67 lines
52 KiB
JSON
67 lines
52 KiB
JSON
[
|
||
{
|
||
"name": "添加LoRA",
|
||
"description": "在现有工作流中添加LoRA节点",
|
||
"content": "在现有工作流中添加LoRA节点，确保与现有模型和提示词节点正确连接\n 在checkpoint节点后添加LoRA节点。\n {\n \"1\": {\n \"inputs\": {\n \"lora_name\": \"DOG.safetensors\",\n \"strength_model\": 1,\n \"strength_clip\": 1,\n \"model\": [\n \"2\",\n 0\n ],\n \"clip\": [\n \"2\",\n 1\n ]\n },\n \"class_type\": \"LoraLoader\",\n \"_meta\": {\n \"title\": \"Load LoRA\"\n }\n }"
|
||
},
|
||
{
|
||
"name": "后处理增强",
|
||
"description": "后处理增强，例如在Preview Image或Save Image节点后添加高清放大功能（如Real-ESRGAN、ESRGAN等）; 或者添加图像缩放节点",
|
||
"content": "- 在Preview Image或Save Image节点后添加高清放大功能（如Real-ESRGAN、ESRGAN等）\n - 添加图像缩放节点\n {\n \"1\": {\n \"inputs\": {\n \"width\": 512,\n \"height\": 512,\n \"interpolation\": \"nearest\",\n \"method\": \"stretch\",\n \"condition\": \"always\",\n \"multiple_of\": 0\n },\n \"class_type\": \"ImageResize+\",\n \"_meta\": {\n \"title\": \"🔧 Image Resize\"\n }\n }\n}\n - 添加图像尺寸调整节点\n {\n \"2\": {\n \"inputs\": {\n \"aspect_ratio\": \"original\",\n \"proportional_width\": 2,\n \"proportional_height\": 1,\n \"fit\": \"letterbox\",\n \"method\": \"lanczos\",\n \"round_to_multiple\": \"8\",\n \"scale_to_longest_side\": false,\n \"longest_side\": 1024\n },\n \"class_type\": \"LayerUtility: ImageScaleByAspectRatio\",\n \"_meta\": {\n \"title\": \"LayerUtility: ImageScaleByAspectRatio\"\n }\n }\n}\n -添加图像放大节点\n \"11\": {\n \"inputs\": {\n \"width\": 512,\n \"height\": 512,\n \"upscale_method\": \"nearest-exact\",\n \"keep_proportion\": false,\n \"divisible_by\": 2,\n \"crop\": \"disabled\",\n \"image\": [\n \"12\",\n 0\n ]\n },\n \"class_type\": \"ImageResizeKJ\",\n \"_meta\": {\n \"title\": \"Resize Image\"\n }\n },\n -添加VAEdecode节点\n \"12\": {\n \"inputs\": {},\n \"class_type\": \"VAEDecode\",\n \"_meta\": {\n \"title\": \"VAE Decode\"\n }\n }\n}"
|
||
},
|
||
{
|
||
"name": "提示词优化",
|
||
"description": "修改现有提示词节点的内容(提示词应该在(CLIP Text Encode Prompt或Text _O节点内编辑); 添加单独的提示词输入节点",
|
||
"content": "{\n \"12\": {\n \"inputs\": {\n \"text\": [\n \"13\",\n 0\n ]\n },\n \"class_type\": \"CLIPTextEncode\",\n \"_meta\": {\n \"title\": \"CLIP Text Encode (Prompt)\"\n }\n },\n \"13\": {\n \"inputs\": {\n \"delimiter\": \", \",\n \"clean_whitespace\": \"true\",\n \"text_a\": [\n \"15\",\n 0\n ],\n \"text_b\": [\n \"16\",\n 0\n ]\n },\n \"class_type\": \"Text Concatenate\",\n \"_meta\": {\n \"title\": \"Text Concatenate\"\n }\n },\n \"15\": {\n \"inputs\": {\n \"text\": \"\"\n },\n \"class_type\": \"Text _O\",\n \"_meta\": {\n \"title\": \"Text _O\"\n }\n },\n \"16\": {\n \"inputs\": {\n \"text\": \"\"\n },\n \"class_type\": \"Text _O\",\n \"_meta\": {\n \"title\": \"Text _O\"\n }\n }\n}"
