# Dataset Preparation

Before fine-tuning, prepare your dataset as a **ZIP file**. Then upload it to a **public URL** or via the Segmind **data upload endpoint**.

***

## Upload Endpoints

* **Flux Dev** → [Upload here](https://docs.segmind.com/readme/flux-fine-tuning/flux-fine-tuning-api#id-4.-get-fine-tune-data-upload-pre-signed-url)
* **Flux Kontext** → [Upload here](https://docs.segmind.com/readme/flux-fine-tuning/flux-kontext-fine-tuning-api#id-4.-get-fine-tune-data-upload-pre-signed-url)
* **Fast Flux** → [Upload here](https://docs.segmind.com/readme/flux-fine-tuning/fast-flux-fine-tuning-api#id-4.-get-fine-tune-data-upload-pre-signed-url)
* **Flux Pro** → [Upload here](https://docs.segmind.com/readme/flux-fine-tuning/flux-pro-fine-tuning-api#id-4.-get-fine-tune-data-upload-pre-signed-url)

⚠️ Use **public or private upload** depending on your model.

***

## Pipeline-Specific Guidelines

### 🔹 Flux Dev

* Upload 10–20 images in a ZIP.
* Select a `trigger_word` → model learns to associate this word with your subject/style.
* Captions: Auto-generated or custom `.txt` per image.
  * Example: `img_0.jpg` → `img_0.txt`.
* Image resolution: \~1024×1024 (larger images will be resized).
* Style LoRAs: Use images highlighting distinctive features, keep style consistent.
* Character LoRAs: Show subject in different settings/expressions.
  * Avoid different haircuts, ages, or excessive hand-face overlaps.

📌 **Reference Dataset:** Coming soon.

***

### 🔹 Flux Pro

* At least 5 high-quality images.
* Supported: JPG, JPEG, PNG, WebP.
* Optional `.txt` files with same name as images.
  * Example: `sample.jpg` → `sample.txt`.
* Package all into a single ZIP.

📌 **Reference Dataset:** Coming soon.

***

### 🔹 Fast Flux

* Upload 10–20 images in a ZIP.
* Select a `trigger_word`.
* Captions: Auto-generated or custom `.txt` per image.
  * Example: `img_0.jpg` → `img_0.txt`.
* Image resolution: \~1024×1024.
* Style LoRAs: Use varied subjects, keep style consistent.
* Character LoRAs: Avoid hair/age variations & hand-face overlaps.

📌 **Reference Dataset:** Coming soon.

***

### 🔹 Flux Kontext

* Paired images (`INDEX_start.ext` and `INDEX_end.ext`).
* `INDEX.txt` optional (edit instructions).
* Use zero-padded indexes (`01`, `02`, …).

📌 **Reference Dataset:** [Kontext Fine-Tune Samples](https://github.com/segmind/kontext-finetune-datasets/)