Skip to main content
This page describes the settings you’ll encounter across Pleyor’s generation models. They’re grouped by what they control.
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.
aspect_ratio
string
Width-to-height ratio of the output, such as 1:1 or 16:9.
resolution
string
Output resolution, often expressed as a preset like 720p or 1080p.
target_aspect_ratio
string
For aspect-ratio changes, the ratio the input is reframed to.
target_resolution
string
For upscaling, the resolution to produce, such as 4k.
output_format
string
File format of the output, such as png or jpeg.
quality
string
Quality preset that trades render time and cost against fidelity.
background
string
Whether the output background is opaque or transparent.
input_fidelity
string
How closely an edit preserves the original input image.

Prompt controls

Settings that change how the model interprets and expands your prompt.
negative_prompt
string
Describes what to avoid in the output.
enhance_prompt
boolean
Lets the model rewrite your prompt for better results before generating.
enable_prompt_expansion
boolean
Expands a short prompt into a more detailed one automatically.
expand_prompt
boolean
Alternate name some models use for automatic prompt expansion.
prompt_optimizer
boolean
Optimizes the prompt for the model’s preferred phrasing.
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.
guidance_scale
number
How strictly the model adheres to the prompt. Higher values follow it more closely.
cfg_scale
number
Classifier-free guidance scale — another name for prompt adherence strength on some models.
num_inference_steps
number
Number of denoising steps. More steps can add detail at the cost of speed.
strength
number
How much the output departs from the input image. Higher values change it more.
reference_strength
number
How strongly reference images influence the result.
style_strength
number
How strongly a style reference is applied.
remove_color_bias
boolean
Neutralizes color casts carried over from reference inputs.
rendering_speed
string
Speed preset that trades render time against quality.

Video

Settings specific to video generation and editing.
duration
string | number
Length of the generated clip, in seconds.
generate_audio
boolean
Generates a matching audio track alongside the video.
generate_background_music
boolean
Adds generated background music to the clip.
camera_fixed
boolean
Locks the camera in place so the shot doesn’t move.
movement_amplitude
string
How much motion the model introduces into the scene.
keep_audio
boolean
Retains the source clip’s audio when editing video.
keep_original_sound
boolean
Preserves the original sound rather than replacing it.
character_orientation
string
How a character is framed or facing in the output.
preserve_audio
boolean
Keeps the existing audio track when upscaling video.
acceleration
string
Speed-versus-quality preset for the render.
output_quality
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:
scale
number
Upscale factor, such as 2 or 4.
creativity
number
How much new detail the model may add. Higher values invent more.
resemblance
number
How closely the result stays true to the original image.
fractality
number
How much fine, repeating texture detail is introduced.
hdr
number
Strength of high-dynamic-range enhancement.
sharpen
number
Amount of sharpening applied to the result.
face_enhancement
boolean
Applies dedicated restoration to faces. Some models add face_enhancement_strength and face_enhancement_creativity to tune it.
optimized_for
string
Tunes the upscaler for a content type, such as photos or art.
engine
string
Selects the underlying upscaling engine when a model offers more than one.
mode
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.
stability
number
Consistency of the voice. Higher values are steadier; lower values are more expressive.
similarity_boost
number
How closely the output matches the source voice.
style
number
How much stylistic exaggeration is applied to the delivery.
speed
number
Speaking rate of the voice.

Music

Settings for music generation.
duration
number
Length of the generated track, in seconds.
force_instrumental
boolean
Generates an instrumental track with no vocals.

Text and LLMs

Settings for text-generation models.
reasoning_effort
string
How much the model reasons before answering. Higher effort can improve quality at the cost of speed.
enable_web_search
boolean
Allows the model to search the web for current information.
output_schema_preset
string
Constrains the output to a structured format using a predefined schema.