API Reference

Models

Presets

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Create

models.presets.create(strmodel_id, PresetCreateParams**kwargs) -> PresetCreateResponse

POST/models/{modelId}/presets

Create a new preset for the given modelId

ParametersExpand Collapse

model_id: str

inference_id: str

The inference ID used to generate new images

original_assets: Optional[bool]

If set to true, returns the original asset without transformation

project_id: Optional[str]

The projectId used for ownership resource management. Either to assert ownership or to set the owner of the resource(s)

is_default: Optional[bool]

Whether this preset should be the default preset for the model

ReturnsExpand Collapse

class PresetCreateResponse: …

preset: Preset

id: str

The preset ID (example: “eyVcnFJcR92BxBkz7N6g5w”)

author_id: str

The author user ID (example: “VFhihHKMRZyDDnZAJwLb2Q”)

created_at: str

The preset creation date as an ISO string (example: “2023-02-03T11:19:41.579Z”)

is_default: bool

Whether the preset is the default preset of the model (example: true)

model_id: str

The model ID (example: “eyVcnFJcR92BxBkz7N6g5w”)

owner_id: str

The owner ID (example: “VFhihHKMRZyDDnZAJwLb2Q”)

parameters: PresetParameters

The inference parameters

prompt: str

Full text prompt including the model placeholder. (example: “an illustration of phoenix in a fantasy world, flying over a mountain, 8k, bokeh effect”)

type: Literal["controlnet", "controlnet_img2img", "controlnet_inpaint", 15 more]

The type of inference to use. Example: txt2img, img2img, etc.

Selecting the right type will condition the expected parameters.

Note: for inpainting with models that support multiple base models, Scenario determines the best available baseModel for a given modelId.

One of the following:

"controlnet"

"controlnet_img2img"

"controlnet_inpaint"

"controlnet_inpaint_ip_adapter"

"controlnet_ip_adapter"

"controlnet_reference"

"controlnet_texture"

"img2img"

"img2img_ip_adapter"

"img2img_texture"

"inpaint"

"inpaint_ip_adapter"

"outpaint"

"reference"

"reference_texture"

"txt2img"

"txt2img_ip_adapter"

"txt2img_texture"

aspect_ratio: Optional[Literal["16:9", "1:1", "21:9", 8 more]]

The aspect ratio of the generated images. Only used for the model flux.1.1-pro-ultra. The aspect ratio is a string formatted as “width:height” (example: “16:9”).

One of the following:

"16:9"

"1:1"

"21:9"

"2:3"

"3:2"

"3:4"

"4:3"

"4:5"

"5:4"

"9:16"

"9:21"

base_model_id: Optional[str]

The base model to use for the inference. Only Flux LoRA models can use this parameter. Allowed values are available in the model’s attribute: compliantModelIds

concepts: Optional[List[PresetParametersConcept]]

model_id: str

The model ID (example: “model_eyVcnFJcR92BxBkz7N6g5w”)

scale: float

The scale of the model (example: 1.0) For Flux Kontext Prompt Editing, the scale is between 0 and 2.

maximum2

minimum-2

model_epoch: Optional[str]

The epoch of the model (example: “000001”) Only available for Flux Lora Trained models

control_end: Optional[float]

Specifies how long the ControlNet guidance should be applied during the inference process.

Only available for Flux.1-dev based models.

The value represents the percentage of total inference steps where the ControlNet guidance is active. For example:

• 1.0: ControlNet guidance is applied during all inference steps
• 0.5: ControlNet guidance is only applied during the first half of inference steps

Default values:

• 0.5 for Canny modality
• 0.6 for all other modalities

maximum1

minimum0.1

control_image: Optional[str]

Signed URL to display the controlnet input image

control_image_id: Optional[str]

Asset id of the controlnet input image

control_start: Optional[float]

Specifies the starting point of the ControlNet guidance during the inference process.

Only available for Flux.1-dev based models.

The value represents the percentage of total inference steps where the ControlNet guidance starts. For example:

• 0.0: ControlNet guidance starts at the beginning of the inference steps
• 0.5: ControlNet guidance starts at the middle of the inference steps

maximum0.9

minimum0

disable_merging: Optional[bool]

If set to true, the entire input image will likely change during inpainting. This results in faster inferences, but the output image will be harder to integrate if the input is just a small part of a larger image.

disable_modality_detection: Optional[bool]

If false, the process uses the given image to detect the modality. If true (default), the process will not try to detect the modality of the given image.

