Text to Image V2

POST

txt2img

object

extra

object

enable_nsfw_detection

boolean

nsfw_detection_level

integer

enable_progress_info

object

response_image_type

string

prompt

string

negative_prompt

string

sampler_name

string

batch_size

integer

n_iter

integer

steps

integer

cfg_scale

integer

seed

integer

height

integer

width

integer

model_name

string

restore_faces

boolean

restore_faces_model

null

sd_vae

object

clip_skip

integer

enable_hr

object

hr_upscaler

object

hr_scale

object

hr_resize_x

object

hr_resize_y

object

img_expire_ttl

object

sd_refiner

object

checkpoint

string

switch_at

number

controlnet_units

object

model

string

weight

object

input_image

string

module

string

control_mode

object

mask

object

resize_mode

object

processor_res

integer

threshold_a

integer

threshold_b

integer

guidance_start

number

guidance_end

number

pixel_perfect

boolean

The Text-to-Image V2 API is deprecated and will be removed in the future. Please migrate to Text-to-Image V3.

POST Text to Image V2

The text-to-image endpoint will return only a task_id. You should use the task_id to call the /v2/progress API endpoint to retrieve the image generation results. We will gradually phase out the V2 endpoints. It is recommended to use the V3 endpoints to generate images.

Request Headers

Authorization

string

required

Request Body

extra

object

prompt

string

required

Positive prompt words, separated by ,. If you want to use LoRA, you can call the /v3/model endpoint with the parameter filter.types=lora to retrieve the sd_name_in_api field as the model_name. Remember that the format for LoRA models is <lora:$sd_name:$weight>.

negative_prompt

string

required

Negative prompt words, separated by ,.

sampler_name

string

required

This denoising process is called sampling because Stable Diffusion generates a new sample image at each step.
Enum: DPM++ 2M Karras, DPM++ SDE Karras, DPM++ 2M SDE Exponential, DPM++ 2M SDE Karras, Euler a, Euler, LMS, Heun, DPM2, DPM2 a, DPM++ 2S a, DPM++ 2M, DPM++ SDE, DPM++ 2M SDE, DPM++ 2M SDE Heun, DPM++ 2M SDE Heun Karras, DPM++ 2M SDE Heun Exponential, DPM++ 3M SDE, DPM++ 3M SDE Karras, DPM++ 3M SDE Exponential, DPM fast, DPM adaptive, LMS Karras, DPM2 Karras, DPM2 a Karras, DPM++ 2S a Karras, Restart, DDIM, PLMS, UniPC

batch_size

integer

required

The number of images generated in one single generation. Range: [0, 8]

n_iter

integer

required

The number of generations. Range: [0, 8]

steps

integer

required

Think of steps as iterations in the image creation process. Range: (0, 50]

cfg_scale

integer

required

This setting determines how closely Stable Diffusion will adhere to your prompt. Range: (0, 30]

seed

integer

required

A seed is a number from which Stable Diffusion generates noise.

height

integer

required

Height of the image. Range: (0, 2048]

width

integer

required

Width of the image. Range: (0, 2048]

model_name

string

required

Name of the Stable Diffusion model. You can call the /v3/model endpoint with the parameter filter.types=checkpoint to retrieve the sd_name_in_api field as the model_name.

restore_faces

boolean

required

Enable the Stable Diffusion face restoration plugin.

restore_faces_model

null

required

sd_vae

string¦null

VAE (Variational Auto Encoder). sd_vae can be accessed in the API /v3/model with query parameters filter.types=vae to retrieve the sd_name field as the sd_vae.

clip_skip

integer

This parameter indicates the number of layers to stop from the bottom during optimization, so clip_skip on 2 would mean, that in SD1.x model where the CLIP has 12 layers, you would stop at 10th layer.

enable_hr

boolean¦null

Hires.fix function switch.

hr_upscaler

string¦null

Upscalers model names. AI upscalers are models trained with massive amounts of data.
Enum: Latent, ESRGAN_4x, R-ESRGAN 4x+, R-ESRGAN 4x+ Anime6B

hr_scale

number¦null

The magnification factor of the image, if params hr_resize_x and hr_resize_y are set, this parameter will be ignored.
Enum: 1, 2

hr_resize_x

integer¦null

The target image width, the maximum image size is 2048, only take effect when parameters hr_scale=1.

hr_resize_y

integer¦null

The target image hight, the maximum image size is 2048, only take effect when parameters hr_scale=1.

img_expire_ttl

integer¦null

Image storage time (seconds). Range [0, 604800]

sd_refiner

object¦null

Refiner infos to enhances the image details.

controlnet_units

object[]¦null

ControlNet.

model

string

required

Model to use on the image passed to this unit before using it for conditioning. ***Controlnets for SD 1.5: control_v11e_sd15_ip2p, control_v11e_sd15_shuffle, control_v11f1e_sd15_tile, control_v11f1p_sd15_depth, control_v11p_sd15_canny, control_v11p_sd15_inpaint, control_v11p_sd15_lineart, control_v11p_sd15_mlsd, control_v11p_sd15_normalbae, control_v11p_sd15_openpose, control_v11p_sd15_scribble, control_v11p_sd15_seg, control_v11p_sd15_softedge, control_v11p_sd15s2_lineart_anime, ip-adapter-plus-face_sd15, ip-adapter_sd15_plus, ip-adapter_sd15; ***Controlnets for SDXL: t2i-adapter_diffusers_xl_canny, t2i-adapter_diffusers_xl_depth_midas, t2i-adapter_diffusers_xl_depth_zoe, t2i-adapter_diffusers_xl_lineart, t2i-adapter_diffusers_xl_openpose, t2i-adapter_diffusers_xl_sketch, t2i-adapter_xl_canny, t2i-adapter_xl_openpose, t2i-adapter_xl_sketch, ip-adapter_xl

