RunDiffusion: Juggernaut Z
juggernaut-z- Price
- From $0.0149
- Modalities
- Image
About Juggernaut Z
Juggernaut Z is a cinematic fine-tune of Z-Image Base from Team Juggernaut, trained by KandooAI and released through RunDiffusion. It is tuned for presentation-ready output: dramatic lighting, sharp camera focus, natural skin texture, and cleaner anatomy. Its character is portraits, fashion, architecture, and concept scenes with a polished, filmic feel.
Where it works well
- Dramatic, cinematic lighting with a deliberate camera-focus look, as described on the model card.
- Portraits with cleaner facial detail and natural skin texture, which the model card lists as a tuned area.
- Improved anatomy and scene composition compared with the Z-Image Base it was trained from.
- The base model is six billion parameters, and the card lists LoRAs trained on Z-Image Base as compatible.
When to choose another model
- Its polished, cinematic bias is wrong for flat, neutral, or documentary-looking images.
- The model card describes text-to-image tuning, so editing an existing picture is a secondary use next to prompting for new ones.
Getting started
Create API key
Create a key in Console, then use it with every model on the platform.
Send your first request
Copy the example for your language and run it against the endpoint.
Image editingText to imageTokenLab endpointPOST/v1/images/generationscurl -X POST "https://api.tokenlab.sh/v1/images/generations" \ -H "Authorization: Bearer sk-xxx" \ -H "Content-Type: application/json" \ -d '{ "operation": "image-to-image", "model": "juggernaut-z", "prompt": "A minimalist product photo of matte black headphones on a soft blue background.", "image_url": "https://example.com/source.png" }'
Parameters
Image editing
| Parameter | Values and limits | Default | Notes |
|---|---|---|---|
cfg_scale | ≥ 0, ≤ 20 | Not provided | Use multiples of 0.01. |
guidance_scale | ≥ 0, ≤ 20 | Not provided | Use multiples of 0.01. |
height | ≥ 128, ≤ 2048 | 1024 | Use an integer. Use multiples of 16. |
image | Not provided | Not provided | Alias of the combined images input. See input_limits.images for the total input image count. |
image_url | Not provided | Not provided | Alias of the combined images input. See input_limits.images for the total input image count. |
image_urls | Not provided | Not provided | Alias of the combined images input. See input_limits.images for the total input image count. |
images | Inputs: ≥ 1, ≤ 1 | Not provided | Limits apply when this input is supplied. Image aliases are combined into one input image list; the limit applies to the combined list. |
mask_url | Not provided | Not provided | Mask: a public image URL or a data URL. White marks the area to repaint, black is kept. It applies to the source image. |
n | 1 | 1 | Use an integer. |
negative_prompt | Not provided | Not provided | Minimum length: 2 characters. Maximum length: 3000 characters. |
operationRequired | Not provided | Not provided | Not provided |
output_format | jpeg, png, webp | Not provided | Default encoding is shared by these equivalent values: jpg, jpeg. |
prompt | Not provided | Not provided | Minimum length: 2 characters. Maximum length: 10000 characters. |
seed | ≥ 0, ≤ 9007199254740991 | Not provided | Use an integer. |
steps | ≥ 1, ≤ 50 | 35 | Use an integer. |
width | ≥ 128, ≤ 2048 | 1024 | Use an integer. Use multiples of 16. |
Text to image
| Parameter | Values and limits | Default | Notes |
|---|---|---|---|
cfg_scale | ≥ 0, ≤ 20 | Not provided | Use multiples of 0.01. |
guidance_scale | ≥ 0, ≤ 20 | Not provided | Use multiples of 0.01. |
height | ≥ 128, ≤ 2048 | 1024 | Use an integer. Use multiples of 16. |
images | Not provided | Not provided | Text-to-image does not accept source images. Do not send this field for that operation. Use one of this model's declared image operations for source-image requests. |
n | 1 | 1 | Use an integer. |
negative_prompt | Not provided | Not provided | Minimum length: 2 characters. Maximum length: 3000 characters. |
operationRequired | Not provided | Not provided | Not provided |
output_format | jpeg, png, webp | Not provided | Default encoding is shared by these equivalent values: jpg, jpeg. |
prompt | Not provided | Not provided | Minimum length: 2 characters. Maximum length: 10000 characters. |
seed | ≥ 0, ≤ 9007199254740991 | Not provided | Use an integer. |
steps | ≥ 1, ≤ 50 | 35 | Use an integer. |
width | ≥ 128, ≤ 2048 | 1024 | Use an integer. Use multiples of 16. |
Fields outside this contract are rejected.
Pricing
The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.
Image editing
per request- Official price
- $0.0149
- Verified price
- —
- Discount
- —
Text to image
per request- Official price
- $0.0149
- Verified price
- —
- Discount
- —
| Official priceper request | Verified priceper request | Discount | |
|---|---|---|---|
| Image editing | $0.0149 | — | — |
| Text to image | $0.0149 | — | — |
Usage & activity
Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.
Usage & availability
Last 24 hours- Requests
- Success rate
- P95 latency
- Total tokens
Data is based on aggregate user requests, excluding status checks.
Open in Console
Open Juggernaut Z in Console with a prompt ready to edit or send.
Help me create an image with juggernaut-z using image-edit at /v1/images/edits. Show the result, cost, and any limits I should know.
Use cases
Best for- Text to Image
Portrait and fashion concepts
Create editorial portraits and lookbook ideas with strong lighting and believable skin.
Architectural visualization
Generate moody exterior and interior concept views for presentations. Good for exteriors, interiors, and building studies where light direction sets the mood.
Cinematic concept art
Sketch film and game scenes with atmosphere to establish mood boards. Useful for mood boards and key art before production design starts.
Prompt examples
Cinematic portrait of a violinist backstage, warm rim light, shallow depth of field, detailed skin texture.
Fashion editorial of a model in a red trench coat on a rainy street, dramatic lighting, sharp focus.
Brutalist concrete museum at dusk, long shadows, a single figure for scale.
FAQ
What is Juggernaut Z based on?
It is a fine-tune of Z-Image Base, the six-billion-parameter model, made by Team Juggernaut and trained by KandooAI. Because it shares that base, LoRAs trained on Z-Image Base are described as compatible.
What does Juggernaut Z do best?
Portraits, fashion, architecture, and cinematic concept work. The card cites stronger lighting, sharper focus, more refined skin texture, and cleaner anatomy over the base model.
Which settings does the maker recommend?
For its open weights, the model card suggests a guidance scale of about 6, within 6 to 9, and about 35 sampling steps, within 25 to 45. Hosted use may handle these settings for you.
Does Juggernaut Z edit images?
It supports image editing as well as text-to-image. The maker's tuning focuses on generation from prompts, so its strongest results come from new pictures with strong lighting and portrait detail.
How much does Juggernaut Z cost?
On TokenLab, Juggernaut Z costs $0.0149 per request. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
Which endpoint should Juggernaut Z use?
Use https://api.tokenlab.sh/v1/images/edits for Juggernaut Z. The request example below shows the matching code shape.
Which operations does Juggernaut Z support?
Juggernaut Z supports Image editing, Text to image. Select an operation above to see its endpoint and request example.
Compare Juggernaut Z
Sources
Reviewed Oct 2, 2026