curl --request POST \
--url https://api.tikway.ai/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "diffusion-4-5-full",
"prompt": "A serene Japanese garden at dawn, mist above a koi pond, cinematic lighting, highly detailed",
"negative_prompt": "lowres, blurry, text, watermark",
"size": "1024x1536",
"n": 1,
"steps": 28,
"scale": 5,
"sampler": "Euler Ancestral",
"noise_schedule": "karras"
}
'{
"created": 1713833628,
"background": "opaque",
"data": [
{
"b64_json": "...",
"index": 0
}
],
"output_format": "png",
"size": "1024x768"
}Image generation
diffusion-4-5-full uses the same parameter set as diffusion-4-5-curated: prompt, images, negative_prompt, n, size, seed, steps, scale, quality_toggle, sampler, noise_schedule, character_prompts, hook_url and response_format.
n is 1~4. A maximum of 1 ordinary image source image can be used; vibe_transfer and character_reference cannot be used at the same time. NovelAI does not have a standalone JSON editing endpoint, editing is still done through the images of this generated endpoint.
curl --request POST \
--url https://api.tikway.ai/v1/images/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "diffusion-4-5-full",
"prompt": "A serene Japanese garden at dawn, mist above a koi pond, cinematic lighting, highly detailed",
"negative_prompt": "lowres, blurry, text, watermark",
"size": "1024x1536",
"n": 1,
"steps": 28,
"scale": 5,
"sampler": "Euler Ancestral",
"noise_schedule": "karras"
}
'{
"created": 1713833628,
"background": "opaque",
"data": [
{
"b64_json": "...",
"index": 0
}
],
"output_format": "png",
"size": "1024x768"
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
NovelAI image generation Request Body. The unified reference image uses images; the gateway is responsible for converting to TTAPI NovelAI native parameters.
Required. The NovelAI Diffusion V4.5 model currently connected to TTAPI.
diffusion-4-5-full, diffusion-4-5-curated 1"diffusion-4-5-full"
"diffusion-4-5-curated"
Positive cue words.
1 - 32000Optional. Unified reference map array. type=image (or omitted) is the source image of a single image; type=vibe_transfer is the atmosphere reference; type=character_reference is the precise character/style reference. There can only be one ordinary image source image, and vibe_transfer and character_reference cannot be mixed.
16Hide child attributes
Hide child attributes
1image or null is the image source image; the remaining values represent the NovelAI reference image type.
image, vibe_transfer, character_reference, null Reference strength. The maximum value of the plot is 0.99.
0 <= x <= 1Fidelity. The graph is converted to noise = 1 - fidelity.
0 <= x <= 1Only used by character_reference.
character, style, character&style Negative cue words.
Number of images generated.
1 <= x <= 4Output dimensions, converted by gateway to width and height.
^[1-9][0-9]*x[1-9][0-9]*$Random seed.
Number of sampling steps.
x >= 1Cue words guide intensity.
Quality switch.
Euler Ancestral, Euler, DPM++ 2S Ancestral, DPM++ 2M SDE, DPM++ 2M, DPM++ SDE karras, exponential, polyexponential Fixed returning Base64 image so that the response conforms to the Response Schema of this interface.
b64_json, url Optional. The callback address when the TTAPI task completes or fails.
Response
The Unix timestamp (in seconds) when the gateway completed image conversion.
Background settings inferred from unified inbound requests; NovelAI raw responses are typically not echoed.
transparent, opaque The format inferred from the downloaded image MIME type or request output_format.
png, jpeg, webp Unified quality field; if quality is requested, the gateway will map and echo it.
low, medium, high The size of the original request; NovelAI's original response is usually not echoed.

