如果觉得生成效果的真实感还不够，可以尝试搭配一些 Real / Realism 类的 LoRA，通常能进一步提升画面的写实感和质感。

If you feel the results are not realistic enough, you can try adding some Real / Realism LoRAs. They can usually help improve the overall realism and texture of the images.

V3 Update

V3 增加了更多女性角色的多样性，并进一步优化了皮肤质感，让整体表现更加自然、细腻。

V3 adds more diversity to female characters and further improves skin texture, resulting in a more natural and refined overall look.

V2：噪点更低、更平滑，但细节可能略少于 V1.5。新版本不代表一定更好，请按需选择。

V2: Less noise and smoother results, but slightly less detail than V1.5. Newer doesn’t always mean better—choose based on your preference.

1.5

增加了一些真实感，新增int8、bf16|Improved realism; added INT8 and BF16.

中文说明

VelvetMuse 是一款基于 Krea 2 Turbo 的 FP8 模型，主要面向写实成人角色、人像摄影、皮肤与服饰质感、丝袜细节、姿势表现及整体画面美化。

模型采用 Turbo 架构，能够以较少的采样步数实现快速生成，适合写实人像、时尚摄影和成人题材创作。

模型信息

• 基础模型：Krea 2 Turbo

• 精度：FP8 Scaled

• 格式：Safetensors

• 触发词：无

• 成人内容：是

• 文件大小：约 12.24 GiB

推荐设置

• Steps：8

• CFG：1.0

• Sampler：Euler

• Scheduler：Simple

• 建议分辨率：1024 级别或更高

• 推荐使用自然语言描述人物、服装、姿势、镜头、构图和光线

模型特点

• 写实成人角色与摄影质感

• 细腻的皮肤和服饰表现

• 增强丝袜材质与腿部细节

• 更丰富的人物姿势

• 较好的光影、色彩和整体画面表现

• Turbo 快速生成

English Description

VelvetMuse is an FP8 model based on Krea 2 Turbo, designed for realistic adult characters, portrait photography, refined skin and clothing textures, hosiery details, expressive poses, and polished visual quality.

Built on the Turbo architecture, it delivers fast generation with a low step count and is suitable for realistic portraits, fashion photography, and adult-oriented artwork.

Model Information

• Base Model: Krea 2 Turbo

• Precision: FP8 Scaled

• Format: Safetensors

• Trigger Word: None

• Adult Content: Yes

• File Size: Approximately 12.24 GiB

Recommended Settings

• Steps: 8

• CFG: 1.0

• Sampler: Euler

• Scheduler: Simple

• Recommended Resolution: 1024-class or higher

• Detailed natural-language prompts are recommended for subjects, clothing, poses, camera angles, composition, and lighting

Features

• Realistic adult character rendering

• Refined skin and clothing textures

• Enhanced hosiery and leg details

• More expressive character poses

• Improved lighting, color, and overall visual quality

• Fast Turbo generation