ace_step_15
Train an ACE-Step music LoRA on Civitai's cloud — no local GPU required
- continue_from
- api_config
- moderation_status
- epochs
- workflow_id
- raw_json
Music LoRA training, minus the GPU. CivitaiTrainingAiToolkitAceStep15 runs Ostris's AI Toolkit trainer on Civitai's cloud to train a LoRA on the ACE-Step music model (v1.5). You supply a zip of training audio, pick how long to train, and Civitai's fleet does the rest - each epoch hands you a downloadable model you can then generate from. No VRAM budget to babysit, no environment setup, just Buzz per training run.
ACE-Step is the community's default open-weights music generator - the "local Suno" - and one of its signature moves is that people train artist-style LoRAs on it exactly the way they train checkpoint LoRAs on images. That's what this node is for: capture a genre, an artist's production style, or a signature sound as a LoRA without running a trainer locally. It lives in the Civitai/Training/ace_step_15 menu of Civitai's official ComfyUI pack.
How it works
The node submits a training workflow (engine: ai-toolkit, ecosystem: ace_step_15) to Civitai's Orchestration API. Your training data goes up as a zip, the cloud trains the LoRA, and each epoch produces a checkpoint you can download. The AI Toolkit is the trainer under the hood - the one-person suite the community reached for first on every new architecture.
The critical input is training_data_json, and it's not a list of files - it's a JSON object pointing at a hosted zip, with an image count for billing:
{"type": "zip", "sourceUrl": "urn:air:ace-step:dataset:civitai:12345@1", "count": 20}
sourceUrl is an AIR URN to the zip of training audio, and count is the number of items in it - the API uses it to price the run. Get this shape right and the rest is dials.
The inputs that matter
- training_data_json (required) - the zip + count object above.
- epochs / steps - epochs is the number of saved checkpoints (each one a downloadable model, 1–200); steps is the total training length and the main pricing driver (1–10000). Set either and the other is derived.
- trigger_word - the token that activates your trained LoRA in prompts later.
- network_dim / network_alpha - LoRA size and strength shaping, the standard pair from local trainers.
- lr (default 0.0001), batch_size, lr_scheduler, optimizer_type - the same knobs Kohya users know, all optional.
The required-looking billing fields (storage_buzz_per_epoch, default_steps, uses_step_pricing, max_batch_size) are generator plumbing - leave them at their defaults unless you know what you're doing.
Outputs: moderation_status (whether the trained model passed content review), epochs, plus the usual workflow_id and raw_json.
Installing it
This ships in Civitai Comfy Nodes, Civitai's official ~160-node pack for their Orchestration API:
- ComfyUI Manager: Manager → Custom Nodes Manager → search Civitai Comfy Nodes → Install, then restart.
- CLI:
comfy node registry-install civitai-comfy-nodes - Source:
cd ComfyUI/custom_nodes && git clone https://github.com/civitai/civitai-comfy-nodes.git && pip install -r civitai-comfy-nodes/requirements.txt(justrequests).
You need a Civitai account, Buzz, and credentials - a Civitai Auth node, CIVITAI_API_TOKEN (best for headless), or a stored key from the Civitai sidebar.
Where people get burned
- training_data_json is JSON, not a path. Paste a valid object with
type,sourceUrl, andcount; a broken shape fails client-side with a JSON error before it ever submits. - Training is genuinely paid. Every step is metered and storage per epoch adds to the bill - the
storage_buzz_per_epochfield exists precisely because more epochs cost more. Watch the cost report on the node after a run. - Moderation gates your output. Trained models pass through Civitai's content review (
moderation_statustells you the verdict), and the same platform rules that govern the web generator apply. - Early preview. The pack README warns of breaking changes without notice. Long trainings can exceed the default 30-minute timeout - raise it via the Auth node or
CIVITAI_COMFY_TIMEOUT.
If training a music LoRA is a one-off for you, cloud training beats standing up a trainer and babysitting it. If it's a hobby, the Buzz meter will eventually point you back to running AI Toolkit locally.
