Start building

Clarity Upscaler

clarity-ai/clarity-upscaler

Clarity Upscaler by ClarityAI - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortlessly.

Use in agentGet API key
Base price
$0.03 / run
Execution
async
Model type
image
Input fields
8

Try the model

Playground

Open playground
Input
The prompt to use for generating the image. Be as descriptive as possible for best results.

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

The URL of the image to upscale.
020
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 20.
450
The number of inference steps to perform. Range: 4 to 50.
The same seed and the same prompt given to the same version of Stable Diffusion will output the same image every time. Minimum: 0.
14
The upscale factor Range: 1 to 4.
01
The resemblance of the upscaled image to the original image. The higher the resemblance, the more the model will try to keep the original image. Refers to the strength of the ControlNet. Range: 0 to 1.
01
The creativity of the model. The higher the creativity, the more the model will deviate from the prompt. Refers to the denoise strength of the sampling. Range: 0 to 1.
OutputReady

Your output will appear here

Complete the inputs, then click Run.

Specifications

Pricing

Base price
$0.03 / run

Context & modalities

Input
Schema-defined
Output
image

Capabilities

Chat
Not supported
Vision
Not supported
Reasoning
Not supported
Structured output
Not supported
Function calling
Not supported
Audio input
Not supported

Access

Provider
ClarityAI
Model ID
clarity-ai/clarity-upscaler
Execution
async
API
Unified Run API
Endpoint
/v1/run

API README

Clarity Upscaler

clarity-ai/clarity-upscaler enhances a low-resolution or soft image into a cleaner, more detailed result intended for larger displays and closer inspection. Its restoration process aims to reconstruct plausible texture and edge definition while retaining the source image's overall structure, subject, and visual character. This combination makes the model a practical choice when the creative outcome depends on those qualities rather than on a generic media conversion.

For production work, The model is suited to photographs, generated artwork, product imagery, and older web assets that need a more polished master without redesigning the composition. The result is most reliable when the source material and creative brief clearly describe the intended subject, progression, visual or sonic character, and the qualities that must remain unchanged.

Highlights

Detail reconstruction restores fine surface information lost in small or compressed sources.

Structure preservation maintains the original composition and recognizable subject.

Artifact cleanup reduces softness and compression-related degradation during enlargement.

High-resolution finishing prepares existing imagery for larger placements and crops.

Pricing

Billing unitPrice
Per request$0.03

When to Use

✅ Good fit❌ Consider alternatives
The model's named workflow matches the source material and intended outputA different input modality or model route is required
A managed asynchronous result is suitable for the production pipelineA synchronous, interactive editor is essential
The documented controls cover the required duration, framing, or formatThe project needs controls outside this endpoint's schema
Creative iteration benefits from a repeatable request structureExact deterministic pixels, frames, geometry, or samples are mandatory
A finished downloadable media asset is the desired deliverableEditable source layers or a native project file are required

Prompt Guide

For image-conditioned generation, state the intended result first, then add the subject or source treatment, progression, style, and delivery constraints. Keep one creative variable per phrase, use the documented field names for controls, and change one setting at a time when comparing results.

{
  "image": "https://static.sandbase.ai/examples/bytedance/seedvr/upscale/image/input_image_0.png",
  "prompt": "masterpiece, best quality, highres"
}

Technical Specs

SpecValue
Model IDclarity-ai/clarity-upscaler
Inputscreativity, guidance_scale, image, num_inference_steps, prompt, resemblance, seed, upscale_factor
Required inputsprompt, image
Output fieldscontent_type, url
ExecutionAsync (submit, then poll for result)

Related Models

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API
Endpoint
https://api.sandbase.ai/v1/run
Model ID
clarity-ai/clarity-upscaler
# Preserve Unicode and shell metacharacters in the request body.
result=$(printf '%s' 'ewogICJtb2RlbCI6ICJjbGFyaXR5LWFpL2NsYXJpdHktdXBzY2FsZXIiLAogICJpbWFnZSI6ICJodHRwczovL3N0YXRpYy5zYW5kYmFzZS5haS9leGFtcGxlcy9ieXRlZGFuY2Uvc2VlZHZyL3Vwc2NhbGUvaW1hZ2UvaW5wdXRfaW1hZ2VfMC5wbmciLAogICJwcm9tcHQiOiAibWFzdGVycGllY2UsIGJlc3QgcXVhbGl0eSwgaGlnaHJlcyIsCiAgImNyZWF0aXZpdHkiOiAwLjM1LAogICJyZXNlbWJsYW5jZSI6IDAuNiwKICAiZ3VpZGFuY2Vfc2NhbGUiOiA0LAogICJ1cHNjYWxlX2ZhY3RvciI6IDIsCiAgIm51bV9pbmZlcmVuY2Vfc3RlcHMiOiAxOAp9' \
  | base64 --decode \
  | curl --fail-with-body --silent \
      -X POST "https://api.sandbase.ai/v1/run" \
      -H "Authorization: Bearer $SANDBASE_API_KEY" \
      -H "Content-Type: application/json" \
      --data-binary @-)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All language models
ModelContextInput / 1MOutput / 1MReleased
Clarity UpscalerThis model
ClarityAI		———Feb 4, 2024