<h1 id="bunny's-english-sfw-wildcards">🐰 BUNNY’s English SFW Wildcards</h1>GPT-Converted English Version | 380 Entries | ~940K Tokens<hr /><h2 id="why-i-made-this">💡 Why I Made This / 为什么做这个</h2>When using Chinese prompts with Krea 2, I noticed that the model tends to generate Asian-looking portraits more often.我在使用 Krea 2 时发现，中文提示词会让模型更倾向于生成 亚洲人像。Because of this, I converted part of the original Chinese wildcard collection into English for my own use, mainly to test my BUNNY’s LoRA Series across a broader variety of portrait generations.因此，我将原始中文 Wildcard 的一部分转换成英文，主要用于测试我的 BUNNY’s LoRA 系列 在更多样化人像生成中的表现。🔗 My LoRA Series / 我的 LoRA 系列<a target="_blank" rel="ugc" href="https://civarchive.com/user/FourBunny/models?tag=character">View BUNNY’s LoRA Series Here</a>Since I had already converted such a large amount for personal testing, I decided to share it publicly as well. 🐰既然已经为了自用测试转换了这么大的体量，我也决定顺便公开分享。<hr /><h2 id="original-post">📌 Original Post / 原帖</h2><a target="_blank" rel="ugc" href="https://civarchive.com/models/2231696/sfw15000-and-qwen-and-z-image-or-15000-portrait-and-selfie-wildcards-for-qwen-and-z-image">🔗 Original SFW15000 Wildcard Post</a>The original Chinese wildcard collection comes from the post above.原始中文版 Wildcard 来源于上方帖子。This release is my English-converted version for personal LoRA testing and natural-language image generation workflows.本次发布的是我为了 LoRA 测试与自然语言生图工作流制作的英文转换版本。<hr /><h2 id="about-this-version">🤖 About This Version / 关于此版本</h2>The prompts were converted from Chinese into fluent English using GPT, with the goal of preserving as much of the original detail, structure, scene description, composition, lighting, camera perspective, materials, and visual atmosphere as possible.这些提示词使用 GPT 从中文转换为流畅英文，目标是尽可能保留原文中的细节、结构、场景描述、构图、光影、镜头视角、材质与整体画面氛围。This is not a simple keyword extraction or tag conversion.这并不是简单的关键词提取或 TAG 转换。The original long-form natural-language structure is retained as much as possible, including:✨ Character appearance 👗 Outfits 🕺 Poses and actions 😊 Expressions 🏙️ Environments 📐 Composition 📷 Camera perspective 💡 Lighting 🧵 Materials and textures 🌫️ Depth of field 🎨 Overall visual atmosphere英文版尽可能保留原始长篇自然语言 Prompt 的信息密度与描述结构。<hr /><h2 id="current-size">📦 Current Size / 当前规模</h2>This release contains:🐰 380 converted entries 🔥 Approximately 940K tokens当前版本包含：🐰 380 条英文转换 Prompt 🔥 总规模约 94 万 TokensThese are not short one-line tags. Many entries are extremely long and highly detailed natural-language prompts.这些并不是普通的一行短 TAG，而是大量细节密度极高的超长自然语言 Prompt。Due to my limited GPT usage quota, this is not a complete conversion of the full original collection.由于我的 GPT 使用额度有限，目前并未完成原始合集的全部转换。However, the current 380-entry version is already large enough for extensive random generation, workflow testing, and LoRA evaluation.不过，目前这 380 条的实际文本体量已经非常大，足够用于大量随机生图、工作流测试和 LoRA 效果评估。<hr /><h2 id="model-compatibility">🧪 Model Compatibility / 模型兼容性</h2><h3 id="tested:-krea-2">✅ Tested: Krea 2</h3>This English version has been tested with Krea 2, and it works well with long natural-language prompts.英文版已使用 Krea 2 进行实际生图测试，长自然语言提示词可以正常工作。In theory, these wildcards should also work with most modern image-generation models that have strong natural-language understanding.理论上，大多数具备较强自然语言理解能力的现代图像生成大模型都可以尝试使用。Especially suitable for models that support:📝 Long-form prompts 🏞️ Detailed scene descriptions 🎬 Complex composition instructions 💬 Natural-language prompting尤其适合支持长提示词、详细场景描述、复杂构图指令与自然语言 Prompt 的模型。<hr /><h2 id="anima-warning-anima">⚠️ ANIMA Warning / ANIMA 注意事项</h2>❌ ANIMA is not recommended.❌ 不推荐用于 ANIMA。In my testing, these prompts are simply too long and information-dense for ANIMA.根据我的测试，这类提示词对于 ANIMA 来说过长、信息密度过高。Very long prompts can easily cause:🌫️ Blurry generations ⚠️ Reduced image quality 🌀 Unstable composition 📉 Overall visual degradation超长提示词很容易导致：🌫️ 画面变糊 ⚠️ 质量下降 🌀 构图不稳定 📉 整体视觉效果劣化So while the wildcard file can technically be loaded into an ANIMA workflow, I do not recommend using the full unmodified prompts directly.因此，虽然 Wildcard 文件 technically 可以加载进 ANIMA 工作流，但我不建议直接使用完整的原始长提示词。<hr /><h2 id="upcoming-nsfw-modified-version-nsfw">🔞 Upcoming NSFW Modified Version / 即将发布的 NSFW 修改版</h2>The previously mentioned DeepSeek NSFW version is now finished and released.之前在 SFW 版本中提到的 DeepSeek NSFW 版本现在已经完成并正式发布。<h3 id="nsfw-wildcards-or-light-to-medium-or-11-txt-files-or-~1.6m-tokens-total"><a rel="ugc" href="https://civarchive.com/models/2771205/bunnys-nsfw-wildcards-or-light-to-medium-or-11-txt-files-or-16m-tokens-total">NSFW Wildcards | Light-to-Medium | 11 TXT Files | ~1.6M Tokens Total</a></h3>🚀 后续计划：我将发布专为“人物 LoRA”优化的精翻重度 NSFW 版本。🚀 Coming next: I will release a carefully refined Heavy NSFW version specifically optimized for Character LoRAs.✂️ 新版本将剔除面部与发型描写，避免与人物 LoRA 自带的特征发生冲突。✂️ The upcoming version will remove facial and hairstyle descriptions to prevent conflicts with your character LoRA's original features.This upcoming version will be a more carefully refined Heavy / Hardcore NSFW version, specifically optimized for character LoRA image generation.这个后续版本会是更加精细处理的 重度 / Hardcore NSFW 精翻版，并且专门针对 人物 LoRA 出图 进行优化。<hr /><h2 id="content">✅ Content / 内容说明</h2>This release contains SFW content only.当前版本仅包含 SFW 内容。Suitable for:🎲 Random prompt generation 👤 Portrait generation 🤳 Selfie generation 🧪 Workflow testing 🐰 BUNNY’s LoRA testing 💡 Prompt inspiration 📚 Dataset inspiration 🤖 Natural-language image model testing适合用于随机提示词生成、人像生成、自拍生成、工作流测试、LoRA 测试、Prompt 灵感、数据集灵感以及自然语言图像模型测试。<hr />🐰 BUNNY’s SeriesMore LoRAs, sliders, concepts, testing tools, and wildcard resources will be added over time.后续会继续发布更多 LoRA、滑块、概念模型、测试工具与 Wildcard 资源。

Files with SHA256: 44a0a3a25ede7984077d740a4fe0e9bffd8ea2af567b0351fa9416d418476536