Which settings appear, their allowed values, and their defaults vary by model. A node’s config panel is the source of truth for the model you’ve selected. Not every model exposes every setting below, and some are only available on specific tiers.
Format and composition
Controls for the shape, size, and encoding of the output.string
Width-to-height ratio of the output, such as
1:1 or 16:9.string
Output resolution, often expressed as a preset like
720p or 1080p.string
For aspect-ratio changes, the ratio the input is reframed to.
string
For upscaling, the resolution to produce, such as
4k.string
File format of the output, such as
png or jpeg.string
Quality preset that trades render time and cost against fidelity.
string
Whether the output background is opaque or transparent.
string
How closely an edit preserves the original input image.
Prompt controls
Settings that change how the model interprets and expands your prompt.string
Describes what to avoid in the output.
boolean
Lets the model rewrite your prompt for better results before generating.
boolean
Expands a short prompt into a more detailed one automatically.
boolean
Alternate name some models use for automatic prompt expansion.
boolean
Optimizes the prompt for the model’s preferred phrasing.
boolean
Allows the model to search the web for current context while generating.
Generation strength (image and video)
Controls for how literally the model follows the prompt and how much it transforms the input.number
How strictly the model adheres to the prompt. Higher values follow it more closely.
number
Classifier-free guidance scale. Another name for prompt adherence strength on some models.
number
Number of denoising steps. More steps can add detail at the cost of speed.
number
How much the output departs from the input image. Higher values change it more.
number
How strongly reference images influence the result.
number
How strongly a style reference is applied.
boolean
Neutralizes color casts carried over from reference inputs.
string
Speed preset that trades render time against quality.
Video
Settings specific to video generation and editing.number
Length of the generated clip, in seconds. Each model supports a specific set
of lengths. In the studio this is a slider that snaps to those values, and
runs triggered through the API or MCP adjust an unsupported length to the
nearest one the model accepts. Models with a fixed clip length, or that take
their length from the source video, don’t expose this setting.
boolean
Generates a matching audio track alongside the video.
boolean
Adds generated background music to the clip.
boolean
Locks the camera in place so the shot doesn’t move.
string
How much motion the model introduces into the scene.
boolean
Retains the source clip’s audio when editing video.
boolean
Preserves the original sound rather than replacing it.
string
How a character is framed or facing in the output.
boolean
Keeps the existing audio track when upscaling video.
string
Speed-versus-quality preset for the render.
string
Quality preset for the produced video.
Upscale (image)
Image upscalers expose detail controls that shape how much the model invents versus preserves. The most common ones:number
Upscale factor, such as
2 or 4.number
How much new detail the model may add. Higher values invent more.
number
How closely the result stays true to the original image.
number
How much fine, repeating texture detail is introduced.
number
Strength of high-dynamic-range enhancement.
number
Amount of sharpening applied to the result.
boolean
Applies dedicated restoration to faces. Some models add
face_enhancement_strength and face_enhancement_creativity to tune it.string
Tunes the upscaler for a content type, such as photos or art.
string
Selects the underlying upscaling engine when a model offers more than one.
string
Upscaling mode the model runs in.
Upscalers vary widely. Beyond these, individual models expose their own detail knobs; the config panel lists every control available for the model you pick.
Speech (text-to-speech)
Settings that shape synthesized voice.number
Consistency of the voice. Higher values are steadier; lower values are more expressive.
number
How closely the output matches the source voice.
number
How much stylistic exaggeration is applied to the delivery.
number
Speaking rate of the voice.
Music
Settings for music generation.number
Length of the generated track, in seconds.
boolean
Generates an instrumental track with no vocals.
Text and LLMs
Settings for text-generation models.string
How much the model reasons before answering. Higher effort can improve quality at the cost of speed.
boolean
Allows the model to search the web for current information.
string
Constrains the output to a structured format using a predefined schema.