sandbase-ai/creative-upscaler

Name: Creative Upscaler
Author: sandbase-ai

Creative Upscaler is sandbase-ai's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.

Input

Prompt(string)

The prompt to use for generating the image. Be as descriptive as possible for best results. If no prompt is provide BLIP2 will be used to generate a prompt.

Image URL or upload(string)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum

The image to upscale.

This field is required.

Guidance scale (CFG)(number)

016

The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. Range: 0 to 16.

Num Inference Steps(integer)

1200

The number of inference steps to use for generating the image. The more steps the better the image will be but it will also take longer to generate. Range: 1 to 200.

Prompt Suffix(string)

The suffix to add to the prompt. This is useful to add a common ending to all prompts such as 'high quality' etc or embedding tokens.

Additional Lora Scale(number)

The scale of the additional LORA model to use for the upscaling. Default is 1.0

Base Model Url(string)

The URL to the base model to use for the upscaling

Model Type(string)

The type of model to use for the upscaling. Default is SD_1_5 Allowed values: SD_1_5, SDXL.

Scale(number)

The scale of the output image. The higher the scale, the bigger the output image will be. Range: 1 to 5.

Additional Embedding Url(string)

The URL to the additional embeddings to use for the upscaling. Default is None

Detail(number)

How much detail to add Range: 0 to 5.

Skip Ccsr(boolean)

If set to true, the image will not be processed by the CCSR model before being processed by the creativity model.

Shape Preservation(number)

How much to preserve the shape of the original image Range: 0 to 3.

Creativity(number)

How much the output can deviate from the original Range: 0 to 1.

Enable Safety Checks(boolean)

If set to true, the resulting image will be checked whether it includes any potentially unsafe content. If it does, it will be replaced with a black image.

Additional Lora Url(string)

The URL to the additional LORA model to use for the upscaling. Default is None

Override Size Limits(boolean)

Allow for large uploads that could take a very long time.

Seed(integer)

The same seed and the same prompt given to the same version of Stable Diffusion will output the same image every time.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDsandbase-ai/creative-upscaler

Input Schema

18 parameters · 2 required · 16 optional

Parameter	Type	Required	Description
`image`	string	Required	The image to upscale.
`prompt`	string	Required	The prompt to use for generating the image. Be as descriptive as possible for best results. If no prompt is provide BLIP2 will be used to generate a prompt.
`seed`	integer	Optional	The same seed and the same prompt given to the same version of Stable Diffusion will output the same image every time.
`scale`	number	Optional	The scale of the output image. The higher the scale, the bigger the output image will be. · Min: 1 · Max: 5 · Default: 2
`detail`	number	Optional	How much detail to add · Min: 0 · Max: 5 · Default: 1
`skip_ccsr`	boolean	Optional	If set to true, the image will not be processed by the CCSR model before being processed by the creativity model. · Default: false
`creativity`	number	Optional	How much the output can deviate from the original · Min: 0 · Max: 1 · Default: 0.5
`model_type`	string	Optional	The type of model to use for the upscaling. Default is SD_1_5 · Options: SD_1_5, SDXL · Default: "SD_1_5" SD_1_5SDXL
`prompt_suffix`	string	Optional	The suffix to add to the prompt. This is useful to add a common ending to all prompts such as 'high quality' etc or embedding tokens. · Default: " high quality, highly detailed, high resolution, sharp"
`base_model_url`	string	Optional	The URL to the base model to use for the upscaling
`guidance_scale`	number	Optional	The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. · Min: 0 · Max: 16 · Default: 7.5
`shape_preservation`	number	Optional	How much to preserve the shape of the original image · Min: 0 · Max: 3 · Default: 0.25
`additional_lora_url`	string	Optional	The URL to the additional LORA model to use for the upscaling. Default is None
`num_inference_steps`	integer	Optional	The number of inference steps to use for generating the image. The more steps the better the image will be but it will also take longer to generate. · Min: 1 · Max: 200 · Default: 20
`enable_safety_checks`	boolean	Optional	If set to true, the resulting image will be checked whether it includes any potentially unsafe content. If it does, it will be replaced with a black image. · Default: true
`override_size_limits`	boolean	Optional	Allow for large uploads that could take a very long time. · Default: false
`additional_lora_scale`	number	Optional	The scale of the additional LORA model to use for the upscaling. Default is 1.0 · Default: 1
`additional_embedding_url`	string	Optional	The URL to the additional embeddings to use for the upscaling. Default is None

