README.md

---
license: apache-2.0
pipeline_tag: text-to-image
library_name: diffusers
---

# Faun Model Card

![A beautiful faun with the upper body of a woman and the brown, furry legs and cloven hooves of a goat, sitting gracefully on a moss-covered log in an enchanted forest. She has elegant, curved horns, and her long, wavy dark hair is adorned with small, delicate flowers. She is wearing a simple, light-green Grecian-style dress. With a serene expression, she is playing a wooden pan flute. The setting is a magical woodland, with a gentle stream flowing behind her and vibrant wildflowers blooming on the forest floor. The scene is illuminated by warm, ethereal golden sunlight filtering through the dense tree canopy, creating a dreamlike atmosphere with glowing fireflies or magical orbs of light floating in the air.](./faun.png)

**Faun** is a text-to-image model assembled from Chroma-Flash and a low-step LoRA. It is the default image generation model used in [DREAMIO: AI-Powered Adventures](https://dreamio.xyz/). It produces high-quality images with excellent prompt adherence in as few as 6 sampling steps.

## Usage

There are two primary ways to use the model:

### 1. In DREAMIO (Online)
Faun is seamlessly integrated into [DREAMIO: AI-Powered Adventures](https://dreamio.xyz/) as the default image generator.

### 2. With ComfyUI (Offline)
You can use this model locally in your own ComfyUI setup for complete control and offline generation.

**Step-by-Step Guide:**

1. **Download the Model:**
* Download the model checkpoint file.
* Place it in your ComfyUI installation folder at `ComfyUI/models/checkpoints/`.

2. **Load the Workflow:**
* Drag and drop the image above directly onto the ComfyUI window.
* ComfyUI will automatically load the exact workflow used to generate the image, including the prompts, settings, and model paths.

3. **Connect to DREAMIO (Optional):**
* You can connect your local ComfyUI instance to DREAMIO to use your own hardware for in-game image generation.
* For detailed instructions on this setup, please refer to the official guide: [Using ComfyUI with DREAMIO](https://dreamio.xyz/docs/guides/using-comfyui/).

## Hardware Requirements

This model requires a GPU with at least **24GB of VRAM** for optimal performance.

***

# Faun-Turbo

You can achieve a 2x inference speedup by using various cache nodes in ComfyUI. With a cache node and a different sampler, this model can generate images in as little as 2.8 seconds on a laptop with an NVIDIA GeForce RTX 5090 Laptop GPU: 

![faun-turbo](https://cdn-uploads.huggingface.co/production/uploads/65f92ba4b81aea31d5157865/4RLCW-XJpOd_Oli5fjz6g.png)