OptionalbpmOptionalcomposerEnable AI composer mode for higher quality music generation (default: true). Disable for faster generation or when using reference audio. Maps to generate_audio_codes in the ComfyUI workflow.
OptionalcreativityComposition variation / temperature (0-2, default: 0.85). Higher = more creative, lower = more predictable. Maps to temperature in the ComfyUI workflow.
OptionaldisableNSFWFilterDisable NSFW filter for Project. Default is false, meaning NSFW filter is enabled. If image triggers NSFW filter, it will not be available for download.
OptionaldurationDuration of the audio in seconds (10-600, default: 30)
OptionalguidanceGuidance scale. For most Stable Diffusion models, optimal value is 7.5.
For video models: Regular models range 0.7-8.0, LoRA version (lightx2v) range 0.7-1.6, step 0.01.
This maps to guidanceScale in the keyFrame for both image and video models.
OptionalkeyscaleKey/scale setting (e.g., "C major", "A minor"). Omitted to use server default.
OptionallanguageLyrics language code (default: en)
OptionallorasArray of LoRA IDs to apply. Available LoRAs are model-specific. The worker will download the LoRA if not already present on the persistent volume. LoRA IDs are resolved to filenames via the worker config API. Example: ['multiple_angles']
OptionalloraArray of LoRA strengths corresponding to each LoRA in the loras array. Values should be between 0.0 and 2.0. Defaults to 1.0 if not specified. Example: [0.9]
OptionallyricsSong lyrics. Omit for instrumental generation.
ID of the model to use, available models are available in the availableModels property of the ProjectsApi instance.
OptionalnegativePrompt for what to be avoided. If not provided, server default is used.
OptionalnetworkOverride current network type. Default value can be read from sogni.account.currentAccount.network
Number of media files to generate. Depending on project type, this can be number of images or number of videos.
OptionaloutputOutput audio format. Can be 'mp3', 'flac', or 'wav'. Defaults to 'mp3'.
Prompt for what to be created
OptionalpromptHow closely the AI composer follows your prompt (0-10, default: 2.0). Higher values = stricter prompt adherence. Maps to cfg_scale in the ComfyUI workflow.
OptionalsamplerSampler, available options depend on the model.
OptionalschedulerScheduler, available options depend on the model.
OptionalseedSeed for one of images in project. Other will get random seed. Must be Uint32
OptionalshiftShift parameter for ModelSamplingAuraFlow (1-6, default: 3 for turbo). Controls how denoising effort is distributed across generation steps. Higher values front-load structure/composition, producing more coherent arrangements. Lower values distribute effort evenly, focusing more on detail/texture. Official ComfyUI template uses shift=3 for ACE-Step 1.5 Turbo.
OptionalstepsNumber of steps. For most Stable Diffusion models, optimal value is 20.
OptionalstyleImage style prompt. If not provided, server default is used.
OptionaltimesignatureTime signature (2, 3, 4, or 6 - default: 4)
OptionaltokenSelect which tokens to use for the project. If not specified, the Sogni token will be used.
Beats per minute (30-300, default: 120)