You're looking at a specific version of this model. Jump to the model overview.
simpletuner /z-image:f783963f
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| train_data |
string
|
Zip or tar of training images. Matching .txt captions are preserved; missing captions use the trigger and filename.
|
|
| hf_dataset |
string
|
Hugging Face dataset repo ID to use when no archive is provided (e.g., user/dataset).
|
|
| model |
None
|
Z-Image-Turbo
|
Training assistant version for Z-Image Turbo. v1 preserves the original recipe.
|
| resolution |
None
|
1024
|
Training and validation scales; multi-scale sampling preserves aspect ratios.
|
| use_synthetic_regularisation |
boolean
|
False
|
Mix synthetic images into half of training updates. Available at 512 and 1024 resolutions.
|
| hf_caption_column |
string
|
caption
|
Caption column when using hf_dataset.
|
| hf_instance_prompt |
string
|
Use this caption for every Hugging Face image instead of a caption column. Include your trigger.
|
|
| hf_revision |
string
|
Optional Hugging Face dataset commit or revision.
|
|
| validation_prompt |
string
|
a detailed photograph, natural lighting
|
Validation prompt; include the concept or trigger you are teaching.
|
| enable_crop |
boolean
|
False
|
Enable cropping when preparing samples.
|
| crop_style |
None
|
center
|
Crop location style when cropping is enabled.
|
| crop_aspect |
None
|
preserve
|
Aspect handling for crops: square (1:1) or preserve source aspect.
|
| trigger_word |
string
|
TOK
|
Subject token used in generated fallback captions and instance prompts.
|
| caption_strategy |
None
|
textfile
|
Captions for uploaded images: matching text files with filename fallbacks, filenames, or one instance prompt.
|
| train_batch_size |
integer
|
2
Min: 1 Max: 4 |
Training batch size (1-4).
|
| checkpoints_total_limit |
integer
|
5
Min: 1 Max: 5 |
Maximum checkpoints to retain (max 5).
|
| checkpoint_step_interval |
integer
|
250
Min: 1 |
Save checkpoints and generate validation images every N optimizer updates.
|
| max_train_steps |
integer
|
4000
|
Total optimizer updates. Regularisation updates count toward this limit.
|
| learning_rate |
number
|
Min: 0.00000001 Max: 0.01 |
Learning rate. Leave blank for the model recipe.
|
| lora_rank |
integer
|
Min: 1 Max: 256 |
Adapter rank; alpha matches rank. Leave blank for rank 64.
|
| lora_dropout |
number
|
0
Max: 0.999 |
Adapter dropout probability.
|
| seed |
integer
|
42
|
Training and validation seed.
|
| attention_mechanism |
None
|
kohaku-fa-auto
|
Automatic centered Kohaku attention, or native Diffusers attention.
|
| gradient_checkpointing_interval |
integer
|
Min: 1 Max: 64 |
Blocks per checkpointed segment. Leave blank for the model recipe.
|
| gradient_checkpointing_segment_stride |
integer
|
Min: 1 Max: 64 |
Start a checkpointed segment every N blocks. Leave blank for contiguous segments.
|
| regional_compile |
boolean
|
True
|
Compile repeated transformer blocks.
|
| dataloader_prefetch |
boolean
|
True
|
Prepare the next training batches in the background.
|
| push_checkpoints_to_hub |
boolean
|
True
|
Upload retained intermediate checkpoints as well as final weights when hub_model_id is set.
|
| pixel_area |
integer
|
Min: 256 Max: 2048 |
Legacy single-resolution override. Prefer resolution for new jobs.
|
| num_train_epochs |
integer
|
Min: 1 |
Legacy epoch limit, used with max_train_steps=0.
|
| checkpoint_epoch_interval |
integer
|
Min: 1 |
Optional epoch-based checkpoint interval.
|
| s3_bucket |
string
|
|
S3-compatible bucket for publishing checkpoints.
|
| s3_region |
string
|
S3 region (optional).
|
|
| s3_endpoint_url |
string
|
Custom S3 endpoint URL (for non-AWS providers).
|
|
| s3_base_path |
string
|
Prefix inside the bucket (defaults to cog/zimage/{job_id}).
|
|
| s3_public_base_url |
string
|
Public base URL to build shareable links (optional).
|
|
| s3_access_key |
string
|
S3 access key (leave blank to use IAM/instance roles).
|
|
| s3_secret_key |
string
|
S3 secret key (leave blank to use IAM/instance roles).
|
|
| hub_model_id |
string
|
Hugging Face model repo for the final LoRA and validation images (e.g., user/model).
|
|
| hf_token |
string
|
Hugging Face token for downloads and write access when publishing to hub_model_id.
|
|
| return_logs |
boolean
|
True
|
Print the tail of debug.log.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'format': 'uri', 'title': 'Output', 'type': 'string'}