|
||
},
|
||
{
|
||
"name": "图像反推",
|
||
"description": "理解图片信息并用文字表达出来",
|
||
"content": "添加图像反推节点（如CLIP Interrogator）\n{\n \"11\": {\n \"inputs\": {\n \"prompt_mode\": \"fast\",\n \"image_analysis\": \"off\"\n },\n \"class_type\": \"ClipInterrogator\",\n \"_meta\": {\n \"title\": \"Clip Interrogator ♾️Mixlab\"\n }\n }\n}\n - 添加更复杂或者更好用的图像反推节点(加载图片使用florence2进行反推)\n {\n \"6\": {\n \"inputs\": {\n \"image\": \"06.JPG\"\n },\n \"class_type\": \"LoadImage\",\n \"_meta\": {\n \"title\": \"$image.image!:The image to analyze, must be a url\"\n }\n },\n \"10\": {\n \"inputs\": {\n \"model\": \"microsoft/Florence-2-large\",\n \"precision\": \"fp16\",\n \"attention\": \"sdpa\"\n },\n \"class_type\": \"DownloadAndLoadFlorence2Model\",\n \"_meta\": {\n \"title\": \"DownloadAndLoadFlorence2Model\"\n }\n },\n \"11\": {\n \"inputs\": {\n \"text_input\": \"\",\n \"task\": \"more_detailed_caption\",\n \"fill_mask\": true,\n \"keep_model_loaded\": false,\n \"max_new_tokens\": 1024,\n \"num_beams\": 3,\n \"do_sample\": true,\n \"output_mask_select\": \"\",\n \"seed\": 1098631327477633,\n \"image\": [\n \"6\",\n 0\n ],\n \"florence2_model\": [\n \"10\",\n 0\n ]\n },\n \"class_type\": \"Florence2Run\",\n \"_meta\": {\n \"title\": \"Florence2Run\"\n }\n },\n \"18\": {\n \"inputs\": {\n \"anything\": [\n \"11\",\n 2\n ]\n },\n \"class_type\": \"easy showAnything\",\n \"_meta\": {\n \"title\": \"Show Any\"\n }\n },\n \"20\": {\n \"inputs\": {\n \"value\": \"Generate high-quality text descriptions from images using local Florence model.\\n \\n Main use cases:\\n 1. **Reverse image prompt generation**:\\n - When users upload an image and want to get prompts for AI art generation\\n - Analyzes visual elements, style, composition, etc. to generate prompts for Stable Diffusion, DALL-E, and other models\\n - In this case, return the tool's raw output directly to users without any modification or summary\\n - Users can directly use these prompts for image generation\\n 2. **Image content understanding**:\\n - When users ask about specific content, objects, scenes, people, etc. in the image\\n - Need to understand the semantic content of the image and answer users' specific questions\\n - In this case, combine tool output with conversation context to give users contextually appropriate natural responses\\n - Don't return raw output directly, but provide targeted replies based on understanding results\"\n },\n \"class_type\": \"PrimitiveStringMultiline\",\n \"_meta\": {\n \"title\": \"MCP\"\n }\n }\n}"
|
||
},
|
||
{
|
||
"name": "sdxl特征保持",
|
||