Inputs (24)
| Name | Type | Default | Description |
|---|---|---|---|
| training_data_json | STRING | Represents training data in various formats | |
| storage_buzz_per_epoch | FLOAT | 0.000–2147483647 | Per-epoch surcharge (buzz). Each epoch is a delivered checkpoint plus its preview samples, billed on top of the per-step training cost — so raising the epoch count raises the price by this much each. Override per ecosystem where per-epoch samples are expensive to compute (e.g. video). |
| default_steps | INT | 00–2147483647 | Default total step budget when neither Civitai.Orchestration.Grains.Workflows.Steps.Training.AIToolkit.AIToolkitTrainingInput.Steps nor Civitai.Orchestration.Grains.Workflows.Steps.Training.AIToolkit.AIToolkitTrainingInput.Epochs is supplied. Override per ecosystem where the default training length differs (e.g. video needs more steps, quickly-overtrained models need fewer). |
| uses_step_pricing | BOOLEAN | false | True when billing uses the per-step model. This is the default; the only exception is the legacy path where the caller supplied Civitai.Orchestration.Grains.Workflows.Steps.Training.AIToolkit.AIToolkitTrainingInput.Epochs but no Civitai.Orchestration.Grains.Workflows.Steps.Training.AIToolkit.AIToolkitTrainingInput.Steps (existing consumers), which keeps the historical flat per-epoch price. |
| max_batch_size | INT | 00–2147483647 | Ecosystem-specific maximum training batch size — the upper bound the user's Civitai.Orchestration.Grains.Workflows.Steps.Training.AIToolkit.AIToolkitTrainingInput.BatchSize is clamped to. Most ecosystems cap at 1. |
| samples_jsonopt | STRING | Sample generation configuration for training workflows | |
| epochsopt | INT | 11–200 | Number of training epochs — the number of saved checkpoints produced (each epoch yields one downloadable model). When omitted it is derived from Civitai.Orchestration.Grains.Workflows.Steps.Training.AIToolkit.AIToolkitTrainingInput.Steps; when both are supplied, both are honored (epochs = checkpoint count, steps = total). |
| stepsopt | INT | 11–10000 | Total number of training steps. This is the primary control over training length and determines pricing. When supplied, Civitai.Orchestration.Grains.Workflows.Steps.Training.AIToolkit.AIToolkitTrainingInput.Epochs (the number of saved checkpoints) is derived from it; when omitted, steps are derived from epochs. |
| batch_sizeopt | INT | 11–4 | Training batch size. Defaults to 1; raise it (up to the ecosystem's maximum) to train faster at the cost of more GPU memory. A larger batch sees more images per step, so fewer steps are needed for a comparable result. Values above the ecosystem maximum are clamped down. |
| lropt | FLOAT | 0.000–1 | Sets the learning rate for the model. This is the learning rate when performing additional learning on each attention block (and other blocks depending on the setting). |
| text_encoder_lropt | FLOAT | 0.000–1 | Sets the learning rate for the text encoder. Only used when TrainTextEncoder is true. For models with multiple text encoders, this applies to all of them. |
| train_text_encoderopt | BOOLEAN | false | Whether to train the text encoder(s) alongside the model. Enabling this can improve prompt understanding but increases training time and memory usage. |
| lr_scheduleropt | COMBO | You can change the learning rate in the middle of learning. A scheduler is a setting for how to change the learning rate. | |
| optimizer_typeopt | COMBO | The optimizer determines how to update the neural net weights during training. Various methods have been proposed for smart learning, but the most commonly used in LoRA learning is "adamw8bit". | |
| network_dimopt | INT | 11–256 | The larger the Dim setting, the more learning information can be stored, but the possibility of learning unnecessary information other than the learning target increases. A larger Dim also increases LoRA file size. |
| network_alphaopt | INT | 11–256 | The smaller the Network alpha value, the larger the stored LoRA neural net weights. For example, with an Alpha of 16 and a Dim of 32, the strength of the weight used is 16/32 = 0.5, meaning that the learning rate is only half as powerful as the Learning Rate setting. If Alpha and Dim are the same number, the strength used will be 1 and will have no effect on the learning rate. |
| noise_offsetopt | FLOAT | 0.000–1 | Adds noise to training images. 0 adds no noise at all. A value of 1 adds strong noise. |
| flip_augmentationopt | BOOLEAN | false | If this option is turned on, the image will be horizontally flipped randomly. It can learn left and right angles, which is useful when you want to learn symmetrical people and objects. |
| shuffle_tokensopt | BOOLEAN | false | Randomly changes the order of your tags during training. The intent of shuffling is to improve learning. If you are using captions (sentences), this option has no meaning. |
| keep_tokensopt | INT | 00–10 | If your training images have tags, you can randomly shuffle them. However, if you have words that you want to keep at the beginning, you can use this option to specify "Keep the first 0 words at the beginning". This option does nothing if the Shuffle Tokens option is off. |
| trigger_wordopt | STRING | A trigger word that activates the trained LoRA when used in prompts. Only applicable to certain ecosystems (sd1, sdxl, flux1, chroma, zimagebase, zimageturbo, flux2klein). | |
| continue_fromopt | CIVITAI_AIR | Optional previously-trained LoRA to continue training from ("train further"). When set, the first epoch resumes from this model instead of the base model, and the new epochs build on top of it. | |
| samples_overrides_jsonopt | STRING | — | |
| api_configopt | CIVITAI_CONFIG | Optional Civitai Auth connection; defaults to CIVITAI_API_TOKEN or stored OAuth login. |
Outputs (4)
| Name | Type | Description |
|---|---|---|
| moderation_status | STRING | — |
| epochs | STRING | — |
| workflow_id | STRING | — |
| raw_json | STRING | — |