Neta Lumina

Playground

Neta Lumina generates high-quality anime-style images, developed by Neta.art Lab for anime illustrations and character art. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Neta Lumina

Generate stunning anime and illustration-style images with Neta Lumina — a specialized text-to-image model optimized for character art, dynamic poses, and artistic styles. With support for artist tags, character references, and custom dimensions, it’s the perfect tool for anime fans, illustrators, and creative content creators.

Why It Looks Great

Anime & illustration focus: Optimized for character art, anime styles, and illustrative aesthetics.
Artist style support: Reference specific artists using tags (e.g., @artistname:1.0) for style guidance.
Character tags: Use character references for recognizable designs and features.
Custom dimensions: Precise control over width and height for any aspect ratio.
Dynamic compositions: Excels at foreshortening, action poses, and expressive perspectives.
Prompt Enhancer: Built-in tool to refine and expand your descriptions automatically.
Multiple formats: Export as JPEG, PNG, or WebP.

Parameters

Parameter	Required	Description
prompt	Yes	Text description including style tags, character references, and scene details.
size	No	Custom dimensions with separate width and height controls.
width	No	Output width in pixels (e.g., 1024).
height	No	Output height in pixels (e.g., 1024).
seed	No	Random seed for reproducibility. Use -1 for random.
output_format	No	File format: jpeg, png, or webp. Default: jpeg.

How to Use

Write your prompt — include style tags, character references, and scene descriptions.
Use Prompt Enhancer (optional) — click to automatically enrich your description.
Set dimensions — adjust width and height sliders to your desired resolution.
Set seed (optional) — use -1 for random, or a specific number to reproduce results.
Choose output format — select jpeg, png, or webp based on your needs.
Run — click the button to generate.
Download — preview and save your image.

Pricing

Flat rate per image generation.

Output	Cost
Per image	$0.01

Best Use Cases

Character Art — Create original characters or fan art with distinctive anime aesthetics.
Dynamic Illustrations — Generate action poses, foreshortening, and expressive compositions.
Style Exploration — Experiment with different artist styles using reference tags.
Fan Art & Derivatives — Generate art featuring known characters with style variations.
Concept Art — Rapid character and scene ideation for creative projects.

Example Prompts

“foreshortening, This artwork by (@haneru:1.0) features character:#elphelt valentine in a playful and dynamic pose. The illustration showcases her upper body with a foreshortened perspective that emphasizes her outstretched hand holding food near her”
“1girl, silver hair, red eyes, gothic lolita dress, sitting on throne, dramatic lighting, detailed background”
“dynamic action pose, male warrior, sword slash motion blur, fantasy armor, epic battle scene”
“cute chibi style, cat ears, pastel colors, simple background, kawaii expression”
“portrait, detailed eyes, flowing hair, soft lighting, dreamy atmosphere, by (@artistname:0.8)“

Prompt Syntax Tips

Syntax	Purpose	Example
(@artist:weight)	Reference artist style	(@haneru:1.0)
character:#name	Reference specific character	character:#elphelt valentine
1girl, 1boy	Character count/gender	1girl, blue hair
Descriptive tags	Scene and style details	dynamic pose, foreshortening

Pro Tips for Best Results

Use artist tags with weights (0.5-1.5) to control style influence strength.
Combine character tags with style modifications for unique variations.
Include composition terms: “foreshortening”, “dynamic angle”, “close-up”, “full body”.
Describe specific features: hair color, eye color, clothing, accessories.
Square dimensions (1024×1024) work well for portraits; adjust for full-body or scenes.
Use PNG format for highest quality or WebP for smaller file sizes.

Notes

Artist and character tags work best when the model has been trained on relevant data.
Experiment with tag weights to find the right balance of style influence.
Processing is fast and affordable — ideal for rapid iteration and exploration.
Generation time may vary based on resolution and current queue load.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/neta-lumina" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "size": "1024*1024",
    "seed": -1,
    "output_format": "jpeg",
    "enable_base64_output": false,
    "enable_sync_mode": false
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

Parameter	Type	Required	Default	Range	Description
prompt	string	Yes		-	The positive prompt for the generation.
size	string	No	1024*1024	256 ~ 1536 per dimension	The size of the generated media in pixels (width*height).
seed	integer	No	-1	-1 ~ 2147483647	The random seed to use for the generation. -1 means a random seed will be used.
output_format	string	No	jpeg	jpeg, png, webp	The format of the output image.
enable_base64_output	boolean	No	false	-	If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.
enable_sync_mode	boolean	No	false	-	If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API.

Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data.id	string	Unique identifier for the prediction, Task Id
data.model	string	Model ID used for the prediction
data.outputs	array	Array of URLs to the generated content (empty when status is not `completed`)
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.has_nsfw_contents	array	Array of boolean values indicating NSFW detection for each output
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Result Request Parameters

Parameter	Type	Required	Default	Description
id	string	Yes	-	Task ID

Result Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data	object	The prediction data object containing all details
data.id	string	Unique identifier for the prediction, the ID of the prediction to get
data.model	string	Model ID used for the prediction
data.outputs	string	Array of URLs to the generated content (empty when status is not completed).
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Multitalk Openai Whisper