"description": "当用户在使用sdxl工作流并需提及特征保持时优先推荐该类工作流，旨在保持图像的特征提取、保持主体结构不变、保持主体形状、控制人物角色姿态、保持场景的深度和空间结构、基于线稿或者草图生成图像等场景下，可以用添加ControlNet节点来实现",
|
||
"content": "**ControlNet集成**：(preprocessor可选canny、depth等参数,模型样式选择，Controlnet开始、结束权重)\n {\n \"22\": {\n \"inputs\": {\n \"strength\": 1,\n \"start_percent\": 0,\n \"end_percent\": 1,\n \"control_net\": [\n \"23\",\n 0\n ],\n \"image\": [\n \"24\",\n 0\n ]\n },\n \"class_type\": \"ControlNetApplyAdvanced\",\n \"_meta\": {\n \"title\": \"Apply ControlNet\"\n }\n },\n \"23\": {\n \"inputs\": {\n \"control_net_name\": \"ControlNet-Standard-Lineart-for-SDXL.safetensors\"\n },\n \"class_type\": \"ControlNetLoader\",\n \"_meta\": {\n \"title\": \"Load ControlNet Model\"\n }\n },\n \"24\": {\n \"inputs\": {\n \"preprocessor\": \"none\",\n \"resolution\": 512\n },\n \"class_type\": \"AIO_Preprocessor\",\n \"_meta\": {\n \"title\": \"AIO Aux Preprocessor\"\n }\n }\n}"
|
||
},
|
||
{
|
||
"name": "flux风格特征迁移",
|
||
"description": "当用户在使用flux的工作流并提及风格特征迁移时优先推荐该节点，该类节用途主要应用于flux工作流的图片风格特征迁移和提取，风格转换，两张图片参考迁移，重绘遮罩区域或重绘背景，使用时请先分析是否为flux工作流",
|
||
"content": "需要注意：Flux_redux是多个节点连接的组合，针对reduxadvanced节点中condition、style_model、clip_vision这三类属于必须连接项、image可以选择加载图片或从vaedeconde后面接入、mask类型属于选择性连接，当用户提到遮罩或限定区域重绘时需要连接，其他情况请按照下述json进行参考改写。\n{\n \"1\": {\n \"inputs\": {\n \"downsampling_factor\": 3,\n \"downsampling_function\": \"area\",\n \"mode\": \"center crop (square)\",\n \"weight\": 1,\n \"autocrop_margin\": 0.1,\n \"style_model\": [\n \"2\",\n 0\n ],\n \"clip_vision\": [\n \"3\",\n 0\n ]\n },\n \"class_type\": \"ReduxAdvanced\",\n \"_meta\": {\n \"title\": \"ReduxAdvanced\"\n }\n },\n \"2\": {\n \"inputs\": {\n \"style_model_name\": \"flux1-redux-dev.safetensors\"\n },\n \"class_type\": \"StyleModelLoader\",\n \"_meta\": {\n \"title\": \"Load Style Model\"\n }\n },\n \"3\": {\n \"inputs\": {\n \"clip_name\": \"sigclip_vision_patch14_384.safetensors\"\n },\n \"class_type\": \"CLIPVisionLoader\",\n \"_meta\": {\n \"title\": \"Load CLIP Vision\"\n }\n }\n}"
|
||
},
|
||
{
|
||
"name": "sdxl特征迁移",
|
||
"description": "当用户在使用sdxl工作流并提及特征迁移时优先推荐该类工作流，旨在保持图像的特征提取、颜色提取,保持主体不变重绘背景或改变遮罩区域内容，可以用添加IPAdapter Advanced节点来实现",
|
||
"content": "**IPAdapter集成**：(weight type可选linear、ease in-out等参数,weight可选0.1-1开始、结束权重可选0.1-1) {\n \"1\": {\n \"inputs\": {\n \"weight\": 1,\n \"weight_type\": \"linear\",\n \"combine_embeds\": \"concat\",\n \"start_at\": 0,\n \"end_at\": 1,\n \"embeds_scaling\": \"V only\",\n \"ipadapter\": [\n \"2\",\n 0\n ],\n \"clip_vision\": [\n \"3\",\n 0\n ]\n },\n \"class_type\": \"IPAdapterAdvanced\",\n \"_meta\": {\n \"title\": \"IPAdapter Advanced\"\n }\n },\n \"2\": {\n \"inputs\": {\n \"ipadapter_file\": \"ip-adapter_sdxl_vit-h.safetensors\"\n },\n \"class_type\": \"IPAdapterModelLoader\",\n \"_meta\": {\n \"title\": \"IPAdapter Model Loader\"\n }\n },\n \"3\": {\n \"inputs\": {\n \"clip_name\": \"CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors\"\n },\n \"class_type\": \"CLIPVisionLoader\",\n \"_meta\": {\n \"title\": \"Load CLIP Vision\"\n }\n }\n}"
