train_dreambooth_lora_flux_kontext.py: error: the following arguments are required: --instance_prompt

### Describe the bug

train_dreambooth_lora_flux_kontext.py: error: the following arguments are required: --instance_prompt

### Reproduction

accelerate launch --main_process_port 29513 train_dreambooth_lora_flux_kontext.py \
--pretrained_model_name_or_path=black-forest-labs/FLUX.1-Kontext-dev \
--output_dir="kontext-i2i" \
--dataset_name="/root/paddlejob/workspace/env_run/output/wanghuake/DATA/merged_output" \
--image_column="output" --cond_image_column="file_name" --caption_column="instruction" \
--mixed_precision="bf16" \
--resolution=1024 \
--train_batch_size=1 \
--guidance_scale=1 \
--gradient_accumulation_steps=4 \
--gradient_checkpointing \
--optimizer="adamw" \
--use_8bit_adam \
--cache_latents \
--learning_rate=1e-4 \
--lr_scheduler="constant" \
--lr_warmup_steps=200 \
--max_train_steps=1000 \
--rank=16 \
--seed="0" \

### Logs

```shell

```

### System Info

train_dreambooth_lora_flux_kontext.py: error: the following arguments are required: --instance_prompt

### Who can help?

_No response_

Start with train_dreambooth_lora_flux_kontext.py and inspect its argument parser alongside the dataset_name, image_column, cond_image_column, and caption_column options used in the reproduction command. Re-run the command to confirm when --instance_prompt is required, then define done as the dataset-based training invocation accepting the documented inputs without the reported argument error.

Scritto dal modello di indicizzazione a partire dal testo della issue.