These models are used in the Generate Video Direct tab of Shot Studio to create motion from multiple reference images or storyboard frames.
When to Use
- Generate Video Direct — Skip first frame generation and create video from uploaded references
- Storyboard to Video — Transform storyboard sequences into animated clips
- Reference-Based Animation — Generate motion that respects specific visual references
- Rapid Prototyping — Quickly test motion concepts from existing images
Recommended Models
These models consistently deliver the best results for multi-image video generation:Google Veo 3.1 (Ingredients)
- Credits: 200
- Rating: ⭐⭐⭐⭐⭐ (5/5)
- Provider: fal.ai
- Avg. Duration: ~98 seconds
- Best for: Highest quality motion from reference sequences
Pika Scenes (v2.2)
- Credits: 40
- Rating: ⭐⭐⭐⭐ (4/5)
- Provider: fal.ai
- Avg. Duration: ~80 seconds
- Best for: Smooth scene transitions and natural motion
Seedance 1.0 Lite Reference
- Credits: 36
- Rating: ⭐⭐⭐⭐⭐ (5/5)
- Provider: fal.ai
- Avg. Duration: ~66 seconds
- Best for: Cost-effective high-quality generation from references
Supported Models
These models are available but may have varying quality or processing times:Vidu Reference-to-Video
- Credits: 80
- Rating: ⭐⭐⭐ (3/5)
- Provider: fal.ai
- Avg. Duration: ~568 seconds
- Use when: Exploring alternative reference-based generation methods
Kling 1.6 Elements Pro
- Credits: 95
- Rating: ⭐⭐ (2/5)
- Provider: fal.ai
- Avg. Duration: ~266 seconds
- Use when: Experimenting with element-based generation (slow processing)
Kling v1.6 Elements Std
- Credits: 45
- Rating: ⭐⭐⭐ (3/5)
- Provider: fal.ai
- Avg. Duration: ~158 seconds
- Use when: Cost-effective element-based generation (Default model)
Tips for Best Results
- Consistent Reference Images — Use images that share similar style, lighting, and composition
- Clear Story Progression — Reference images should show logical progression of action or movement
- Match Shot Attributes — Ensure references align with your shot’s camera settings and movement
- Quality References — Higher quality input images produce better motion results
- Experiment with Sequence — Try different numbers of reference images (2-5 works well)