Request header parameters
AuthorizationstringRequired
Accept-Encodingstring
Request Body parameters
model_namestringRequired
This parameter specifies the name of the model checkpoint. Retrieve the corresponding sd_name_in_api value by invoking the https://novita.ai/reference/model/query_model.html endpoint with type=checkpoint as the query parameter.
input_imagestringRequired
The base64 of input image, with a maximum resolution of 2048 * 2048 and a max file size of 30 Mb, the returned image will be the same with size of input images.
promptstringRequired
Text input required to guide the image generation, divided by `,`, Range [1, 1024].
negative_promptstring
Text input that will not guide the image generation, divided by `,`, you can also add embedding (textual inversion) models like `badhandv4_16755`,Range: [1, 1024]
image_numintegerRequired
Image numbers. Range: [1, 16]
sd_vaestringRequired
VAE(Variational Auto Encoder),sd_vae can be access in api /v3/models with query params type=vae, like sd_name_in_api: customVAE.safetensors, get reference at https://novita.ai/get-started/Misc.html#what-s-variational-autoencoders-vae.
loras[object]
LoRA is a fast and lightweight training method that inserts and trains a significantly smaller number of parameters instead of all the model parameters. Currenlty supports up to 5 LoRAs.
Show propertiesembeddings[object]
Textual Inversion is a training method for personalizing models by learning new text embeddings from a few example images, currenlty supports up to 5 embeddings.
Show propertiesstepsintegerRequired
The number of denoising steps. More steps usually can produce higher quality images, but take more time to generate, Range: [1, 8]
guidance_scalenumberRequired
This setting says how close the Stable Diffusion will listen to your prompt, higer guidance forces the model to better follow the prompt, but result in lower quality output, Range [0, 3].
seedintegerRequired
A seed is a number from which Stable Diffusion generates noise, which, makes generation deterministic. Using the same seed and set of parameters will produce identical image each time, minimum -1.
clip_skipinteger
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, Range [1, 12], get reference at https://novita.ai/get-started/Misc.html#what-s-clip-skip.
strengthnumber¦null
The lower the strength, the more closely the output images will resemble the input image, Range: [0, 1]
Responses
images[object]
Image information.
Show properties