anime krea2 工作流
Derived from my detailed-krea2 workflow (see that workflow's description on more details on how the core of it and all the slots/options works), but with the "Krea2-Anime" (v1.5, by "civitadmin") finetune swapped in from https://civitai.red/models/2908999/krea2-anime?modelVersionId=3310477 This finetune is intended to be focused towards creating anime/illustration style photos via Krea 2's base model capabilities. Author called out prompting suggestions in particular: Prompts are absolutely crucial. If your prompt is too simple, the results will look just like basic anime model outputs. But if you include highly detailed scene descriptions, the outcome will be on a completely different level. Given that this is an anime focused model, the snofs LoRA helper that is built into the detailed-krea2 workflow base still exists here, but is disabled by default to prevent interference with the base checkpoint. It can be re-enabled by setting slot7 to 1 (or any other strength). If you do, try it at a very low strength first. Prompting Tip: A blend of rich natural language (environment, action, character, style) paired with strategic prompt tags yields the best results; overly minimal prompts often lead to overly simplistic images.
兼容 / 可用于 Graydient 支持的应用
选项
| 选项 | 映射到 | 默认 |
|---|---|---|
(prompt) | Prompt text | — |
/run:anime-krea2 | Workflow shortcode | anime-krea2 |
使用的模型
anime krea2 模型由 ModelTrends 通过短代码 /run:anime-krea2 导入 在 ModelTrends 查看 面向开发者（可选）
API 示例代码。你可以用此工作流构建个人应用。准备部署时请 升级到商务计划。详见 完整渲染 API 文档。
curl https://cloud.graydient.ai/api/v3/render/ \
-X POST \
-H "Content-Type: application/vnd.api+json" \
-H "Accept: application/vnd.api+json" \
-H "Authorization: Bearer $GRAYDIENT_TOKEN" \
-d '{
"prompt": "/workflow /run:anime-krea2 ",
"callback_url": "https://example.com/webhook/render"
}'这就是幕后工作原理。已经为你配置好了。上表中的参数插入这些槽位，允许你更改工作方式和加载的模型。你无需理解或修改它——它已经设置好，能直接使用。
此工作流页面列出了短代码、选项和 ModelTrends 下载。完整节点图可随工作流下载在 ModelTrends 获得。 此页面尚未绘制该工作流的节点图。请在 ModelTrends 打开以下载工作流文件和加载的模型。
所有工作流：强大工作流程