User Guide
AI Models
Complete reference of all AI models available in OpenStory
OpenStory provides a curated set of models for script analysis, image generation, motion/video generation, and music generation. LLM calls use OpenRouter (directly or through fal's compatible route), images and videos use Prism, and music uses Fal.ai.
Provider Routing
FAL_KEYcovers music generation and can also cover LLM calls routed through fal.OPENROUTER_KEYprovides direct OpenRouter access for LLM models and is optional when a fal key is available.
Keys saved under Settings → API Keys are scoped to the current team. A deployment can also provide platform-wide fallback keys through environment variables.
Script Analysis Models
These LLM models analyze your script, extract scenes, characters, and locations, and generate prompts. You can select multiple models to generate parallel sequences for comparison.
| Model | Vendor | Context Window | Credits / 1M tokens (input/output) |
|---|---|---|---|
| GPT-5.6 Luna | OpenAI | 1.05M tokens | 20 / 120 (default) |
| DeepSeek V4 Flash | DeepSeek | 1.05M tokens | 20 / 120 (scene split) |
Image Generation Models
These models create the visual images for each scene. You can select multiple models to generate variant images for comparison.
| Model | Vendor | Default Output | Credits / image | Notes |
|---|---|---|---|---|
| Nano Banana 2 | 1K | 30 | Fast generation and editing | |
| Nano Banana Pro | 1K | 50 | Enhanced realism and typography | |
| GPT Image 2 | OpenAI | 1K, low quality | 10 | Default; strong text/UI rendering |
Edit Endpoints
Most image models support reference image editing via dedicated edit endpoints. This allows the AI to use character and location reference images when generating scenes, improving visual consistency.
Motion/Video Models
These models animate still images into video clips.
| Model | Vendor | Credits / second | Notes |
|---|---|---|---|
| Seedance 2.0 | ByteDance | 30 | Native audio |
| Seedance 2.0 Fast | ByteDance | 20 | Faster generation |
| Wan 2.6 | Alibaba | 20 | Native audio |
| Wan 2.6 Flash | Alibaba | 10 | Faster generation |
| MiniMax H3 | MiniMax | 10 | Default; native audio |
Aspect Ratio Compatibility
Not all motion models support all aspect ratios. OpenStory automatically filters to show only compatible models and will switch to a compatible default if your current model doesn't support the selected ratio.
Audio Support
Some motion models can generate audio alongside video. OpenStory checks each model's capabilities to determine audio support.
Music & Audio Models
| Model | Vendor | Max Duration | Credits / generation | Type | License |
|---|---|---|---|---|---|
| ACE-Step 1.5 | ACE Studio | 600s (10 min) | 10 | Music | Open Source |
| ACE-Step | ACE Studio | 240s (4 min) | 10 | Music | Open Source |
Music vs. Sound Effects
Both models generate background music from text prompts, optional tags, and optional lyrics. ACE-Step 1.5 is the default.
Capabilities
| Feature | ACE-Step 1.5 | ACE-Step |
|---|---|---|
| Prompt-based | Yes | Yes |
| Lyrics support | Yes | Yes |
| Instrumental | Yes | Yes |
| Long-form | 10 minutes | 4 minutes |
One US dollar corresponds to 100 OpenStory credits. All prices above use the OpenStory product tariff.