Skip to main content
Glama

post-upscale-inferences

Upscale images using AI with customizable styles, presets, and parameters to enhance resolution and detail while maintaining control over fidelity and creativity.

Instructions

Trigger the upscaling of an image. You can use styles and presets to quickly get results or craft your very own settings.

Note:This endpoint is deprecated and will be removed in the future. Please leverage POST /generate/custom/{modelId} endpoint instead with model_scenario-upscale-v3 modelId for example. See https://docs.scenario.com/docs/upscale-generation for more details.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
originalAssetsNoIf set to true, returns the original asset without transformation
dryRunNo
imageYesImage to upscale. Must reference an existing AssetId or be a data URL.
creativityDecayNoAmount of decay in creativity over the upscale process. The lowest the value, the less the creativity will be preserved over the upscale process.
tileStyleNoIf set to true, during the upscaling process, the model will match tiles of the source image with tiles of the style image(s). This will result in a more coherent restyle. Works best with style images that have a similar composition.
seedNoUsed to reproduce previous results. Default: randomly generated number.
styleImagesNo
scalingFactorNoScaling factor (when `targetWidth` not specified)
presetNoOptimize the upscale for a specific use case. Precise: Upscale for high fidelity. Balanced: Upscale for a balance between fidelity and creativity. Creative: Upscale for creativity.
styleImagesFidelityNoCondition the influence of the style image(s). The higher the value, the more the style images will influence the upscaled image.
detailsLevelNoAmount of details to remove or add
fractalityNoDetermine the scale at which the upscale process works. - With a small value, the upscale works at the largest scale, resulting in fewer added details and more coherent images. Ideal for portraits, for example. - With a large value, the upscale works at the smallest scale, resulting in more added details and more hallucinations. Ideal for landscapes, for example. (info): A small value is slower and more expensive to run.
negativePromptNoA negative full text prompt that discourages the upscale from generating certain characteristics. It is recommended to test without using a negative prompt. Default: empty string. Example: "Low resolution, blurry, pixelated, noisy."
overrideEmbeddingsNoOverride the embeddings of the model. Only your prompt and negativePrompt will be used. Use with caution.
promptFidelityNoIncrease the fidelity to the prompt during upscale. Default: optimized for your preset and style.
styleNoOptimize the upscale for a specific style. standard works in most cases. Use one of the other styles to refine the outputs.
refinementStepsNoAdditional refinement steps before scaling. If scalingFactor == 1, the refinement process will be applied (1 + refinementSteps) times. If scalingFactor > 1, the refinement process will be applied refinementSteps times.
creativityNoAllow the generation of "hallucinations" during the upscale process, which adds additional details and deviates from the original image. Default: optimized for your preset and style.
imageFidelityNoStrengthen the similarity to the original image during the upscale. Default: optimized for your preset and style.
imageTypeNoPreserve the seamless properties of skybox or texture images. Input has to be of same type (seamless).
promptNoA full text prompt to guide the upscale and forcing the generation of certain characteristics. Default: empty string. Example: "UHD 8K hyper detailed studio photo of man face with yellow skin, anatomical++, disturbing+++, black background. Bloody++."
targetWidthNoTarget width for the upscaled image, take priority over scaling factor

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/pasie15/scenario.com-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server