ComfyUI Node
Foundation-1 Generate
Generates a tempo-synced musical sample loop using Foundation-1. Connect Foundation1ModelLoader → model input.
Foundation-1 Generate
- model
- audio
- AUDIO
◄tagsSynth Lead, Warm, Wide, Bright, Clean, Melody►
◄bpm140 BPM►
◄bars8 Bars►
◄keyE minor►
◄steps250►
◄cfg_scale7.0►
◄seed0►
◄sampler_typedpmpp-3m-sde►
◄sigma_min0.300►
◄sigma_max500►
◄unload_after_generatefalse►
◄torch_compilefalse►
◄init_noise_level0.70►
Categoryaudio/Foundation-1
Inputs (15)
| Name | Type | Default | Description |
|---|---|---|---|
| model | FOUNDATION1_MODEL | Connect to Foundation1ModelLoader. | |
| tags | STRING | Synth Lead, Warm, Wide, Bright, Clean, Melody | Instrument, timbre, FX, and notation tags separated by commas. See the Tag Reference Sheet. Do NOT put BPM, Bars, or Key here — use the dropdowns below. |
| bpm | COMBO | 140 BPM | Tempo of the generated loop. |
| bars | COMBO | 8 Bars | Loop length in 4/4 bars. |
| key | COMBO | E minor | Musical key for the generated loop. |
| steps | INT | 25010–500 | Diffusion steps. Higher = better quality but slower. 100–250 is the practical range. The training demo used 250. |
| cfg_scale | FLOAT | 7.01–15 | Classifier-free guidance scale. Higher = stronger prompt adherence, less variation. 6–8 recommended. Training demo used 7. |
| seed | INT | 00–18446744073709550000 | Generation seed. Use ComfyUI's seed controls to randomise. |
| sampler_type | COMBO | dpmpp-3m-sde | Diffusion sampler. 'dpmpp-3m-sde' recommended for quality. 'dpmpp-2m-sde' is slightly faster. |
| sigma_min | FLOAT | 0.3000.001–10 | Minimum noise level for k-diffusion schedule. Default 0.3. |
| sigma_max | FLOAT | 50010–1000 | Maximum noise level for k-diffusion schedule. Default 500. |
| unload_after_generate | BOOLEAN | false | After generation, move the model from VRAM to CPU RAM. Frees VRAM while keeping weights in memory for a faster next run (avoids a full disk reload). When enabled, ComfyUI's native 'Free Memory' button will also clear the CPU copy. |
| torch_compile | BOOLEAN | false | Compile the model with torch.compile before the first generation. The first run after enabling will be slower (compilation warmup). Every subsequent run in the same session will be faster. Compiled state is cached — toggling off requires a model reload. Requires PyTorch 2.0+. CUDA only. Disable if you see errors. |
| audioopt | AUDIO | Optional input audio for variation generation. Connect an AUDIO output from another node (e.g. LoadAudio, or a previous Foundation1Generate output). When connected, the model will create a variation/interpretation of this audio guided by your prompt. Leave disconnected for standard text-to-audio generation. | |
| init_noise_levelopt | FLOAT | 0.700.01–1 | Variation strength when an input audio is connected. Lower values (0.1–0.3) produce output close to the input. Higher values (0.5–0.9) give more creative interpretations. 1.0 = maximum variation. Only used when audio input is connected. Recommended: 0.5–0.75 for musical variations. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| AUDIO | AUDIO | — |