Seedream 4.0

Delivers ultra-fast, high-resolution image generation, precise natural-language editing, and consistent multi-image output—ideal for creative, batch, or…

Try Seedream 4.0 in the Workbench

Run this model interactively, tune parameters, and compare outputs.

Model ID: bytedance-seedream-4

Seedream 4.0 is a Multimodal LLM designed for unified image generation and advanced image editing via natural language prompts.

It excels in high-speed, high-resolution image synthesis and editing, supporting tasks such as photorealistic image generation, precise object addition/removal, and consistent multi-image output. The model offers robust handling of both Chinese and English prompts, maintains character and style consistency across sets, and enables batch processing for efficient workflows.

Some other noteworthy features of Seedream 4.0 include the ability to generate up to 9–10 matching images in a single batch, seamless style transfer, and detailed transformations—making it valuable for storyboarding, product design, and creative content production.

Metric	Value
Parameter Count	Unknown
Mixture of Experts	Unknown
Context Length	Unknown
Multilingual	Yes
Quantized*	Unknown

*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.

Example request

Use the Workbench as a request builder: configure parameters for this model in the UI, then open the API tab to copy the exact cURL or Python call.

Sync

See the image generation reference for more details.

cURL

curl -X POST https://hub.oxen.ai/api/ai/images/generate \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "bytedance-seedream-4",
  "prompt": "Add a funny hat",
  "input_image": [
    "https://hub.oxen.ai/api/repos/ox/Oxen-Character-Simple-Vector-Graphic/file/main/images/reference/bloxy_white_bg.png"
  ]
}'

Async

See the async queue reference for more details.

cURL

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "bytedance-seedream-4",
  "prompt": "Add a funny hat",
  "input_image": [
    "https://hub.oxen.ai/api/repos/ox/Oxen-Character-Simple-Vector-Graphic/file/main/images/reference/bloxy_white_bg.png"
  ]
}' | jq -r '.generations[0].generation_id')

# Poll the single generation until it 404s (terminal state).
while curl -s -o /dev/null -w "%{http_code}" \
    -H "Authorization: Bearer $OXEN_API_KEY" \
    "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | grep -q "^200$"; do
  sleep 5
done
echo "Done. See the 'Async with SSE' tab to receive the result URL."

Async with SSE

See the async queue reference for more details.

cURL

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "bytedance-seedream-4",
  "prompt": "Add a funny hat",
  "input_image": [
    "https://hub.oxen.ai/api/repos/ox/Oxen-Character-Simple-Vector-Graphic/file/main/images/reference/bloxy_white_bg.png"
  ]
}' | jq -r '.generations[0].generation_id')

# Stream the SSE channel, grab the data line that follows a
# media_generation_completed event for our id, and pretty-print it.
curl -sN -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/events \
  | awk -v id="$GEN_ID" '
    /^event: media_generation_completed$/ { expect=1; next }
    /^data: / && expect {
      payload = substr($0, 7)
      if (index(payload, "\"generation_id\":\"" id "\"")) { print payload; exit }
      expect = 0
    }
  ' | jq .

Fetch model details

The models endpoint returns the full model object, including its json_request_schema.

curl -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/ai/models/bytedance-seedream-4

Request parameters

Required parameters

Field	Type	Default	Description
prompt	string	"Add a funny hat"	Text description of what you want to generate, or the instruction on how to edit the given image.
input_image	array<string>	["https://hub.oxen.ai/api/repos/ox/Oxen-Character-Simple-Vector-Graphic/file/main/images/reference/bloxy_white_bg.png"]	Input images to transform or use as reference (supports multiple image urls)