| Provider | ByteDance |
Best for:
- 480p content
- Budget projects
Model Comparison
| Model | Quality | Speed | Duration | Audio | Cost Range |
|---|---|---|---|---|---|
| Veo 3 | ★★★★★ | ★★ | 4-8s | Yes | 70 cr |
| Veo 3.1 Ref | ★★★★★ | ★★★ | Variable | Yes | 60 cr |
| Veo 3 Fast | ★★★★ | ★★★ | 4-8s | Yes | 55-60 cr |
| Kling 2.6 Pro | ★★★★ | ★★★ | 5-10s | Yes | 45-90 cr |
| Sora | ★★★★★ | ★★ | Variable | No | Premium |
| Kling O1 | ★★★ | ★★★★ | 5-10s | No | 40-80 cr |
| Hailuo Pro | ★★★ | ★★★ | 6-10s | No | 35-55 cr |
| Waver 1.0 | ★★★★ | ★★★ | 5-10s | No | 50 cr |
| Wan 2.5 | ★★★ | ★★★★ | 3-10s | No | 40 cr |
Audio Support
Models with native audio generate synchronized sound:
| Model | Audio Support | Audio Quality |
|---|---|---|
| google/veo3 | Native, automatic | Excellent |
| google/veo3-fast | Native, automatic | Excellent |
| google/veo3.1/reference-to-video | Native, automatic | Excellent |
| kwaivgi/kling-v2.6-pro | Native, optional | Good |
For models without audio, use:
- Video Foley node
- MMAudio node
- Lip Sync node
Duration Guidelines
| Model | Durations |
|---|---|
| Veo 3/Veo 3 Fast | 4s, 6s, 8s |
| Kling 2.6 Pro | 5s, 10s |
| Kling O1 | 5s, 10s |
| Hailuo 2.3 | 6s, 10s |
| Hailuo 02 | 6s, 10s |
| Wan 2.5 | 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s |
| Waver 1.0 | 5s, 6s, 7s, 8s, 9s, 10s |
| Wan 2.2 Spicy | 5s, 8s |
| Seedance Pro | 5s, 6s, 7s, 8s, 9s, 10s |
Generation Modes
Text to Video
Generate from text description:
"A golden retriever running through a meadow,
slow motion, cinematic, golden hour lighting"
Image to Video
Animate a still image:
- Upload source image
- Add motion prompt
- Generate animation
Reference to Video
Use multiple reference images for consistency:
- Upload multiple images
- Generate with character/scene consistency
Model Selection Guide
By Use Case
| Use Case | Recommended |
|---|---|
| Social media content | Hailuo Standard/Fast |
| Professional project | Kling 2.6 Pro |
| Premium production | Veo 3 / Veo 3.1 |
| Music video | Kling 2.6 Pro (audio) |
| Quick draft | Hailuo Fast |
| Storyboard animation | Veo 3.1 Reference |
By Budget
| Budget Level | Model |
|---|---|
| Minimal | Hailuo Fast |
| Moderate | Hailuo Standard |
| Standard | Kling 2.6 Pro |
| Premium | Veo 3 / Veo 3.1 |
By Quality Need
| Quality Need | Model |
|---|---|
| Testing | Hailuo Fast |
| Draft | Hailuo Standard |
| Client review | Kling 2.6 Pro |
| Final delivery | Veo 3 / Veo 3.1 |
Workflow Strategy
Efficient Iteration
1. Test concept with Hailuo Fast (30 credits)
2. Refine with Hailuo Standard (35 credits)
3. Final with Veo 3 or Kling Pro (70 credits)
Total: ~135 credits
vs All Veo 3: ~280 credits
Savings: 52%
Storyboard Projects
Hero frames: Budget image model
Video generation:
- Non-critical shots: Hailuo Standard
- Key shots: Kling 2.6 Pro or Veo 3
Tips for Best Results
Prompt Writing
Good: "Slow camera push into a coffee cup,
steam rising, morning light from window,
cozy kitchen background"
Better: "Slow dolly shot pushing in toward
a ceramic coffee cup with visible steam,
soft morning sunlight streaming from
the left, cozy modern kitchen, shallow
depth of field, cinematic"
Motion Guidance
Include motion descriptions:
- Camera movement (pan, zoom, track)
- Subject motion (walk, wave, turn)
- Speed (slow motion, normal, fast)
- Direction (left to right, toward camera)
Quality Optimization
- High-quality source images (for I2V)
- Clear, detailed prompts
- Appropriate model for final use
- Proper aspect ratio selection