← All models
Restyle any image with TeleStyle v2 — provide an original image and a styling reference, and the model re-renders the original in the reference's visual style while preserving its content and composition.
images
Details
- Accepts
- image
Pricing
- Price
- 4.38 cr / megapixel
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | — | The same seed and the same inputs given to the same version of the model will output the same image every time. |
| sync_mode | boolean | If `True`, the media will be returned as a data URI and the output data won't be available in the request history. |
| image_size | — | The size of the generated image. If not provided, the size of the content image is used. |
| lora_scale | number | Strength of the TeleStyleV2 style adapter. 1.0 matches the reference implementation; lower values apply the style more subtly. |
| num_images | integer | The number of images to generate. |
| acceleration | stringenum: none, regular | Acceleration level for image generation. 'none' (the default) honors the requested num_inference_steps, so the default 4-step Lightning configuration runs in 4 steps. 'regular' engages the downstream accelerated path, which runs a fixed 10 steps regardless of num_inference_steps. |
| output_format | stringenum: jpeg, png | The format of the generated image. |
| guidance_scale | number | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. |
| negative_prompt | string | The negative prompt for the generation. |
| style_image_urlrequired | string | URL of the style reference image — the artistic style, material, lighting and color of this image are transferred onto the content image. |
| content_image_urlrequired | string | URL of the content image — the image whose subject and structure are preserved while the style is applied. |
| use_lightning_lora | boolean | If true, use the Lightning LoRA in addition to the default LoRA. |
| num_inference_steps | integer | The number of inference steps to perform. |
| lightning_lora_scale | number | Strength of the Lightning LoRA. 1.0 matches the reference implementation; lower values apply the style more subtly. |
| enable_safety_checker | boolean | If set to true, the safety checker will be enabled. |
| use_style_description | boolean | If true, describe the style image with a VLM and add the description to the prompt. |
| use_content_description | boolean | If true, describe the content image with a VLM and add the description to the prompt. |
Output
| Field | Type | Description |
|---|---|---|
| seed | integer | The seed used for generation. |
| images | array | The stylized image(s). |
| prompt | string | The prompt derived from the content and style images. |
| has_nsfw_concepts | array | Whether the generated image contains NSFW concepts. |