import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Felldude/Krea-2-Raw", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]FP32 Trained QWEN VL Text Encoder & FP32 Trained VAE
This model has gradient estimation/smoothing using Montecarlo for the diffuison model
Model Overview
Model Name: Krea 2
Version: v1.0
Release Date: June 22, 2026
Model Type: Text-to-image diffusion model
Architecture: Diffusion Transformer with 12 billion parameters
License: Krea 2 Community License
Release Format: Open-weight release and Krea-hosted product integrations
Model Developer: Krea.ai, Inc.
- Downloads last month
- 46
Model tree for Felldude/Krea-2-Raw
Base model
krea/Krea-2-Raw