Bytedance Seedream V4 API

Edit
Text To Image

Endpoint: POST https://fal.run/fal-ai/bytedance/seedream/v4/edit Endpoint ID: fal-ai/bytedance/seedream/v4/edit

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/bytedance/seedream/v4/edit",
    arguments={
        "prompt": "Dress the model in the clothes and hat. Add a cat to the scene and change the background to a Victorian era building.",
        "image_urls": [
            "https://storage.googleapis.com/falserverless/example_inputs/seedream4_edit_input_1.png",
            "https://storage.googleapis.com/falserverless/example_inputs/seedream4_edit_input_2.png",
            "https://storage.googleapis.com/falserverless/example_inputs/seedream4_edit_input_3.png",
            "https://storage.googleapis.com/falserverless/example_inputs/seedream4_edit_input_4.png"
        ]
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/bytedance/seedream/v4/edit", {
  input: {
      prompt: "Dress the model in the clothes and hat. Add a cat to the scene and change the background to a Victorian era building.",
      image_urls: [
        "https://storage.googleapis.com/falserverless/example_inputs/seedream4_edit_input_1.png",
        "https://storage.googleapis.com/falserverless/example_inputs/seedream4_edit_input_2.png",
        "https://storage.googleapis.com/falserverless/example_inputs/seedream4_edit_input_3.png",
        "https://storage.googleapis.com/falserverless/example_inputs/seedream4_edit_input_4.png"
      ]
    },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

curl --request POST \
  --url https://fal.run/fal-ai/bytedance/seedream/v4/edit \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "Dress the model in the clothes and hat. Add a cat to the scene and change the background to a Victorian era building.",
  "image_urls": [
    "https://storage.googleapis.com/falserverless/example_inputs/seedream4_edit_input_1.png",
    "https://storage.googleapis.com/falserverless/example_inputs/seedream4_edit_input_2.png",
    "https://storage.googleapis.com/falserverless/example_inputs/seedream4_edit_input_3.png",
    "https://storage.googleapis.com/falserverless/example_inputs/seedream4_edit_input_4.png"
  ]
}'

Input Schema

string

required

The text prompt used to edit the image

ImageSize | Enum

default:"[object Object]"

The size of the generated image. The minimum total image area is 921600 pixels. Failing this, the image size will be adjusted to by scaling it up, while maintaining the aspect ratio.Possible values: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, auto, auto_2K, auto_4K

integer

default:"1"

Number of separate model generations to be run with the prompt. Default value: 1Range: 1 to 6

integer

default:"1"

If set to a number greater than one, enables multi-image generation. The model will potentially return up to max_images images every generation, and in total, num_images generations will be carried out. In total, the number of images generated will be between num_images and max_images*num_images. The total number of images (image inputs + image outputs) must not exceed 15 Default value: 1Range: 1 to 6

integer

Random seed to control the stochasticity of image generation.

boolean

default:"false"

If True, the media will be returned as a data URI and the output data won’t be available in the request history.

boolean

default:"true"

If set to true, the safety checker will be enabled. Default value: true

EnhancePromptModeEnum

default:"standard"

The mode to use for enhancing prompt enhancement. Standard mode provides higher quality results but takes longer to generate. Fast mode provides average quality results but takes less time to generate. Default value: "standard"Possible values: standard, fast

list<string>

required

List of URLs of input images for editing. Presently, up to 10 image inputs are allowed. If over 10 images are sent, only the last 10 will be used.

Output Schema

list<Image>

required

Generated images

integer

required

Seed used for generation

Input Example

{
  "prompt": "Dress the model in the clothes and hat. Add a cat to the scene and change the background to a Victorian era building.",
  "image_size": {
    "height": 2160,
    "width": 3840
  },
  "num_images": 1,
  "max_images": 1,
  "sync_mode": false,
  "enable_safety_checker": true,
  "enhance_prompt_mode": "standard",
  "image_urls": [
    "https://storage.googleapis.com/falserverless/example_inputs/seedream4_edit_input_1.png",
    "https://storage.googleapis.com/falserverless/example_inputs/seedream4_edit_input_2.png",
    "https://storage.googleapis.com/falserverless/example_inputs/seedream4_edit_input_3.png",
    "https://storage.googleapis.com/falserverless/example_inputs/seedream4_edit_input_4.png"
  ]
}

Output Example

{
  "images": [
    {
      "url": "https://storage.googleapis.com/falserverless/example_outputs/seedream4_edit_output.png"
    }
  ],
  "seed": 746406749
}

Endpoint: POST https://fal.run/fal-ai/bytedance/seedream/v4/text-to-image Endpoint ID: fal-ai/bytedance/seedream/v4/text-to-image

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/bytedance/seedream/v4/text-to-image",
    arguments={
        "prompt": "A trendy restaurant with a digital menu board displaying \"Seedream 4.0 is available on fal\" in elegant script, with diners enjoying their meals."
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/bytedance/seedream/v4/text-to-image", {
  input: {
      prompt: "A trendy restaurant with a digital menu board displaying \"Seedream 4.0 is available on fal\" in elegant script, with diners enjoying their meals."
    },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

curl --request POST \
  --url https://fal.run/fal-ai/bytedance/seedream/v4/text-to-image \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "A trendy restaurant with a digital menu board displaying \"Seedream 4.0 is available on fal\" in elegant script, with diners enjoying their meals."
}'

Input Schema

string

required

The text prompt used to generate the image

ImageSize | Enum

default:"[object Object]"

The size of the generated image. Total pixels must be between 960x960 and 4096x4096.Possible values: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, auto, auto_2K, auto_4K

integer

default:"1"

Number of separate model generations to be run with the prompt. Default value: 1Range: 1 to 6

integer

default:"1"

integer

Random seed to control the stochasticity of image generation.

boolean

default:"false"

If True, the media will be returned as a data URI and the output data won’t be available in the request history.

boolean

default:"true"

If set to true, the safety checker will be enabled. Default value: true

EnhancePromptModeEnum

default:"standard"

Output Schema

list<Image>

required

Generated images

integer

required

Seed used for generation

Input Example

{
  "prompt": "A trendy restaurant with a digital menu board displaying \"Seedream 4.0 is available on fal\" in elegant script, with diners enjoying their meals.",
  "image_size": {
    "height": 4096,
    "width": 4096
  },
  "num_images": 1,
  "max_images": 1,
  "sync_mode": false,
  "enable_safety_checker": true,
  "enhance_prompt_mode": "standard"
}

Output Example

{
  "images": [
    {
      "url": "https://storage.googleapis.com/falserverless/example_outputs/seedream4_t2i_output.png"
    }
  ],
  "seed": 746406749
}

Bytedance Seedream v4 — Image Generation
Bytedance — Image Generation
Bytedance Seedream v4 Edit — Image Generation

Limitations

num_images range: 1 to 6
max_images range: 1 to 6
enhance_prompt_mode restricted to: standard, fast
Content moderation via safety checker

Video Generation

Image Generation

Audio

Vision

3D

Bytedance Seedream V4 API

Try it in the Playground

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Try it in the Playground

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Limitations

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

​Related

​Limitations

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Related

Limitations