Multimodal Video Generation Instruction
The instruction used in Seedance 2.0 to generate a video based on a detailed text description provided in a reference image, due to character limits in the text input.

- Prompt included
- Model and format preset
- Premium template

The prompt behind this video
Copy the exact prompt behind Multimodal Video Generation Instruction, or open it in the studio and make it yours.
Generate a video based on the text description in the reference image.
How to use Multimodal Video Generation Instruction in 3 steps
- 1Upload ImagePNG, JPG or paste
Add your photo
Upload the photo the template builds on. The prompt, model and format are already set.
- 2…a portrait of your subject in softgolden-hour light, 85mm…
Personalize
Edit the subject and creative details for your destination.
- 3
GenerateGenerate
Press Generate — your video is created in PicX Studio, so you can compare it with the original and refine one variable at a time.
More like this
Templates with the same subject, style or setup. Open one to see its prompt.

Professional TikTok Video Director Instruction

Sequence and Movement Instruction for Martial Arts Video

Storyboard to Live Action Video Instruction

Grok Imagine prompt with animation instructions

Character Movement Video Instruction

LLM Prompting Instructions for Formatting and Immersion

Real Animal Spear Dance Video Generation

Traditional Chinese Ink Wash Video Generation

Storyboard to Scene Generation

Cyberpunk Guerrilla Girl Video Generation

Interior View Video Generation Prompt

Back to the Future 4 R-rated Video Generation
Make it yours
Multimodal Video Generation Instruction works as-is. These are the safest ways to change it without losing the look.
Change one field
Copy a single group, rewrite it, and generate again so you can see what that field is doing.
Keep the frame, change the subject
Hold the composition and light of Multimodal Video Generation Instruction, then swap wardrobe, props or the person for a new take.
| If the result… | Why | Fix |
|---|---|---|
| The result drifts from the preview | Too many fields changed at once. | Reuse Multimodal Video Generation Instruction as-is first, then change one group — subject, light, or setting. |
| The model over-stylizes the scene | The prose prompt leaves finish and camera underspecified. | Add one camera or lighting sentence and stay on Seedance 2.0. |
More Seedance 2.0 templates
Other prompts made for Seedance 2.0.
More video prompts
Fresh picks from across the catalog.
Browse template categories
Multimodal Video Generation Instruction questions
How do I use the Multimodal Video Generation Instruction template?
Add your photo if the template asks for one, edit the prompt if you like — the template's model and format are already selected — and press Generate. Your version opens in PicX Studio.
Can I customize the Multimodal Video Generation Instruction template?
Yes. You can change the subject, setting, lighting, mood, format, and available model controls before creating your video.
Is the Multimodal Video Generation Instruction template free?
Opening and editing this template is free. Generating uses credits, shown on the Generate button when you are signed in.
Which AI model should I use?
Start with Seedance 2.0, which is the model associated with this template. You can compare another compatible model for a different finish.
Looking for something else? Browse all templates.

Your photo, any look
Thousands of ready templates for every top image and video model, from one credit balance.

















