Seedream V3 is a state-of-the-art text-to-image model that creates photorealistic, high-detail images with artistic flair. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
ว่าง
$0.027ต่อครั้ง·~37 / $1
ตัวอย่างดูทั้งหมด
A young write girl with curly hair eating ice cream, colorful city background, realistic lighting, street-style photography look, lifelike details
A smiling young woman in a sunlit field, wearing a flowing yellow dress, realistic lighting, bright colors, ultra-detailed face, high-resolution, photo-realistic
A man in a hooded jacket climbs a rugged mountain path at dawn, breath misting in the cold air. The rising sun casts long shadows over snow-dusted peaks. Wide-angle shot reveals vast alpine scenery, followed by close-up of his determined face. Wind rustles his backpack straps. Sound of crunching snow underfoot and distant eagle cries. Epic orchestral undertone, dynamic movement through drone tracking shots.
A fluffy cartoon bunny exploring a magical forest, oversized mushrooms and glowing plants, smooth camera motion, Pixar-style lighting
A glowing jellyfish floating through an endless galaxy, stars twinkling in the background, camera rotates gently around, ethereal ambiance, surreal beauty
An intense, dynamic close-up of a muscular man in his 30s, his face glistening with sweat and showing intense concentration, performing a heavy deadlift in a gritty gym. The video shows his muscles tensing and the weight lifting off the ground. The lighting is dramatic and high-contrast, with spotlights creating deep shadows. The atmosphere is raw and powerful. Documentary style, super slow-motion, sharp focus on the man's expression, professional video quality.
a realistic and beautiful close-up of a young woman with long, curly brown hair. she is smiling happily, with a look of surprise on her face. she is standing in a lush green garden with flowers in the background. natural lighting, sharp focus on her face, realistic, cinematic, dynamic motion. shot on a Arri Alexa mini LF, 8K.
Inside a classic, well-stocked university library, a group of four or five students are seated around a large wooden table, piled high with books and laptops. They are engaged in an intense academic discussion. One student is quickly jotting down notes, another is flipping through a heavy, hardcover book, and a third is gesticulating to explain complex concepts. Their expressions are focused and full of intellectual curiosity.
A smiling potter is shaping a clay pot on a potter's wheel in her studio. Her hands, covered in clay, gently and skillfully mold the spinning lump of clay, and the pot's form takes shape under her fingertips. The studio is filled with sunlight, and shelves are lined with pottery of various shapes and sizes, creating a peaceful and creative atmosphere.
โมเดลที่เกี่ยวข้อง
README
Seedream v3 — /seedream-v3
Seedream v3 is a high-quality text-to-image model built for fast, photorealistic generation with strong composition and detail. Write a clear prompt describing subject, scene, lighting, and style, and it produces clean, lifelike images suitable for marketing creatives, portraits, lifestyle photography concepts, and general visual production.
Key capabilities
- Text-to-image generation with strong realism and fine detail
- Reliable composition across custom sizes (set width/height directly)
- Good lighting and material rendering for lifelike results
- Efficient for rapid iteration with controllable randomness via seed
Use cases
- Lifestyle and street-style photography concepts
- Portrait generation with realistic skin, hair, and fabric detail
- Marketing creatives and ad-style key visuals
- Product and brand imagery with controlled lighting
- Rapid ideation for concepts, thumbnails, and mood boards
Pricing
| Output | Price |
|---|---|
| Per image | $0.027 |
Parameters
- prompt (required): Text description of what to generate
- width / height: Output size
- guidance_scale: Prompt adherence strength (higher = stricter; too high may reduce naturalness)
- seed: Random seed (-1 for random; fixed value for reproducible results)
Prompting guide
A stable prompt structure:
- Subject: who/what is in frame
- Action: what they are doing
- Scene: location + background details
- Lighting: time of day, key light, contrast
- Style: photorealistic, street photography, cinematic, etc.
Template: A [subject] [action] in [scene], [lighting], [camera/framing], [style], high detail.
Example prompts
- A young girl with curly hair eating ice cream, colorful city background, realistic lighting, street-style photography look, lifelike details, shallow depth of field.
- Close-up portrait of a man in soft window light, natural skin texture, 85mm lens look, subtle film grain, photorealistic.
- Studio product photo of a minimalist sneaker on a clean backdrop, softbox lighting, crisp shadow, premium advertising style.
Seedream v3 API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bytedance/seedream-v3 with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Seedream v3 below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/bytedance/seedream-v3" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1024*1024",
"guidance_scale": 2.5,
"seed": -1,
"enable_base64_output": false,
"enable_sync_mode": false
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("bytedance/seedream-v3", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1024*1024",
"guidance_scale": 2.5,
"seed": -1,
"enable_base64_output": false,
"enable_sync_mode": false
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"bytedance/seedream-v3",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1024*1024",
"guidance_scale": 2.5,
"seed": -1,
"enable_base64_output": false,
"enable_sync_mode": false
}
)
print(output["outputs"][0]) # → URL of the generated outputSeedream v3 API — Frequently asked questions
What is the Seedream v3 API?
Seedream v3 is a ByteDance model for image generation, exposed as a REST API on WaveSpeedAI. Seedream V3 is a state-of-the-art text-to-image model that creates photorealistic, high-detail images with artistic flair. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Seedream v3 API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/bytedance/bytedance-seedream-v3.
How much does Seedream v3 cost per run?
Seedream v3 starts at $0.027 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Seedream v3 accept?
Key inputs: `prompt`, `size`, `seed`, `guidance_scale`, `enable_base64_output`, `enable_sync_mode`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/bytedance/bytedance-seedream-v3.
How long does Seedream v3 take to generate?
Average end-to-end generation time on WaveSpeedAI is around 13 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Seedream v3 outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (ByteDance). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.