diff --git a/README_CN.md b/README_CN.md index afd031c..9197494 100644 --- a/README_CN.md +++ b/README_CN.md @@ -1,6 +1,14 @@ -
-

Comflowy 节点

- ![Version](https://img.shields.io/badge/node_version-0.1-lightblue?style=for-the-badge&labelColor=darkblue) +banner + +# Comflowy 插件 + +
+ + ![Version](https://img.shields.io/badge/node_version-0.1-lightblue) + + + +
在开发 Comflowy 产品的时候，我们发现虽然社区里有很多插件，但有不少节点更多的是为了解决特定的问题，或者实现某个特定的技术。在用户体验上，相对没那么友好。 @@ -9,6 +17,25 @@ ## 一、节点列表 +1. **Comflowy LLM 节点：** 这是一个调用 LLM 的节点。你可以用它来实现类似 Prompt Generator 的功能。它与市面上的 LLM 节点不同的是，它是通过调用 API 的方式获取结果，这就意味着你不需要安装 Ollama 就能调用 LLM 模型。不再需要担心你的电脑配置是否足够运行这些 LLM 模型。**同时它还是免费的**。 + * 你可以使用我们的在线版 Comflowy 运行包含此节点的 [工作流](https://app.comflowy.com/template/84bea01c-e109-41f2-89c6-914fc999a1cf) 。 + * 也可以下载 [工作流文件](workflows/LLM_CN.json) 并导入到 ComfyUI 里使用。 + *
+ 工作流截图 +
+ + ![image](images/LLM.png) + +2. **Comflowy Omost 节点：** [Omost](https://github.com/lllyasviel/Omost) 插件是一个能帮助你撰写 Prompt 的插件，但本地运行此插件，需要配置较高的电脑。我们基于对 Omost 的理解，实现了一款类似的节点，但与之稍微不同的是，我们并没有运行 Omost 官方的模型，而是通过 Prompt Engineering 的方式实现。这样运行的速度会更快一些。 + * 在线版 [工作流](https://app.comflowy.com/template/1ce47688-4c85-42af-88ad-290f283eb9ec)。 + * 本地版 [工作流文件](workflows/Omost_LLM.json) 。 + *
+ 工作流截图 +
+ + ![image](images/Omost_LLM.png) + + ## 二、如何使用 > [!NOTE] @@ -17,15 +44,19 @@
Step 1: 安装 Comflowy 插件 - - 方法一：使用 [ComfyUI Manager](https://github.com/ltdrdata/ComfyUI-Manager) 安装（推荐） - - 方法二：Git 安装 - CompyUI插件目录(例如“CompyUI\custom_nodes\”)中打开cmd窗口，键入以下命令： +- 方法一：使用 [ComfyUI Manager](https://github.com/ltdrdata/ComfyUI-Manager) 安装（推荐） +- 方法二：Git 安装 + CompyUI插件目录(例如“CompyUI\custom_nodes\”)中打开cmd窗口，键入以下命令： + ```shell git clone https://github.com/chflame163/ComfyUI_LayerStyle.git ``` - - 方法三：下载zip文件 + +- 方法三：下载zip文件 + 或者下载解压zip文件，将得到的文件夹复制到 ```ComfyUI\custom_nodes\``` 目录下。 +
@@ -44,12 +75,16 @@ ![image](images/API_Key_Node.png)
-## 更新记录 +## 三、更新记录 + +* V0.1：支持 LLM 节点、Omost 节点、Http 节点。 + +## 四、感谢 -## 感谢 1. 感谢 [SiliconFlow](https://siliconflow.cn/) 提供的免费 LLM 服务。 -2. 感谢所有为此开源项目做出贡献的人： +2. 感谢 [Omost](https://github.com/lllyasviel/Omost) 作者以及 [ComfyUI-Omost](https://github.com/huchenlei/ComfyUI_omost?tab=readme-ov-file) 插件的作者。 +3. 感谢所有为此开源项目做出贡献的人： - \ No newline at end of file + diff --git a/images/LLM.png b/images/LLM.png new file mode 100644 index 0000000..f417a55 Binary files /dev/null and b/images/LLM.png differ diff --git a/images/Omost_LLM.png b/images/Omost_LLM.png new file mode 100644 index 0000000..fc1a59b Binary files /dev/null and b/images/Omost_LLM.png differ diff --git a/images/comflowy_banner.png b/images/comflowy_banner.png new file mode 100644 index 0000000..3f6641e Binary files /dev/null and b/images/comflowy_banner.png differ diff --git a/workflows/LLM_CN.json b/workflows/LLM_CN.json index 455aaa3..c952ea4 100644 --- a/workflows/LLM_CN.json +++ b/workflows/LLM_CN.json @@ -390,7 +390,7 @@ "一艘古代战舰", "# Role： Stable Diffusion prompt 助理\n你来充当一位有艺术气息的Stable Diffusion prompt 助理。