---
license: other
license_name: minimax-h3-community-license
license_link: https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE
base_model: MiniMaxAI/MiniMax-H3
language:
- en
pipeline_tag: image-text-to-video
tags:
- lora
- bf16
- 2d
- cartoon
- illustration
- image-to-video
- i2v
- video
- video-generation
- portrait
- minimax-h3
- safetensors
---

# **MiniMax-H3-Rough-2D-Cartoon-Illustration**

MiniMax-H3-Rough-2D-Cartoon-Illustration is an experimental 2D cartoon illustration LoRA adapter trained on the general-purpose multimodal model MiniMax H3. This LoRA is trained on a high-quality, video-based dataset featuring free-flow motion illustrations, rough 2D cartoon styles, and dynamic visual movements.

> [!IMPORTANT]
> The Adapter/LoRA is experimental and may generate artifacts.

> [!NOTE]
> All checkpoints are available here: https://huggingface.co/buckets/prithivMLmods/minimax-h3-rough-2d-cartoon-illustration. It is recommended to use checkpoint 1000 / 1200.

## Model Details

* **Base Model:** MiniMax H3
* **Adapter Name:** `minimax-h3-rough-2d-cartoon-illustration`
* **Created by:** [prithivMLmods](https://huggingface.co/prithivMLmods)
* **Model Type:** LoRA / Adapter

## Training Specifications

| Parameter                    | Configuration                                                         |
| :--------------------------- | :-------------------------------------------------------------------- |
| **Resolution**               | Default `480x832` (dynamically adjusted based on packed video frames) |
| **Save Precision**           | BF16                                                                  |
| **Learning Rate**            | 1e-4                                                                  |
| **Optimizer**                | AdamW                                                                 |
| **Network Dimension (Rank)** | 16                                                                    |
| **Total Steps**              | 1200                                                                  |
| **Trigger Words**            | `rough 2D cartoon illustration`                                       |

## Dataset

This adapter is trained on high-quality, video-based data featuring free-flow motion illustrations and rough 2D cartoon visuals.

**Data Source:** [Pexels Videos](https://www.pexels.com/videos/)

## License

This adapter follows the **MiniMax H3 Community License** in accordance with the base model terms.