Instructions to use Rin247/Krea-2-Turbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Rin247/Krea-2-Turbo with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Rin247/Krea-2-Turbo", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Rin247/Krea-2-Turbo", 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-Turbo
Quantised media packages of krea/Krea-2-Turbo.
MECHA Forge
MECHA β Model Engineering & Contextual Hearth Assembly
These media packages have been forged and optimized in the MECHA Forge. Each one holds the Denoiser, Text Encoder, and VAE components packaged together for easier deployment.
Description
Krea 2 Turbo: the 8-step distilled checkpoint of Krea 2 (12B dense DiT). Fast, high-quality text-to-image at up to 2048 px. Uses a Qwen3-VL text encoder and the Qwen-Image VAE. Distilled: 8 steps, no CFG.
Available quantizations
| Quant | Denoiser | Text encoder | VAE |
|---|---|---|---|
| FP4 | FP4 | FP4 | FP8 |
| FP8 | FP8 | FP8 | FP8 |
| INT4 | INT4 | INT4 | INT8 |
| INT8 | INT8 | INT8 | INT8 |
The VAE is shared between formats: FP4 reuses the FP8 file, INT4 reuses the INT8 file.
Recommended settings
From the source model card (adjust to taste):
| Parameter | Value |
|---|---|
| Steps | 8 |
| CFG / Guidance scale | 0 (distilled) |
| Resolution | 1024-2048 (total pixels) |
| Notes | Distilled; few-step sampling; fast inference |
Example prompts
Caught in the moment (candid, slice of life):
masterpiece, best quality, 1man, solo, candid moment, natural lighting.
A sunlit street cafe on a summer afternoon, a small round bistro table
under a striped parasol, potted plants and climbing flowers, warm golden
light and a gentle breeze. A 30-year-old man with short dark hair and
brown eyes, relaxed build, wearing a linen shirt and chinos, sitting with
a glass of iced coffee and a calm smile, candid and at ease.
Fashion photography (magazine cover style):
Fashion photography, magazine cover style: a 30-year-old man with a strong
jawline, short textured hair, and warm brown eyes; wearing a tailored navy
suit, open-collar white shirt, leather loafers; studio rim lighting, bold
serif typography, high contrast, cinematic, 8K, sharp focus, GQ editorial.
Scenery:
Scenery: a misty mountain ridge at dawn, pine forests below, low clouds
drifting through the valley, first light on snow-capped peaks, photorealistic,
wide angle, 8K.
- Downloads last month
- 63