I suddenly realized that I haven't published a checkpoint for ZIT. This checkpoint was created a month ago.therefore, many original images are no longer valid, and I'm not sure if I can post them. If you need to see the image effects and LoRa settings for the tooltip, please go to TensorArt.

我之前忘了在civitai发布 ZIT 的检查点。这个检查点是一个月前创建的，因此很多原始图像已经失效，我不确定是否还能发布它们。如果您需要查原图效果、提示词、设置和搭配的LoRa，请前往 TensorArt。

v1.2 this checkpoint excels in generating female portraits, group scenes, and aesthetic compositions. Utilizing a multimodal training approach, it adapts seamlessly to diverse art styles and handles both SFW and little NSFW tasks with high fidelity. A key feature is its character diversity, ensuring a wide range of ethnicities beyond just Asian characters.

v1.2 版本在生成女性肖像、群像和美学构图方面表现出色。它采用多模态训练方法，能够无缝适应各种艺术风格，并能高保真地处理适合所有年龄段（SFW）和轻量成人内容（NSFW）的任务。其关键特性在于角色多样性，确保了除亚洲角色之外的更多种族选择。

Online usage-在线试用: TensorArt | TensorHub | SeaArt

Sampler: heunpp2 + linear_quadratic schedule, seeds_3 + normal is better sampler. CFG Scale: 1 – 2，Steps: 8 – 20

Recommended Speed: CFG: 1, Step: 10

Recommended Quality: CFG: 1.5, Step: 20

Prompting Tip: The more detailed and fluent your prompt, the closer the result matches your vision. Please ensure your prompts are well-structured.

提示提示：您的提示越详细流畅，结果就越接近您的预期。请确保您的提示结构清晰。

Built on the ZIT FP8 architecture, it is highly optimized for TensorArt and remains friendly to low-VRAM GPUs. It employs a specialized mechanism to bypass CLIP restrictions, significantly enhancing its capability in handling NSFW content.

Performance Note: While attempts to fully restore Turbo acceleration were unsuccessful, this checkpoint stands as the premier choice for quality-focused users. Whether on the TensorHub or locally, if you prioritize image fidelity over generation speed, this is currently your best option.

它基于 ZIT FP8 架构构建，针对 TensorArt 进行了高度优化，并且对低显存 GPU 也非常友好。它采用专门的机制来绕过 CLIP 限制，有效增强其处理 NSFW 内容的能力。

性能说明：虽然恢复 Turbo 加速功能的尝试未成功(还是需要8步以上)，但此检查点是注重质量的用户首选。无论是在tensorhub或者本地使用，如果您优先考虑图像质量而不是生成速度，那么这是一个好选择。