Bytedance Dreamina V3.0 Image To Video 720p
Playground
Try it on WavespeedAI!Dreamina V3.0 converts text or images into pro 720P videos with natural dynamic expression, diverse styles and multi-scene narratives. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
ByteDance Dreamina v3.0 Image-to-Video 720p
Bring your images to life with ByteDance’s Dreamina v3.0 at an accessible price point. This image-to-video model generates smooth, cinematic 720p videos from static images guided by your text descriptions — ideal for rapid iteration, social content, and creative exploration.
Need higher resolution? Try Dreamina v3.0 Image-to-Video 1080p for Full HD output.
Why It Looks Great
- 720p HD output: Sharp, clean video quality suitable for most digital platforms.
- Narrative motion: Describe complex actions and the AI generates coherent, story-driven movement.
- Prompt Enhancer: Built-in tool to refine and expand your motion descriptions automatically.
- Flexible duration: Control how long your generated video runs.
- Cost-effective: Half the price of 1080p for budget-friendly production workflows.
- Reproducible results: Use the seed parameter to recreate exact outputs or explore variations.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the motion, action, and atmosphere you want in the video. |
| image | Yes | Source image to animate (upload or public URL). |
| seed | No | Random seed for reproducibility. Use -1 for random. |
| duration | No | Video length in seconds. Default: 5. |
How to Use
- Write your prompt — describe the motion, actions, and cinematic details you want.
- Use Prompt Enhancer (optional) — click to automatically enrich your motion description.
- Upload your image — drag and drop or paste a public URL.
- Set duration — choose how long you want the video to be.
- Set seed (optional) — use -1 for random, or a specific number to reproduce results.
- Run — click the button to generate.
- Download — preview and save your 720p video.
Pricing
Flat rate per video generation.
| Output | Cost |
|---|---|
| Per video | $0.30 |
Resolution Comparison
| Resolution | Cost | Best For |
|---|---|---|
| 720p | $0.30 | Social media, rapid prototyping, high-volume production |
| 1080p | $0.60 | Professional content, large displays, final deliverables |
Best Use Cases
- Social Media Content — 720p is ideal for Instagram, TikTok, and Twitter where compression reduces quality anyway.
- Concept Testing — Iterate quickly on ideas at half the cost before committing to 1080p finals.
- High-Volume Production — Generate more content within budget for campaigns and content libraries.
- Storyboarding — Visualize sequences and motion concepts during pre-production.
- Creative Exploration — Experiment freely with prompts and styles without budget concerns.
Example Prompts
- “A lone exploration starship slowly approaches a massive, unknown gas giant with colossal rings. Electrical storms are visible on the planet’s surface. From the cockpit point of view, the debris in the rings glitters like diamonds. The camera slowly pushes in.”
- “Gentle camera drift as autumn leaves fall slowly around the subject, warm golden light filtering through trees”
- “The character looks up at the sky in wonder, subtle expression change, soft wind moving their hair”
- “Slow zoom out revealing the full landscape, clouds drifting lazily across the horizon”
- “Coffee steam rises gently from the cup, morning light creating warm shadows across the table”
Pro Tips for Best Results
- 720p is perfect for social platforms — most compress to similar quality anyway.
- Test your concepts at 720p first, then regenerate winners at 1080p for final delivery.
- Describe both subject motion and camera movement for more dynamic results.
- Use cinematic language: “slow motion”, “camera push in”, “dolly shot”, “soft focus”.
- The Prompt Enhancer excels at adding professional cinematography details.
- Keep the same seed when upgrading to 1080p to get a higher-resolution version of the same video.
Notes
- If using a URL for the image, ensure it is publicly accessible. A preview thumbnail confirms successful loading.
- Processing time may vary based on duration and current queue load.
- For final deliverables or large-screen viewing, consider the 1080p version.
- Best results come from images with clear subjects and room for implied motion.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/bytedance/dreamina-v3.0/image-to-video-720p" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"seed": -1,
"duration": 5
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | The positive prompt for the generation. | |
| image | string | Yes | - | The image to be used for the generation. | |
| seed | integer | No | -1 | -1 ~ 2147483647 | The random seed to use for the generation. -1 means a random seed will be used. |
| duration | integer | No | 5 | 5 | The duration of the generated media. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction, the ID of the prediction to get |
| data.model | string | Model ID used for the prediction |
| data.outputs | string | Array of URLs to the generated content (empty when status is not completed). |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |