.gguf quantized version of https://huggingface.co/black-forest-labs/FLUX.2-klein-4B
Recommended settings for Dreamio:
- Dimensions = 512 x 512
- Sampling steps = 4
- Classifier-free guidance scale = 1,00
- Sampler = EULER
- Scheduler = DISCRETE
- TAESD = taef2
The GGUF file includes diffusion model (UNET), text encoder (LLM), and autoencoder (VAE), so you don't need to specify them separately.
- Downloads last month
- 273
Hardware compatibility
Log In to add your hardware
8-bit
Model tree for OlegSkutte/FLUX.2-klein-4B-GGUF
Base model
black-forest-labs/FLUX.2-klein-4B