weight

number¦null

required

weight of this unit. defaults to 1

input_image

string

required

base64 of input image

module

string

required

preprocessor to use on the image passed to this unit before using it for conditioning.
Enum: none, canny, depth, depth_leres, depth_leres++, hed, hed_safe, mediapipe_face, mlsd, normal_map, openpose, openpose_hand, openpose_face, openpose_faceonly, openpose_full, clip_vision, color, pidinet, pidinet_safe, pidinet_sketch, pidinet_scribble, scribble_xdog, scribble_hed, segmentation, threshold, depth_zoe, normal_bae, oneformer_coco, oneformer_ade20k, lineart, lineart_coarse, lineart_anime, lineart_standard, shuffle, tile_resample, invert, lineart_anime_denoise, reference_only, reference_adain, reference_adain+attn, inpaint, inpaint_only, inpaint_only+lama, tile_colorfix, tile_colorfix+sharp, depth_anything

control_mode

integer¦null

required

0 for Balanced,1 for My prompt is more important 2 for ControlNet is more important
Enum: 0, 1, 2

mask

string¦null

Base64 of mask images, support jpg, jpeg and png format images. Only take effect when controlnet_units.model set to control_v11p_sd15_inpaint.

resize_mode

integer¦null

How to resize the input image so as to fit the output resolution of the generation. 0 represent JUST_RESIZE, 1 represent RESIZE_OR_CORP, 2 represent RESIZE_AND_FILL
Enum: 0, 1, 2

processor_res

integer

Resolution of the preprocessor.

threshold_a

integer

First parameter of the preprocessor, only takes effect when preprocessor accepts arguments.

threshold_b

integer

Second parameter of the preprocessor, only takes effect when preprocessor accepts arguments.

guidance_start

number

ratio of generation where this unit starts to have an effect.

guidance_end

number

ratio of generation where this unit stops to have an effect.

pixel_perfect

boolean

Enable pixel-perfect preprocessor, when set to false, it means not to resize images.

Response

code

integer

msg

string

data

object

Example

request

curl --location 'https://api.novita.ai/v2/txt2img' \
--header 'Authorization: Bearer {{API Key}}' \
--header 'Content-Type: application/json' \
--data '{
  'extra': {
    'enable_nsfw_detection': false,
    'nsfw_detection_level': 0,
    'enable_progress_info': false
  },
  'prompt': 'Luxury suite design, Spacious suite area, Luxuriously plush large bed, Refined office desk, Carefully selected furniture for the luxurious suite, High-end and opulent decor, Private office and lounge area, Comfortably luxurious office chair, Amenities for luxury travelers, Premium bedding and linens, Uniquely designed lighting fixtures, Luxurious suite curtain design, Private work corner, Luxurious amenities, Lavish lounge area, Sophisticated indoor plant, decorations, Exquisite luxury design, Exclusive services for the luxury suite, Luxury color scheme. Exclusive furniture for the luxury suite, a bedroom with a large bed and a desk',
  'negative_prompt': '(badhandv4:1.2),(worst quality:2),(low quality:2),(normal quality:2),lowres,bad anatomy,bad hands,((monochrome)),((grayscale)) watermark,moles, easynegative ng_deepnegative_v1_75t, (oversized head:2), (big head:2), (deformed face:1.5),( blurry face:2), bad eyes, irregular eyes, asymmetric eyes, ugly, teeth, (navel:0.9), artefact, jpg artefact, blurry face, blurry, blurred, pixelated, bad eyes, crossed eyes, blurry eyes',
  'sampler_name': 'DPM++ 2M Karras',
  'batch_size': 1,
  'n_iter': 1,
  'steps': 25,
  'cfg_scale': 7,
  'seed': -1,
  'height': 512,
  'width': 512,
  'model_name': 'sd_xl_base_0.9.safetensors',
  'restore_faces': false,
  'restore_faces_model': '',
  'sd_vae': '',
  'clip_skip': 1,
  'enable_hr': false,
  'hr_upscaler': 'Latent',
  'hr_scale': 1,
  'hr_resize_x': null,
  'hr_resize_y': null,
  'img_expire_ttl': null,
  'sd_refiner': {
    'checkpoint': 'sd_xl_refiner_1.0.safetensors',
    'switch_at': null
  },
  'controlnet_units': [
    {
      'model': '',
      'weight': null,
      'input_image': '',
      'module': 'none',
      'control_mode': 0,
      'mask': '',
      'resize_mode': 0,
      'processor_res': null,
      'threshold_a': null,
      'threshold_b': null,
      'guidance_start': null,
      'guidance_end': null,
      'pixel_perfect': false
    }
  ]
}'

response

{
  "code": 0,
  "msg": "",
  "data": {
    "task_id": "d4cf3973-8414-4a5e-aa6f-ef54caf73662"
  }
}

Was this page helpful?

List LoRA Training Task Image to Image V2

Basic

Model APIs

GPUs

POST Text to Image V2

Request Headers

Request Body

Response

Example

Basic

Model APIs

GPUs

​POST Text to Image V2

​Request Headers

​Request Body

​Response

​Example

POST Text to Image V2

Request Headers

Request Body

Response

Example