MODEL PROFILE · 模型档案

Krea2-Turbo-Distill-2step-LoRA

lvladikov · Krea2-Turbo-Distill-2step-LoRA

> 🆕 **New: a 3-step LoRA** takes Krea 2 Turbo from 8 steps down to 3, one step more than this LoRA, with more fine detail than both this and the 4-step LoRA (fine texture 1.13× the 8-step teacher's on its 22 test prompts). This 2-step LoRA stays the fastest of the three. **A quarter of the steps · 4× faster denoising (text encoding and VAE decode excluded) · fine detail at 0.92–1.02× the teacher's across all 12 trained resolutions, the grid bands at its level · colour close to the teacher's · 1 point missing of 352 on a blind prompt-adherence rubric · teacher preferred on 12 of 66 judged renders · 51,195 training samples on recorded teacher trajectories · 32 days on one RTX 3090 · released from settled weights; the project's final checkpoint.** A LoRA for **Krea 2 Turbo** that takes the model from **8 steps down to 2** — Turbo's own weights and sigmas, guidance 0.0, a quarter of the denoising passes — aiming at the best quality two steps can give. It is for **fast previews and drafts**; the **4-step LoRA** remains the recommendation for quality renders.

译文排队中,当前展示来源原文。

图像生成license:other
上下文窗口来源未披露
输入 → 输出文本 → 图像
模型权重待核验
档案更新时间2026/11/2 19:16:31
OVERVIEW

模型介绍

> 🆕 **New: a 3-step LoRA** takes Krea 2 Turbo from 8 steps down to 3, one step more than this LoRA, with more fine detail than both this and the 4-step LoRA (fine texture 1.13× the 8-step teacher's on its 22 test prompts). This 2-step LoRA stays the fastest of the three. **A quarter of the steps · 4× faster denoising (text encoding and VAE decode excluded) · fine detail at 0.92–1.02× the teacher's across all 12 trained resolutions, the grid bands at its level · colour close to the teacher's · 1 point missing of 352 on a blind prompt-adherence rubric · teacher preferred on 12 of 66 judged renders · 51,195 training samples on recorded teacher trajectories · 32 days on one RTX 3090 · released from settled weights; the project's final checkpoint.** A LoRA for **Krea 2 Turbo** that takes the model from **8 steps down to 2** — Turbo's own weights and sigmas, guidance 0.0, a quarter of the denoising passes — aiming at the best quality two steps can give. It is for **fast previews and drafts**; the **4-step LoRA** remains the recommendation for quality renders.

主要特点

特点摘要待依据来源补齐,不凭模型名称推断能力。

局限与注意事项

暂无足够来源支持具体缺点结论。请重点验证实际任务表现、时延、数据政策、许可与版本生命周期。

PRICING & COST

来源报价与费用分析

同一模型在不同渠道、地区和配置下可能采用不同价格。下表独立保留各渠道报价,不将渠道价格视为厂商官方统一价格。

来源 / 渠道输入输出计费单位采集时间
暂未取得可核验报价,请查阅来源渠道。

按月估算基础 Token 费用

—

预估不包含缓存优惠、阶梯定价、多模态附加费用、网络检索、税费及推理额外输出。

INDEPENDENT BENCHMARKS

公开评测与运行配置

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

查看完整已收录榜单 →

常见问题

开放权重是否代表可以免费商用?

不一定。应核对具体版本许可证、商用门槛和使用政策。自部署还会产生算力和维护成本。

这些价格是实时结算价格吗?

不是实时结算价格,而是带采集时间的来源报价快照。请到对应渠道核对当前版本、区域、折扣和计费方式。

资料来源与可追溯记录

许可证:other。模型介绍与第三方评测均以原来源的具体版本和方法为准。