Flux Pro Trainer

Discover Flux Pro Trainer, your ultimate tool for custom image generation. Ready to experience the power of AI? Start your journey here!

Platform: Replicate

Model TrainingConcept Fine-TuningLoRA CreationCustom Image Generation

1.4k runs

0.014 per training step

Commercial

🚀Function Overview

This model trains custom image generation concepts by processing uploaded image sets to create specialized finetune IDs for FLUX Pro architectures.

Key Features

Creates custom finetune IDs compatible with FLUX Pro image generation models
Supports both full fine-tuning and LoRA configurations
Automatic captioning option for uncaptioned images
Training parameter controls like learning rate and steps

Use Cases

•Training custom artistic styles for AI image generation
•Creating personalized character or object concepts
•Developing specialized LoRA models for creative projects

⚙️Input Parameters

input_images

string

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.

training_steps

integer

Number of training steps for the fine-tuning process.

trigger_word

string

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.

mode

string

Mode for the fine-tuned model

learning_rate

number

Learning rate for fine-tuning. If not provided, defaults to 1e-5 for full fine-tuning and 1e-4 for lora fine-tuning

captioning

string

Whether to enable captioning during fine-tuning. Automatic turns on captioning if any images are missing caption files.

priority

string

Priority of the fine-tuning process

finetune_type

string

Type of fine-tuning

lora_rank

integer

Rank of the fine-tuned model

💡Usage Examples

Example 1

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
}

Output Results

f07345cb-4d18-4461-aa6f-179566153d28

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type
Run Count: 1.4k
Commercial Use: Supported
Pricing: 0.014 per training step
Platform: Replicate

Related Keywords

Custom Image GenerationModel TrainingConcept Fine-TuningLoRA CreationAI Art StylesPersonalized Character Concepts

Related Models

Mindy Generator

A model for generating images using text prompts with support for image-to-image translation, inpainting, and LoRA integration.

HDPE Plastic Container Generator

a translucent 5 litres plastic container made from HDPE, for storage and transport of liquid, flavored drink concentrate.

Google Imagen 4 Fast

Use this fast version of Imagen 4 when speed and cost are more important than quality