ifmylove2011 / text-to-image Open weights updated 1 week ago

girlslike-krea2

--- license: apache-2.0 tags: - lora - girlslike - krea2 pipelinetag: text-to-image libraryname: diffusers basemodel: - krea/Krea-2-Raw - krea/Krea-2-Turbo --- 用于测试基于krea2raw int8训练的人物 LoKR / LoRA,仅代表个人审美与训练效果。实际生成结果仅供测试,请勿用于冒充、欺骗或其他不当用途。

Params
12.8 B
Context
—
Downloads 30d
48 K
Likes
151
Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 77 days
▲ 20 K in the last 30 days (29.3%)
86 K19 K
Aug 26Sep 20Oct 16Nov 10

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors fp16 5.3 GB 8.2 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Parameters
12.8 B
Licence
apache-2.0
First seen on the Hub
2026-07-20
Base model
Krea-2-Raw
Training datasets
undisclosed
Added to our catalog
2026-08-26

Family

Base model and the most-downloaded derivatives in the catalog.

Compare with any text-to-image model