black-forest-labs/flux-pro-trainer ❓🖼️📝🔢 → 📝
About
Train FLUX.1 [pro] and FLUX 1.1 [pro] Ultra. Upload images to create a custom finetune_id to use with the inference model
Example Output
Output
f07345cb-4d18-4461-aa6f-179566153d28
Performance Metrics
680.35s
Prediction Time
680.37s
Total Time
All Input Parameters
{
"mode": "general",
"priority": "quality",
"lora_rank": 32,
"captioning": "captioning-disabled",
"input_images": "https://replicate.delivery/pbxt/MvDQOp1uNVTNjYxI9wnvyqXNMumlUzQdBFFPvkqNyIkkG1Rn/ABSRTBNGS.zip",
"trigger_word": "ABSRTBNGS",
"finetune_type": "full",
"training_steps": 300
}
Input Parameters
- mode
- Mode for the fine-tuned model
- priority
- Priority of the fine-tuning process
- lora_rank
- Rank of the fine-tuned model
- captioning
- Whether to enable captioning during fine-tuning. Automatic turns on captioning if any images are missing caption files.
- input_images
- A zip file containing the images that will be used for training. We recommend a minimum of 10 images. If you include captions, include them as one .txt file per image, e.g. my-photo.jpg should have a caption file named my-photo.txt. If you don't include captions, you can turn on captioning.
- trigger_word
- The trigger word refers to the object, style or concept you are training on. Pick a string that isn't a real word, like TOK or something related to what's being trained, like CYBRPNK. The trigger word you specify here will be associated with all images during training. Then when you use your LoRA, you can include the trigger word in prompts to help activate the LoRA.
- finetune_type
- Type of fine-tuning
- learning_rate
- Learning rate for fine-tuning. If not provided, defaults to 1e-5 for full fine-tuning and 1e-4 for lora fine-tuning
- training_steps
- Number of training steps for the fine-tuning process.
Output Schema
Output
Example Execution Logs
Starting fine-tuning...
Input zip size: 2.0MB
Optimized zip size: 0.7MB
{'finetune_id': 'f07345cb-4d18-4461-aa6f-179566153d28', 'polling_url': 'https://api.us1.bfl.ai/v1/get_result?id=f07345cb-4d18-4461-aa6f-179566153d28'}
Fine-tuning...
Still processing...
Still processing...
Still processing...
Still processing...
Still processing...
Still processing...
Still processing...
Still processing...
Fine-tuning completed in 679.8sec
Fine tuning completed. Use your finetune ID f07345cb-4d18-4461-aa6f-179566153d28 to create images with your training.
Version Details
- Version ID
04e652c9c01dcae177b3e3e716aecf3d4f6a671c9533e3fa4b5ae7617a694fe4- Version Created
- April 29, 2025