You can deploy this model and start earning money today!

OlegSkutte/
Faun-GGUF

Name: Faun-GGUF
Rating: 2.5 (178 reviews)

Views

No views yet

Faun-GGUF 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 is a text-to-image model assembled from Chroma-Flash and a low-step LoRA. It was the default image generation model used in DREAMIO: AI-Powered Adventures. It produces high-quality images with excellent prompt adherence in as few as 6 sampling steps. This repository contains quantized GGUF versions specifically designed for use with DREAMIO's built-in local image generation engine.

Quality Comparison

Below is a side-by-side comparison of the output from the q8_0 and q4_k quantization levels. Both images were generated using the same prompt and settings.

faun.q8_0.gguf (16GB+ VRAM) faun.q4_k.gguf (8GB+ VRAM)

Model Files

This repository provides two quantized versions of the model. Choose the one that best fits your hardware:

faun.q8_0.gguf: The recommended version for higher quality. Requires a GPU with 16GB of VRAM or more.
faun.q4_k.gguf: A more compressed version for systems with less memory. Requires a GPU with at least 8GB of VRAM.

Usage with DREAMIO (Local Generation)

You can use this model on your own hardware by loading it into DREAMIO.

Step-by-Step Guide:

Download and Place the Model:
- Download the appropriate GGUF model file (faun.q8_0.gguf or faun.q4_k.gguf) from the "Files and versions" tab based on your GPU's VRAM.
- Place the file in a folder of your choice. Alternatively, you can put it in the default models folder located at [GAME FOLDER]/Files/Models/Images/Checkpoints/.
Configure DREAMIO:
- Launch DREAMIO and navigate to Image Generation Settings.
- Set the Provider to Local.
- If you used a custom folder, click Models folder and select that folder. If you used the default folder, DREAMIO will find it automatically.
- From the Model dropdown menu, choose the Faun model you downloaded.
Apply Recommended Settings:
- Enter the parameters from the "Recommended Settings" section below to achieve the intended output quality and style.
- For detailed instructions on this setup, please refer to the official guide: Local Image Generation Setup (Built-in Engine).

Recommended Settings

To get the best results, apply the following parameters in Image Generation Settings:

Dimensions: 768 x 768
Sampling steps: 6
Classifier-free guidance scale: 1.00
Sampler: EULER_GE
Scheduler: SMOOTHSTEP
TAESD: taef1.q8_0.gguf
Extra sampling arguments: gamma=1.75
Model arguments: chroma_use_t5_mask=true

Hardware Requirements

This model is optimized for local inference on consumer GPUs.

GPU (Recommended): For best performance, use a dedicated GPU.
- 16GB+ VRAM: Use faun.q8_0.gguf for the best quality.
- 8GB+ VRAM: Use faun.q4_k.gguf.
CPU: If you do not have a compatible GPU, you can run the model on your CPU by selecting the CPU backend. Please note that this will be significantly slower.

For users with limited VRAM, enabling the Autoencoder tiling or Offload model to options in the Image Generation Settings can help reduce VRAM usage and prevent "out of memory" errors.

OlegSkutte/Faun-GGUF