import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("CalamitousFelicitousness/Krea-2-Base-Diffusers", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Krea 2 (K2) Base - Diffusers
Diffusers-format conversion of the Krea 2 Base checkpoint, the undistilled foundation model of the Krea 2 family from Krea. The Base checkpoint carries no step or guidance distillation, which keeps it diverse and highly malleable. It is the checkpoint intended for fine-tuning, post-training, and LoRA training.
LoRAs trained on Base apply cleanly to Krea 2 Turbo, so the recommended workflow is to train on Base and run inference on Krea-2-Turbo-Diffusers.
Model Summary
Krea 2 is a latent-diffusion image model trained from scratch with an emphasis on aesthetics and stylistic control. The architecture is a single-stream multimodal diffusion transformer.
- Transformer: single-stream DiT, 12.9B parameters, 28 blocks at width 6144. Grouped-query attention, a learned output gate, per-head QK normalization, and a 3-axis rotary embedding. A text-fusion stage inside the transformer collapses twelve text-encoder hidden-state layers into one conditioning stream.
- Text encoder: Qwen/Qwen3-VL-4B-Instruct, tapped at twelve intermediate layers (text-only conditioning).
- VAE: the Qwen-Image autoencoder (
AutoencoderKLQwenImage, f8, 16 latent channels). - Sampler: flow matching with a resolution-aware timestep shift.
Weights are stored in their original mixed precision (bf16 matmuls, fp32 norms and modulations).
Recommended Settings
Base is undistilled and uses classifier-free guidance with a negative prompt.
| Setting | Value |
|---|---|
| Steps | 52 |
| Guidance (CFG) | 3.5 |
| Resolution | up to 1024 x 1024 |
The timestep shift is resolution-aware: the conditioning interpolates the shift between low and high resolution, so no manual tuning is required across sizes.
Prompting
Natural-language prompts are recommended. Long, detailed descriptions yield the best results, though strong images are produced from short prompts as well. For text rendering, the words to be rendered are wrapped in quotes. An optional prompt-expansion system prompt is available in the upstream krea-2-oss repository.
License
The weights are released under the Krea 2 community license.
Citation
@misc{krea2,
title = {Krea 2},
author = {Krea},
year = {2026},
url = {https://www.krea.ai/krea-2}
}
- Downloads last month
- 12
Model tree for CalamitousFelicitousness/Krea-2-Base-Diffusers
Base model
krea/Krea-2-Raw