For example: with pose modality and false value, the process will detect the pose of people in the given image with depth modality and false value, the process will detect the depth of the given image with scribble modality and truevalue, the process will use the given image as a scribble

⚠️ For models of the FLUX schnell or dev families, this parameter is ignored. The modality detection is always disabled. ⚠️

guidance: Optional[float]

Controls how closely the generated image follows the prompt. Higher values result in stronger adherence to the prompt. Default and allowed values depend on the model type:

• For Flux dev models, the default is 3.5 and allowed values are within [0, 10]
• For Flux pro models, the default is 3 and allowed values are within [2, 5]

maximum20

minimum0

height: Optional[float]

The height of the generated images, must be a 8 multiple (within [64, 2048], default: 512) If model.type is flux.1.1-pro-ultra, you can use the aspectRatio parameter instead

maximum2048

minimum64

multipleOf8

hide_results: Optional[bool]

If set, generated assets will be hidden and not returned in the list of images of the inference or when listing assets (default: false)

image: Optional[str]

Signed URL to display the input image

image_id: Optional[str]

Asset id of the input image

intermediate_images: Optional[bool]

Enable or disable the intermediate images generation (default: false)

ip_adapter_image: Optional[str]

Signed URL to display the IpAdapter image

ip_adapter_image_id: Optional[str]

Asset id of the input IpAdapter image

ip_adapter_image_ids: Optional[List[str]]

Asset id of the input IpAdapter images

ip_adapter_images: Optional[List[str]]

Signed URL to display the IpAdapter images

ip_adapter_scale: Optional[float]

IpAdapter scale factor (within [0.0, 1.0], default: 0.9).

maximum1

minimum0

ip_adapter_scales: Optional[List[float]]

IpAdapter scale factors (within [0.0, 1.0], default: 0.9).

maximum1

minimum0

ip_adapter_type: Optional[Literal["character", "style"]]

The type of IP Adapter model to use. Must be one of [style, character], default to `style“

One of the following:

"character"

"style"

mask: Optional[str]

Signed URL to display the mask image

mask_id: Optional[str]

Asset id of the mask image

modality: Optional[str]

The modality associated with the control image used for the generation: it can either be an object with a combination of maximum

For models of the FLUX schnell or dev families:

• one modality from: canny, tile, depth, blur, pose, gray, low-quality

Optionally, you can associate a value to these modalities or presets. The value must be within ]0.0, 1.0].

Examples:

• canny
• depth:0.5,pose:1.0
• canny:0.5,depth:0.5,lines:0.3
• landscape
• character:0.5
• illusion:1

Note: if you use a value that is not supported by the model family, this will result in an error.

model_epoch: Optional[str]

The epoch of the model to use for the inference. Only available for Flux Lora Trained models.

negative_prompt: Optional[str]

The prompt not to guide the image generation, ignored when guidance < 1 (example: “((ugly face))”) For Flux based model (not Fast-Flux): requires negativePromptStrength > 0 and active only for inference types txt2img / img2img / controlnet.

negative_prompt_strength: Optional[float]

Only applicable for flux-dev based models for txt2img, img2img, and controlnet inference types.

Controls the influence of the negative prompt. Default 0 means the negative prompt has no effect. Higher values increase negative prompt influence. Must be > 0 if negativePrompt is provided.

maximum10

minimum0

num_inference_steps: Optional[float]

The number of denoising steps for each image generation (within [1, 150], default: 30)

maximum150

minimum1

num_samples: Optional[float]

The number of images to generate (within [1, 128], default: 4)

maximum128

minimum1

reference_adain: Optional[bool]

Whether to use reference adain Only for “reference” inference type

reference_attn: Optional[bool]

Whether to use reference query for self attention’s context Only for “reference” inference type

scheduler: Optional[Literal["DDIMScheduler", "DDPMScheduler", "DEISMultistepScheduler", 12 more]]

The scheduler to use to override the default configured for the model. See detailed documentation for more details.

One of the following:

"DDIMScheduler"

"DDPMScheduler"

"DEISMultistepScheduler"

"DPMSolverMultistepScheduler"

"DPMSolverSinglestepScheduler"

"EulerAncestralDiscreteScheduler"

"EulerDiscreteScheduler"

"HeunDiscreteScheduler"

"KDPM2AncestralDiscreteScheduler"

"KDPM2DiscreteScheduler"

"LCMScheduler"

"LMSDiscreteScheduler"

"PNDMScheduler"

"TCDScheduler"

"UniPCMultistepScheduler"

seed: Optional[str]

Used to reproduce previous results. Default: randomly generated number.

maximum2147483647

minimum0

strength: Optional[float]

