impresstation

krea2 LoRA "impresstation" — trigger "stationthis".

Trigger word: stationthis

This is a modified derivative of Krea 2, trained on Krea 2 RAW and intended for use on Krea 2 Turbo. Not an official Krea product nor endorsed by Krea. Use is governed by the Krea 2 Community License — commercial use permitted for entities under $1M USD annual revenue; above that, obtain an enterprise license from Krea.

Sample Outputs

stationthis, stationthis, low poly playstation screenshot style, A determined young woman…	stationthis, stationthis, low poly playstation screenshot style, Under a misty, twilight…
:---:	:---:
stationthis, stationthis, low poly playstation screenshot style, A stoic, sunglasses-wear…	stationthis, stationthis, low poly playstation screenshot style, A stern, determined woma…

Usage (Diffusers)

import torch
from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained(
    "krea/Krea-2-Turbo", torch_dtype=torch.bfloat16
).to("cuda")
pipe.load_lora_weights("ms2stationthis/impresstation")
image = pipe("stationthis, a character portrait", guidance_scale=4.0, num_inference_steps=25).images[0]
image.save("out.png")

Recommended Settings

LoRA strength	Guidance	Steps	Resolution
0.8–1.0	4.0	25	1024×1024

Training Details

• Base: krea/Krea-2-Raw
• Steps: 4000 · Network: LoRA rank 32 / alpha 32
• Optimizer: adamw8bit, lr 1e-4 · Scheduler: flowmatch
• Resolution: 512, 768, 1024 (multi-res bucketed) · Precision: bf16 train / fp16 save

Reproduction

This repo includes the full dataset/ (33 image-caption pairs) and the exact config.yaml so the LoRA can be retrained as-is.

About

Trained on StationThis — an AI creative platform powered by $MS2. Train your own LoRAs via @stationthisbot on Telegram.

_{Published via noema.}