• Currently, the Model Upload feature only supports LoRA models, with a limit of 5 uploads per user. We plan to gradually lift these restrictions in the future;
  • The Model Upload feature is temporarily available free of charge. However, we may introduce a fee for this service in the future. Please stay tuned for future announcements;
  • If you have any questions, please contact our customer service or technical team through the Discord Channel.

1. Enter the Model Upload Page

Log in to your account and click on the "Upload Model" button at the bottom of the page.

2. Click the Upload Model Button

Select the Upload Model button to upload your models.

3. Upload the LoRA Model and Fill in the Model Information

Upload the LoRA model and fill in the model information. The model name must be unique and can only contain letters, numbers, and underscores. The model name cannot be modified after submission.

4. Use the Uploaded Model

After the model is uploaded successfully, you can use the model from the model list.

"<lora:test_sd_name_in_api:1>" added in the "prompt" represents a LoRA request, in the format of <lora:${lora_name}:1>, where your lora_name can be found in the MODEL NAME IN API column.

Request:

curl --location --request POST 'https://api.novita.ai/v2/txt2img' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer {{API Key}}' \
--data-raw '{
    "model_name": "mistoonSapphire_v10_30163.safetensors",
    "width": 512,
    "height": 512,
    "prompt": "<lora:test_sd_name_in_api:1>,1girl",
    "negative_prompt": "3d render, smooth, plastic, blurry, grainy, low-resolution, anime, deep-fried, oversaturated",
    "batch_size": 1,
    "cfg_scale": 7,
    "steps": 20,
    "sampler_name": "DPM++ 2M Karras",
    "n_iter": 1,
    "seed": -1
}'