Downloads · 30 days
5.5K
3% of all-time downloads
mlx-FLUX.1-schnell-4bit-quantized
argmaxinc/mlx-FLUX.1-schnell-4bit-quantized
mlx-FLUX.1-schnell-4bit-quantized is a text-to-image model from argmaxinc. Use it when you need an image from a text prompt. It is set up for diffusionkit. The card lists the license as apache-2.0.
![FLUX.1 [schnell] Grid](./fluxonmac.png) Note: This checkpoint features 4-bit quantization of the mmdit module using MLX's nn.quantize function with default settings (groupsize=64). - Create conda environment
All-time downloads
207K
Public
Repo size
7.4 GB
Likes
38
Public
Repo makeup
Click a slice to open those files.
.safetensors7 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusionkit
- License
- apache-2.0
- Access
- Public
- Created
- Aug 20, 2024
- Updated
- Aug 29, 2024
- SHA
- fc7110ba
Model card
From the Hugging Face model README
FLUX.1-schnell on DiffusionKit MLX!
Check out the original model!
Check out the DiffusionKit github repository!
![FLUX.1 [schnell] Grid](https://huggingface.co/argmaxinc/mlx-FLUX.1-schnell-4bit-quantized/resolve/main/flux_on_mac.png)
Note: This checkpoint features 4-bit quantization of the mmdit module using MLX's nn.quantize function with default settings (group_size=64).
Usage
-
Create conda environment
conda create -n diffusionkit python=3.11 -y
conda activate diffusionkit
pip install diffusionkit
-
Run the cli command
diffusionkit-cli --prompt "detailed cinematic dof render of a \
detailed MacBook Pro on a wooden desk in a dim room with items \
around, messy dirty room. On the screen are the letters 'FLUX on \
DiffusionKit' glowing softly. High detail hard surface render" \
--model-version argmaxinc/mlx-FLUX.1-schnell-4bit-quantized \
--height 768 \
--width 1360 \
--seed 1001 \
--step 4 \
--output ~/Desktop/flux_on_mac.png
- Task
- Text-to-Image
- Library
- diffusionkit
- License
- apache-2.0
- Languages
- en
- Created
- Aug 20, 2024
- Updated
- Aug 29, 2024