Controls the noise intensity introduced to the input image, where a value of 1.0 completely erases the original image’s details. Available for img2img and inpainting. (within [0.01, 1.0], default: 0.75)

maximum1

minimum0.01

style_fidelity: Optional[float]

If style_fidelity=1.0, control more important, else if style_fidelity=0.0, prompt more important, else balanced Only for “reference” inference type

maximum1

minimum0

width: Optional[float]

The width of the generated images, must be a 8 multiple (within [64, 2048], default: 512) If model.type is flux.1.1-pro-ultra, you can use the aspectRatio parameter instead

maximum2048

minimum64

multipleOf8

updated_at: str

The preset last update date as an ISO string (example: “2023-02-03T11:19:41.579Z”)

Create

Python

HTTP

TypeScript

Python

import os
from scenario_sdk import Scenario

client = Scenario(
    api_key=os.environ.get("SCENARIO_SDK_API_KEY"),  # This is the default and can be omitted
    api_secret=os.environ.get("SCENARIO_SDK_API_SECRET"),  # This is the default and can be omitted
)
preset = client.models.presets.create(
    model_id="modelId",
    inference_id="inferenceId",
)
print(preset.preset)

200 example

{
  "preset": {
    "id": "id",
    "authorId": "authorId",
    "createdAt": "createdAt",
    "isDefault": true,
    "modelId": "modelId",
    "ownerId": "ownerId",
    "parameters": {
      "prompt": "prompt",
      "type": "controlnet",
      "aspectRatio": "16:9",
      "baseModelId": "baseModelId",
      "concepts": [
        {
          "modelId": "modelId",
          "scale": -2,
          "modelEpoch": "modelEpoch"
        }
      ],
      "controlEnd": 0.1,
      "controlImage": "controlImage",
      "controlImageId": "controlImageId",
      "controlStart": 0,
      "disableMerging": true,
      "disableModalityDetection": true,
      "guidance": 0,
      "height": 64,
      "hideResults": true,
      "image": "image",
      "imageId": "imageId",
      "intermediateImages": true,
      "ipAdapterImage": "ipAdapterImage",
      "ipAdapterImageId": "ipAdapterImageId",
      "ipAdapterImageIds": [
        "string"
      ],
      "ipAdapterImages": [
        "string"
      ],
      "ipAdapterScale": 0,
      "ipAdapterScales": [
        0
      ],
      "ipAdapterType": "character",
      "mask": "mask",
      "maskId": "maskId",
      "modality": "modality",
      "modelEpoch": "modelEpoch",
      "negativePrompt": "negativePrompt",
      "negativePromptStrength": 0,
      "numInferenceSteps": 1,
      "numSamples": 1,
      "referenceAdain": true,
      "referenceAttn": true,
      "scheduler": "DDIMScheduler",
      "seed": "seed",
      "strength": 0.01,
      "styleFidelity": 0,
      "width": 64
    },
    "updatedAt": "updatedAt"
  }
}

Returns Examples

200 example

{
  "preset": {
    "id": "id",
    "authorId": "authorId",
    "createdAt": "createdAt",
    "isDefault": true,
    "modelId": "modelId",
    "ownerId": "ownerId",
    "parameters": {
      "prompt": "prompt",
      "type": "controlnet",
      "aspectRatio": "16:9",
      "baseModelId": "baseModelId",
      "concepts": [
        {
          "modelId": "modelId",
          "scale": -2,
          "modelEpoch": "modelEpoch"
        }
      ],
      "controlEnd": 0.1,
      "controlImage": "controlImage",
      "controlImageId": "controlImageId",
      "controlStart": 0,
      "disableMerging": true,
      "disableModalityDetection": true,
      "guidance": 0,
      "height": 64,
      "hideResults": true,
      "image": "image",
      "imageId": "imageId",
      "intermediateImages": true,
      "ipAdapterImage": "ipAdapterImage",
      "ipAdapterImageId": "ipAdapterImageId",
      "ipAdapterImageIds": [
        "string"
      ],
      "ipAdapterImages": [
        "string"
      ],
      "ipAdapterScale": 0,
      "ipAdapterScales": [
        0
      ],
      "ipAdapterType": "character",
      "mask": "mask",
      "maskId": "maskId",
      "modality": "modality",
      "modelEpoch": "modelEpoch",
      "negativePrompt": "negativePrompt",
      "negativePromptStrength": 0,
      "numInferenceSteps": 1,
      "numSamples": 1,
      "referenceAdain": true,
      "referenceAttn": true,
      "scheduler": "DDIMScheduler",
      "seed": "seed",
      "strength": 0.01,
      "styleFidelity": 0,
      "width": 64
    },
    "updatedAt": "updatedAt"
  }
}