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "sandbase-ai/creative-upscaler",
  "seed": 42,
  "image": "https://static.sandbase.ai/examples/bytedance/seedvr/upscale/image/input_image_0.png",
  "scale": 2,
  "detail": 1,
  "skip_ccsr": false,
  "creativity": 0.5,
  "model_type": "SD_1_5",
  "prompt_suffix": " high quality, highly detailed, high resolution, sharp",
  "guidance_scale": 7.5,
  "shape_preservation": 0.25,
  "num_inference_steps": 20,
  "enable_safety_checks": true,
  "override_size_limits": false,
  "additional_lora_scale": 1,
  "prompt": "a beautiful sunset over mountains"
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to Creative Upscaler

API README

Creative Upscaler

Creative Upscaler occupies the image-enlargement role in the model catalog for creative-operations teams. Its practical value is to separate this job from adjacent family routes: an upstream service can confirm that it has prompt, image, submit one well-scoped job, and receive an enhanced image asset for downstream approval. This positioning explains when the exact sandbase-ai/creative-upscaler route belongs in an architecture without borrowing promises from another version, tier, or task variant.

A dependable operating cycle begins by checking the campaign objective, review rubric, and export requirement. The caller records required values separately from optional choices such as seed, scale, detail, skip_ccsr, creativity, model_type, runs a small representative sample, and stores the route name with the resulting artifact. Reviewers then compare that artifact with the agreed acceptance criteria, document any rejected setup, and promote only a successful request shape into larger batches. This workflow gives sandbase-ai/creative-upscaler measurable business context while leaving the Highlights section to explain model behavior.

Highlights

Detail-conscious enlargement. Creative Upscaler increases image scale while reconstructing texture that basic interpolation would leave soft.
Source-guided enhancement. The original image remains the visual anchor, so Creative Upscaler improves presentation without asking for a new scene.
Finishing-stage utility. Creative Upscaler fits after selection, when a chosen visual needs cleaner edges and more usable display dimensions.
Creative recovery. This route can strengthen perceived detail in compressed or undersized source material before export.

Pricing

Billing option	Price
Per request	`$0.001250`

When to Use

Scenario	Why it fits
Choose Creative Upscaler	Use it when the job specifically calls for creative upscaler and the route’s documented input contract matches assets already available in your workflow.
Keep the request reproducible	Use the required `image`, `prompt` explicitly, then record optional choices alongside the prompt for repeatable reruns.
Build controlled creative variations	Change one declared control at a time when comparing framing, format, duration, resolution, style, or other route-supported output decisions.
Integrate asynchronous delivery	Use this endpoint when an application can submit work, track completion, and collect the returned media URL instead of requiring an immediate inline artifact.
Validate before a large batch	Run representative prompts and source assets first, confirm the visual or audio behavior, then lock the successful request shape for scaled production.

Prompt Guide

Lead with the subject or transformation, then add the composition, environment, style, lighting, motion, voice, or fidelity details relevant to this route. Keep every parameter inside the documented schema; the example below uses only fields declared for sandbase-ai/creative-upscaler.

{
  "image": "https://static.sandbase.ai/examples/bytedance/seedvr/upscale/image/input_image_0.png",
  "prompt": "A polished editorial composition with clear subject, lighting, color, and camera direction.",
  "model_type": "SD_1_5"
}

Technical Specs

Specification	Details
Model ID	`sandbase-ai/creative-upscaler`
Execution mode	`async`
Task type	`image`
`seed`	`integer` · optional
`image`	`string` · required
`scale`	`number` · optional · min `1` · max `5`
`detail`	`number` · optional · min `0` · max `5`
`prompt`	`string` · required
`skip_ccsr`	`boolean` · optional
`creativity`	`number` · optional · min `0` · max `1`
`model_type`	`string` · optional · choices: `SD_1_5`, `SDXL`
`prompt_suffix`	`string` · optional
`base_model_url`	`string` · optional
`guidance_scale`	`number` · optional · min `0` · max `16`
`shape_preservation`	`number` · optional · min `0` · max `3`
`additional_lora_url`	`string` · optional
`num_inference_steps`	`integer` · optional · min `1` · max `200`
`enable_safety_checks`	`boolean` · optional
`override_size_limits`	`boolean` · optional
`additional_lora_scale`	`number` · optional
`additional_embedding_url`	`string` · optional