\n\n## 任务\n我用自然语言告诉你要生成的prompt的主题，你的任务是根据这个主题想象一幅完整的画面，然后转化成一份详细的、高质量的prompt，让Stable Diffusion可以生成高质量的图像。\n\n## 背景介绍\nStable Diffusion是一款利用深度学习的文生图模型，支持通过使用 prompt 来产生新的图像，描述要包含或省略的元素。\n\n## prompt 概念\n- prompt 用来描述图像，由普通常见的单词构成，使用英文半角\",\"做为分隔符。\n- negative prompt用来描述你不想在生成的图像中出现的内容。\n- 以\",\"分隔的每个单词或词组称为 tag。所以prompt是由系列由\",\"分隔的tag组成的。\n\n## () 和 [] 语法\n调整关键字强度的等效方法是使用 () 和 []。 (keyword) 将tag的强度增加 1.1 倍，与 (keyword:1.1) 相同，最多可加三层。 [keyword] 将强度降低 0.9 倍，与 (keyword:0.9) 相同。\n\n## Prompt 格式要求\n下面我将说明 prompt 的生成步骤，这里的 prompt 可用于描述人物、风景、物体或抽象数字艺术图画。你可以根据需要添加合理的、但不少于5处的画面细节。\n\n### prompt 要求\n- prompt 内容包含画面主体、材质、附加细节、图像质量、艺术风格、色彩色调、灯光等部分，但你输出的 prompt 不能分段，例如类似\"medium:\"这样的分段描述是不需要的，也不能包含\":\"和\".\"。\n- 画面主体：不简短的英文描述画面主体, 如 A girl in a garden，主体细节概括（主体可以是人、事、物、景）画面核心内容。这部分根据我每次给你的主题来生成。你可以添加更多主题相关的合理的细节。\n- 对于人物主题，你必须描述人物的眼睛、鼻子、嘴唇，例如'beautiful detailed eyes,beautiful detailed lips,extremely detailed eyes and face,longeyelashes'，以免Stable Diffusion随机生成变形的面部五官，这点非常重要。你还可以描述人物的外表、情绪、衣服、姿势、视角、动作、背景等。人物属性中，1girl表示一个女孩，2girls表示两个女孩。\n- 材质：用来制作艺术品的材料。 例如：插图、油画、3D 渲染和摄影。 Medium 有很强的效果，因为一个关键字就可以极大地改变风格。\n- 附加细节：画面场景细节，或人物细节，描述画面细节内容，让图像看起来更充实和合理。这部分是可选的，要注意画面的整体和谐，不能与主题冲突。\n- 图像质量：这部分内容开头永远要加上“(best quality,4k,8k,highres,masterpiece:1.2),ultra-detailed,(realistic,photorealistic,photo-realistic:1.37)”， 这是高质量的标志。其它常用的提高质量的tag还有，你可以根据主题的需求添加：HDR,UHD,studio lighting,ultra-fine painting,sharp focus,physically-based rendering,extreme detail description,professional,vivid colors,bokeh。\n- 艺术风格：这部分描述图像的风格。加入恰当的艺术风格，能提升生成的图像效果。常用的艺术风格例如：portraits,landscape,horror,anime,sci-fi,photography,concept artists等。\n- 色彩色调：颜色，通过添加颜色来控制画面的整体颜色。\n- 灯光：整体画面的光线效果。\n\n### 限制：\n- tag 内容用英语单词或短语来描述，并不局限于我给你的单词。注意只能包含关键词或词组。\n- 注意不要输出句子，不要有任何解释。\n- tag数量限制40个以内，单词数量限制在60个以内。\n- tag不要带引号(\"\")。\n- 使用英文半角\",\"做分隔符。\n- tag 按重要性从高到低的顺序排列。\n- 我给你的主题可能是用中文描述，你给出的prompt和negative prompt只用英文，不要包含中文。", "THUDM/glm-4-9b-chat", - "b27f6e3a981156a0ccc4d5a1106f206c", + "", 28799307290994, "randomize", false, @@ -492,10 +492,10 @@ "config": {}, "extra": { "ds": { - "scale": 0.9090909090909091, + "scale": 0.8264462809917354, "offset": [ - 230.4790014253979, - 403.7018017828828 + 255.78564012490165, + 461.2748835297254 ] } }, diff --git a/workflows/Omost_LLM.json b/workflows/Omost_LLM.json new file mode 100644 index 0000000..f008693 --- /dev/null +++ b/workflows/Omost_LLM.json @@ -0,0 +1,597 @@ +{ + "last_node_id": 23, + "last_link_id": 20, + "nodes": [ + { + "id": 5, + "type": "EmptyLatentImage", + "pos": [ + 473, + 609 + ], + "size": { + "0": 315, + "1": 106 + }, + "flags": {}, + "order": 0, + "mode": 0, + "outputs": [ + { + "name": "LATENT", + "type": "LATENT", + "links": [ + 2 + ], + "slot_index": 0, + "label": "LATENT" + } + ], + "properties": { + "Node name for S&R": "EmptyLatentImage" + }, + "widgets_values": [ + 512, + 512, + 1 + ] + }, + { + "id": 8, + "type": "VAEDecode", + "pos": [ + 1209, + 188 + ], + "size": { + "0": 210, + "1": 46 + }, + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "samples", + "type": "LATENT", + "link": 7, + "label": "samples" + }, + { + "name": "vae", + "type": "VAE", + "link": 8, + "label": "vae" + } + ], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 9 + ], + "slot_index": 0, + "label": "IMAGE" + } + ], + "properties": { + "Node name for S&R": "VAEDecode" + } + }, + { + "id": 3, + "type": "KSampler", + "pos": [ + 863, + 186 + ], + "size": { + "0": 338.0391540527344, + "1": 571.4179077148438 + }, + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "MODEL", + "link": 1, + "label": "model" + }, + { + "name": "positive", + "type": "CONDITIONING", + "link": 16, + "label": "positive" + }, + { + "name": "negative", + "type": "CONDITIONING", + "link": 6, + "label": "negative" + }, + { + "name": "latent_image", + "type": "LATENT", + "link": 2, + "label": "latent_image" + } + ], + "outputs": [ + { + "name": "LATENT", + "type": "LATENT", + "links": [ + 7 + ], + "slot_index": 0, + "label": "LATENT" + } + ], + "properties": { + "Node name for S&R": "KSampler" + }, + "widgets_values": [ + 222261456855657, + "randomize", + 20, + 8, + "dpmpp_2m", + "karras", + 1 + ] + }, + { + "id": 9, + "type": "SaveImage", + "pos": [ + 1451, + 189 + ], + "size": { + "0": 239.60360717773438, + "1": 334.3671569824219 + }, + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 9, + "label": "images" + } + ], + "properties": { + "Node name for S&R": "SaveImage" + }, + "widgets_values": [ + "ComfyUI" + ] + }, + { + "id": 17, + "type": "Comflowy_Omost_To_Conditioning", + "pos": [ + 400, + 122 + ], + "size": { + "0": 317.4000244140625, + "1": 126 + }, + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [ + { + "name": "canvas_conds", + "type": "OMOST_CANVAS_CONDITIONING", + "link": 15, + "label": "canvas_conds" + }, + { + "name": "clip", + "type": "CLIP", + "link": 14, + "label": "clip" + } + ], + "outputs": [ + { + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 16 + ], + "slot_index": 0, + "shape": 3, + "label": "CONDITIONING" + } + ], + "properties": { + "Node name for S&R": "Comflowy_Omost_To_Conditioning" + }, + "widgets_values": [ + 0.2, + 0.8, + "average" + ] + }, + { + "id": 7, + "type": "CLIPTextEncode", + "pos": [ + 408, + 348 + ], + "size": { + "0": 425.27801513671875, + "1": 180.6060791015625 + }, + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "CLIP", + "link": 5, + "label": "clip" + } + ], + "outputs": [ + { + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 6 + ], + "slot_index": 0, + "label": "CONDITIONING" + } + ], + "properties": { + "Node name for S&R": "CLIPTextEncode" + }, + "widgets_values": [ + "text, watermark", + false + ] + }, + { + "id": 4, + "type": "CheckpointLoaderSimple", + "pos": [ + -127, + 394 + ], + "size": { + "0": 315, + "1": 98 + }, + "flags": {}, + "order": 1, + "mode": 0, + "outputs": [ + { + "name": "MODEL", + "type": "MODEL", + "links": [ + 1 + ], + "slot_index": 0, + "label": "MODEL" + }, + { + "name": "CLIP", + "type": "CLIP", + "links": [ + 5, + 14 + ], + "slot_index": 1, + "label": "CLIP" + }, + { + "name": "VAE", + "type": "VAE", + "links": [ + 8 + ], + "slot_index": 2, + "label": "VAE" + } + ], + "properties": { + "Node name for S&R": "CheckpointLoaderSimple" + }, + "widgets_values": [ + "dreamshaper_8.safetensors" + ] + }, + { + "id": 22, + "type": "Comflowy_Omost_Preview", + "pos": [ + -198, + 148 + ], + "size": { + "0": 229.20001220703125, + "1": 46 + }, + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [ + { + "name": "canvas_conds", + "type": "OMOST_CANVAS_CONDITIONING", + "link": 19, + "label": "canvas_conds" + } + ], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 20 + ], + "slot_index": 0, + "shape": 3, + "label": "IMAGE" + }, + { + "name": "JSON", + "type": "JSON", + "links": null, + "shape": 3, + "label": "JSON" + } + ], + "properties": { + "Node name for S&R": "Comflowy_Omost_Preview" + } + }, + { + "id": 14, + "type": "ShowText|pysssss", + "pos": [ + -216, + -299 + ], + "size": [ + 328.5512870484456, + 374.97700441128086 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "name": "text", + "type": "STRING", + "link": 13, + "widget": { + "name": "text" + }, + "label": "text" + } + ], + "outputs": [ + { + "name": "STRING", + "type": "STRING", + "links": null, + "shape": 6, + "label": "STRING" + } + ], + "properties": { + "Node name for S&R": "ShowText|pysssss" + }, + "widgets_values": [ + "", + "\n\n{\n \"global_description\": {\n \"description\": \"An ancient warship, weathered by time, dominates the center of the canvas.\",\n \"detailed_descriptions\": [\n \"The hull is covered in barnacles and moss, hinting at its long journey across the seas.\",\n \"The sails are tattered and faded, yet they still hold a sense of grandeur.\",\n \"The ship's rigging is intricate, showcasing the craftsmanship of a bygone era.\"\n ],\n \"tags\": \"ancient, warship, sea, weathered, barnacles, moss, sails, rigging\",\n \"HTML_web_color_name\": \"navy\"\n },\n \"local_descriptions\": [\n {\n \"location\": \"center\",\n \"offset\": \"no\",\n \"area\": \"a large square area\",\n \"distance_to_viewer\": 10.0,\n \"description\": \"An ancient warship stands prominently, its silhouette against the horizon.