ai-toolkit / chroma
Cloud LoRA training for Chroma and friends
- continue_from
- api_config
- moderation_status
- epochs
- workflow_id
- raw_json
Most training nodes in this pack are locked to one model. CivitaiTrainingAiToolkitChroma is the exception: it carries an ecosystem dropdown with nine targets - chroma, ernie, zimageturbo, zimagebase, ltx2, ltx23, hidream-o1, boogu, krea2 - and runs Ostris's AI Toolkit trainer on Civitai's cloud for whichever you pick. It defaults to chroma, which is why the node is named that way, but it's really the "newer image ecosystems" training node. One node, nine model families, zero local GPU.
It lives in the Civitai/Training/ai-toolkit menu of Civitai's official ComfyUI pack. The usefulness is obvious if you've been following the ecosystem churn: every few weeks there's a new base model that people want LoRAs for, and local trainers take days to catch up. This node sidesteps the wait - if Civitai's fleet runs it, you can train on it, and AI Toolkit is the trainer that has historically had each new architecture working first.
How it works
The node submits a training workflow (engine: ai-toolkit, ecosystem: <your pick>) to Civitai's Orchestration API. Supply training images as a hosted zip, choose the ecosystem, and the cloud trains the LoRA - each epoch produces a downloadable model. Swap ecosystem and the same zip workflow trains a LoRA for a completely different base. The tradeoff: batch_size is effectively 1 for several of these ecosystems (the API clamps it), so don't expect big-batch speedups.
The core input is training_data_json, a JSON object (not a path):
{"type": "zip", "sourceUrl": "urn:air:chroma:dataset:civitai:456@1", "count": 25}
sourceUrl is an AIR URN to the zip of training images; count is the number of images, which is how the run is priced.
The inputs that matter
- ecosystem (required) - the base model to train on. Default
chroma;zimageturbo/zimagebaseare the Z-Image line,ltx2/ltx23are video, the rest are the current frontier. Pick before you think about anything else. - training_data_json (required) - the zip + count object.
- epochs / steps - epochs = saved checkpoints (each a downloadable model), steps = total training length and the pricing driver.
- trigger_word - the token that activates your LoRA in prompts.
- network_dim / network_alpha, lr, noise_offset, keep_tokens - standard trainer dials, all optional.
The required-looking storage_buzz_per_epoch, default_steps, uses_step_pricing, and max_batch_size are generated plumbing - leave them.
Outputs: moderation_status, epochs, plus the standard workflow_id and raw_json.
Installing it
This is one of ~160 nodes in Civitai Comfy Nodes, Civitai's official 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 with 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
- Wrong ecosystem = wasted run. The dropdown silently changes the whole training target. Double-check it before spending a run's worth of Buzz.
- training_data_json must be valid JSON with
type,sourceUrl, andcount. Malformed input fails with a local JSON error. - Cloud pricing is real. Steps are metered and every epoch adds a storage surcharge - the
storage_buzz_per_epochtooltip spells out the math. Check the cost report on the node after each run. - Moderation gates the model. Trained LoRAs pass through Civitai's content review and
moderation_statusreports the verdict. - Early preview. The README warns of unannounced changes; early community reports include bugs and slow jobs. Long trainings can hit the default 30-minute timeout - raise it via the Auth node or
CIVITAI_COMFY_TIMEOUT.
For anyone who wants LoRAs on the latest models without running a trainer, this is the one node in the pack that keeps up with the ecosystem churn for you.
Inputs (24)
| Name | Type | Default | Description |
|---|---|---|---|
| ecosystem | COMBO | chroma | 9 options: chroma, ernie, zimageturbo, zimagebase, ltx2, ltx23, +3 |
| 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. | |
| 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 | — |