\",\n \"detailed_descriptions\": [\n \"The warship's silhouette is defined by its towering masts and the curve of its hull.\",\n \"The ship is adorned with intricate carvings and symbols of ancient cultures.\"\n ],\n \"tags\": \"ancient, warship, silhouette, masts, hull, carvings, symbols\",\n \"atmosphere\": \"nostalgic, mysterious\",\n \"style\": \"realistic\",\n \"quality_meta\": \"vivid\",\n \"HTML_web_color_name\": \"navy\"\n },\n {\n \"location\": \"top-right\",\n \"offset\": \"upper-right\",\n \"area\": \"a small square area\",\n \"distance_to_viewer\": 7.0,\n \"description\": \"A distant view of the ship's stern, with a flag waving in the breeze.\",\n \"detailed_descriptions\": [\n \"The flag is a deep red, symbolizing the bravery of the crew who once sailed this vessel.\"\n ],\n \"tags\": \"ship's stern, flag, red, bravery\",\n \"atmosphere\": \"victorious, nostalgic\",\n \"style\": \"realistic\",\n \"quality_meta\": \"vivid\",\n \"HTML_web_color_name\": \"crimson\"\n }\n ]\n}\n" + ] + }, + { + "id": 23, + "type": "PreviewImage", + "pos": [ + 138, + 87 + ], + "size": [ + 210, + 246 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 20, + "label": "images" + } + ], + "properties": { + "Node name for S&R": "PreviewImage" + } + }, + { + "id": 16, + "type": "Comflowy_Omost_LLM", + "pos": [ + -695, + -31 + ], + "size": { + "0": 400, + "1": 200 + }, + "flags": {}, + "order": 2, + "mode": 0, + "outputs": [ + { + "name": "canvas_conds", + "type": "OMOST_CANVAS_CONDITIONING", + "links": [ + 15, + 19 + ], + "slot_index": 0, + "shape": 3, + "label": "canvas_conds" + }, + { + "name": "generated_text", + "type": "STRING", + "links": [ + 13 + ], + "slot_index": 1, + "shape": 3, + "label": "generated_text" + } + ], + "properties": { + "Node name for S&R": "Comflowy_Omost_LLM" + }, + "widgets_values": [ + "An ancient warship", + "THUDM/glm-4-9b-chat", + "", + 673046078093462, + "randomize", + false + ] + } + ], + "links": [ + [ + 1, + 4, + 0, + 3, + 0, + "MODEL" + ], + [ + 2, + 5, + 0, + 3, + 3, + "LATENT" + ], + [ + 5, + 4, + 1, + 7, + 0, + "CLIP" + ], + [ + 6, + 7, + 0, + 3, + 2, + "CONDITIONING" + ], + [ + 7, + 3, + 0, + 8, + 0, + "LATENT" + ], + [ + 8, + 4, + 2, + 8, + 1, + "VAE" + ], + [ + 9, + 8, + 0, + 9, + 0, + "IMAGE" + ], + [ + 13, + 16, + 1, + 14, + 0, + "STRING" + ], + [ + 14, + 4, + 1, + 17, + 1, + "CLIP" + ], + [ + 15, + 16, + 0, + 17, + 0, + "OMOST_CANVAS_CONDITIONING" + ], + [ + 16, + 17, + 0, + 3, + 1, + "CONDITIONING" + ], + [ + 19, + 16, + 0, + 22, + 0, + "OMOST_CANVAS_CONDITIONING" + ], + [ + 20, + 22, + 0, + 23, + 0, + "IMAGE" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.6209213230591554, + "offset": [ + 739.9752097484295, + 420.49411898715607 + ] + } + }, + "version": 0.4 +} \ No newline at end of file