|
||
},
|
||
{
|
||
"name": "扩图",
|
||
"description": "对图片进行外补扩充，使其图片可以扩充到指定的尺寸大小且外扩像素的内容能够跟原图风格保持一致，常应用于场景图片扩充、将图片外扩填充，当用户提及到扩图、图片外补、将图片扩充到指定尺寸等需求时优先推荐该类工作流",
|
||
"content": "这里要注意参考一下几个节点的值，加载的图片输入必须连接到pad image for outpaintng和Getresolution两个节点上面，输入的方式可以为load_image或者从当前画布的图片输出中连接。针对于图片的上下左右四个方向进行自定义支持计算根据用户描述进行对应的数值换算，除此之外，该工作流以Flux_fiil作为扩图原理，详细的流程请参考一下json，结合用户需求来进行改写，当使用该经验时严格按照一下上述描述和以下json流程进行改写。\n{\n \"id\": \"79aace38-7851-4b96-bd56-af64f0d7dfab\",\n \"revision\": 0,\n \"last_node_id\": 23,\n \"last_link_id\": 28,\n \"nodes\": [\n {\n \"id\": 2,\n \"type\": \"FluxGuidance\",\n \"pos\": [\n 2872.55078125,\n 689.3768310546875\n ],\n \"size\": [\n 220,\n 58\n ],\n \"flags\": {},\n \"order\": 7,\n \"mode\": 0,\n \"inputs\": [\n {\n \"label\": \"条件\",\n \"name\": \"conditioning\",\n \"type\": \"CONDITIONING\",\n \"link\": 1\n }\n ],\n \"outputs\": [\n {\n \"label\": \"条件\",\n \"name\": \"CONDITIONING\",\n \"type\": \"CONDITIONING\",\n \"slot_index\": 0,\n \"links\": [\n 18\n ]\n }\n ],\n \"properties\": {\n \"cnr_id\": \"comfy-core\",\n \"ver\": \"0.3.51\",\n \"widget_ue_connectable\": {},\n \"Node name for S&R\": \"FluxGuidance\"\n },\n \"widgets_values\": [\n 30\n ]\n },\n {\n \"id\": 3,\n \"type\": \"CLIPTextEncode\",\n \"pos\": [\n 2887.37939453125,\n 797.4251708984375\n ],\n \"size\": [\n 210,\n 76\n ],\n \"flags\": {},\n \"order\": 0,\n \"mode\": 0,\n \"inputs\": [\n {\n \"label\": \"CLIP\",\n \"name\": \"clip\",\n \"type\": \"CLIP\",\n \"link\": null\n }\n ],\n \"outputs\": [\n {\n \"label\": \"条件\",\n \"name\": \"CONDITIONING\",\n \"type\": \"CONDITIONING\",\n \"links\": [\n 1,\n 16\n ]\n }\n ],\n \"properties\": {\n \"cnr_id\": \"comfy-core\",\n \"ver\": \"0.3.51\",\n \"widget_ue_connectable\": {},\n \"Node name for S&R\": \"CLIPTextEncode\"\n },\n \"widgets_values\": [\n \"\"\n ]\n },\n {\n \"id\": 6,\n \"type\": \"VAEDecode\",\n \"pos\": [\n 3464.810791015625,\n 875.4022827148438\n ],\n \"size\": [\n 140,\n 46\n ],\n \"flags\": {},\n \"order\": 18,\n \"mode\": 0,\n \"inputs\": [\n {\n \"label\": \"Latent\",\n \"name\": \"samples\",\n \"type\": \"LATENT\",\n \"link\": 4\n },\n {\n \"label\": \"VAE\",\n \"name\": \"vae\",\n \"type\": \"VAE\",\n \"link\": 5\n }\n ],\n \"outputs\": [\n {\n \"label\": \"图像\",\n \"name\": \"IMAGE\",\n \"type\": \"IMAGE\",\n \"slot_index\": 0,\n \"links\": [\n 28\n ]\n }\n ],\n \"properties\": {\n \"cnr_id\": \"comfy-core\",\n \"ver\": \"0.3.51\",\n \"widget_ue_connectable\": {},\n \"Node name for S&R\": \"VAEDecode\"\n }\n },\n {\n \"id\": 7,\n \"type\": \"KSampler\",\n \"pos\": [\n 3449.30126953125,\n 561.646728515625\n ],\n \"size\": [\n 272.61431884765625,\n 262\n ],\n \"flags\": {},\n \"order\": 17,\n \"mode\": 0,\n \"inputs\": [\n {\n \"label\": \"模型\",\n \"name\": \"model\",\n \"type\": \"MODEL\",\n \"link\": 6\n },\n {\n \"label\": \"正面条件\",\n \"name\": \"positive\",\n \"type\": \"CONDITIONING\",\n \"link\": 7\n },\n {\n \"label\": \"负面条件\",\n \"name\": \"negative\",\n \"type\": \"CONDITIONING\",\n \"link\": 8\n },\n {\n \"label\": \"Latent\",\n \"name\": \"latent_image\",\n \"type\": \"LATENT\",\n \"link\": 9\n }\n ],\n \"outputs\": [\n {\n \"label\": \"Latent\",\n \"name\": \"LATENT\",\n \"type\": \"LATENT\",\n \"slot_index\": 0,\n \"links\": [\n 4\n ]\n }\n ],\n \"properties\": {\n \"cnr_id\": \"comfy-core\",\n \"ver\": \"0.3.51\",\n \"widget_ue_connectable\": {},\n \"Node name for S&R\": \"KSampler\"\n },\n \"widgets_values\": [\n 422431662489005,\n \"randomize\",\n 8,\n 1,\n \"euler\",\n \"normal\",\n 1\n ]\n },\n {\n \"id\": 8,\n \"type\": \"SimpleMath+\",\n \"pos\": [\n 3060.9716796875,\n 1245.92236328125\n ],\n \"size\": [\n 315,\n 98\n ],\n \"flags\": {},\n \"order\": 11,\n \"mode\": 0,\n \"inputs\": [\n {\n \"name\": \"a\",\n \"shape\": 7,\n \"type\": \"*\",\n \"link\": 10\n },\n {\n \"name\": \"b\",\n \"shape\": 7,\n \"type\": \"*\",\n \"link\": 11\n },\n {\n \"name\": \"c\",\n \"shape\": 7,\n \"type\": \"*\",\n \"link\": null\n }\n ],\n \"outputs\": [\n {\n \"name\": \"INT\",\n \"type\": \"INT\",\n \"slot_index\": 0,\n \"links\": [\n 14\n ]\n },\n {\n \"name\": \"FLOAT\",\n \"type\": \"FLOAT\",\n \"links\": null\n }\n ],\n \"properties\": {\n \"cnr_id\": \"comfyui_essentials\",\n \"ver\": \"cf703edb47ba65bc67507139a7d802b30d151343\",\n \"widget_ue_connectable\": {},\n \"Node name for S&R\": \"SimpleMath+\"\n },\n \"widgets_values\": [\n \"a-b\"\n ]\n },\n {\n \"id\": 9,\n \"type\": \"SimpleMath+\",\n \"pos\": [\n 3060.9716796875,\n 1385.92236328125\n ],\n \"size\": [\n 315,\n 98\n ],\n \"flags\": {},\n \"order\": 10,\n \"mode\": 0,\n \"inputs\": [\n {\n \"name\": \"a\",\n \"shape\": 7,\n \"type\": \"*\",\n \"link\": 12\n },\n {\n \"name\": \"b\",\n \"shape\": 7,\n \"type\": \"*\",\n \"link\": 13\n },\n {\n \"name\": \"c\",\n \"shape\": 7,\n \"type\": \"*\",\n \"link\": null\n }\n ],\n \"outputs\": [\n {\n \"name\": \"INT\",\n \"type\": \"INT\",\n \"slot_index\": 0,\n \"links\": [\n 15\n ]\n },\n {\n \"name\": \"FLOAT\",\n \"type\": \"FLOAT\",\n \"links\": null\n }\n ],\n \"properties\": {\n \"cnr_id\": \"comfyui_essentials\",\n \"ver\": \"cf703edb47ba65bc67507139a7d802b30d151343\",\n \"widget_ue_connectable\": {},\n \"Node name for S&R\": \"SimpleMath+\"\n },\n \"widgets_values\": [\n \"a-b\"\n ]\n },\n {\n \"id\": 10,\n \"type\": \"SimpleMath+\",\n \"pos\": [\n 3400.9716796875,\n 1135.92236328125\n ],\n \"size\": [\n 315,\n 98\n ],\n \"flags\": {},\n \"order\": 14,\n \"mode\": 0,\n \"inputs\": [\n {\n \"name\": \"a\",\n \"shape\": 7,\n \"type\": \"*\",\n \"link\": 14\n },\n {\n \"name\": \"b\",\n \"shape\": 7,\n \"type\": \"*\",\n \"link\": null\n },\n {\n \"name\": \"c\",\n \"shape\": 7,\n \"type\": \"*\",\n \"link\": null\n }\n ],\n \"outputs\": [\n {\n \"name\": \"INT\",\n \"type\": \"INT\",\n \"slot_index\": 0,\n \"links\": [\n 24,\n 25\n ]\n },\n {\n \"name\": \"FLOAT\",\n \"type\": \"FLOAT\",\n \"links\": null\n }\n ],\n \"properties\": {\n \"cnr_id\": \"comfyui_essentials\",\n \"ver\": \"cf703edb47ba65bc67507139a7d802b30d151343\",\n \"widget_ue_connectable\": {},\n \"Node name for S&R\": \"SimpleMath+\"\n },\n \"widgets_values\": [\n \"a/2\"\n ]\n },\n {\n \"id\": 11,\n \"type\": \"SimpleMath+\",\n \"pos\": [\n 3410.9716796875,\n 1275.92236328125\n ],\n \"size\": [\n 315,\n 98\n ],\n \"flags\": {},\n \"order\": 13,\n \"mode\": 0,\n \"inputs\": [\n {\n \"name\": \"a\",\n \"shape\": 7,\n \"type\": \"*\",\n \"link\": 15\n },\n {\n \"name\": \"b\",\n \"shape\": 7,\n \"type\": \"*\",\n \"link\": null\n },\n {\n \"name\": \"c\",\n \"shape\": 7,\n \"type\": \"*\",\n \"link\": null\n }\n ],\n \"outputs\": [\n {\n \"name\": \"INT\",\n \"type\": \"INT\",\n \"slot_index\": 0,\n \"links\": [\n 26,\n 27\n ]\n },\n {\n \"name\": \"FLOAT\",\n \"type\": \"FLOAT\",\n \"links\": null\n }\n ],\n \"properties\": {\n \"cnr_id\": \"comfyui_essentials\",\n \"ver\": \"cf703edb47ba65bc67507139a7d802b30d151343\",\n \"widget_ue_connectable\": {},\n \"Node name for S&R\": \"SimpleMath+\"\n },\n \"widgets_values\": [\n \"a/2\"\n ]\n },\n {\n \"id\": 12,\n \"type\": \"Int\",\n \"pos\": [\n 3400.9716796875,\n 1415.92236328125\n ],\n \"size\": [\n 315,\n 58\n ],\n \"flags\": {},\n \"order\": 1,\n \"mode\": 0,\n \"inputs\": [],\n \"outputs\": [\n {\n \"name\": \"INT\",\n \"type\": \"INT\",\n \"slot_index\": 0,\n \"links\": [\n 12\n ]\n }\n ],\n \"properties\": {\n \"cnr_id\": \"ComfyLiterals\",\n \"ver\": \"bdddb08ca82d90d75d97b1d437a652e0284a32ac\",\n \"widget_ue_connectable\": {},\n \"Node name for S&R\": \"Int\"\n },\n \"widgets_values\": [\n \"768\"\n ]\n },\n {\n \"id\": 13,\n \"type\": \"DualCLIPLoader\",\n \"pos\": [\n 2580.728271484375,\n 676.0438232421875\n ],\n \"size\": [\n 300,\n 122\n ],\n \"flags\": {},\n \"order\": 2,\n \"mode\": 0,\n \"inputs\": [],\n \"outputs\": [\n {\n \"label\": \"CLIP\",\n \"name\": \"CLIP\",\n \"type\": \"CLIP\",\n \"links\": []\n }\n ],\n \"properties\": {\n \"cnr_id\": \"comfy-core\",\n \"ver\": \"0.3.51\",\n \"widget_ue_connectable\": {},\n \"Node name for S&R\": \"DualCLIPLoader\"\n },\n \"widgets_values\": [\n \"clip_l.safetensors\",\n \"t5xxl_fp16.safetensors\",\n \"flux\",\n \"default\"\n ]\n },\n {\n \"id\": 14,\n \"type\": \"VAELoader\",\n \"pos\": [\n 2585.722900390625,\n 822.8394775390625\n ],\n \"size\": [\n 300,\n 58\n ],\n \"flags\": {},\n \"order\": 3,\n \"mode\": 0,\n \"inputs\": [],\n \"outputs\": [\n {\n \"label\": \"VAE\",\n \"name\": \"VAE\",\n \"type\": \"VAE\",\n \"slot_index\": 0,\n \"links\": [\n 5,\n 20\n ]\n }\n ],\n \"properties\": {\n \"cnr_id\": \"comfy-core\",\n \"ver\": \"0.3.51\",\n \"widget_ue_connectable\": {},\n \"Node name for S&R\": \"VAELoader\"\n },\n \"widgets_values\": [\n \"ae.safetensors\"\n ]\n },\n {\n \"id\": 15,\n \"type\": \"ConditioningZeroOut\",\n \"pos\": [\n 2881.81982421875,\n 625.4481201171875\n ],\n \"size\": [\n 159.60000610351562,\n 26\n ],\n \"flags\": {\n \"collapsed\": false\n },\n \"order\": 8,\n \"mode\": 0,\n \"inputs\": [\n {\n \"label\": \"条件\",\n \"name\": \"conditioning\",\n \"type\": \"CONDITIONING\",\n \"link\": 16\n }\n ],\n \"outputs\": [\n {\n \"label\": \"条件\",\n \"name\": \"CONDITIONING\",\n \"type\": \"CONDITIONING\",\n \"slot_index\": 0,\n \"links\": [\n 19\n ]\n }\n ],\n \"properties\": {\n \"cnr_id\": \"comfy-core\",\n \"ver\": \"0.3.51\",\n \"widget_ue_connectable\": {},\n \"Node name for S&R\": \"ConditioningZeroOut\"\n }\n },\n {\n \"id\": 16,\n \"type\": \"DifferentialDiffusion\",\n \"pos\": [\n 2883.218994140625,\n 554.0230102539062\n ],\n \"size\": [\n 184.8000030517578,\n 26\n ],\n \"flags\": {\n \"collapsed\": false\n },\n \"order\": 12,\n \"mode\": 0,\n \"inputs\": [\n {\n \"label\": \"模型\",\n \"name\": \"model\",\n \"type\": \"MODEL\",\n \"link\": 17\n }\n ],\n \"outputs\": [\n {\n \"label\": \"模型\",\n \"name\": \"MODEL\",\n \"type\": \"MODEL\",\n \"links\": [\n 6\n ]\n }\n ],\n \"properties\": {\n \"cnr_id\": \"comfy-core\",\n \"ver\": \"0.3.51\",\n \"widget_ue_connectable\": {},\n \"Node name for S&R\": \"DifferentialDiffusion\"\n }\n },\n {\n \"id\": 17,\n \"type\": \"UNETLoader\",\n \"pos\": [\n 2567.580810546875,\n 538.827392578125\n ],\n \"size\": [\n 300,\n 82\n ],\n \"flags\": {},\n \"order\": 4,\n \"mode\": 0,\n \"inputs\": [],\n \"outputs\": [\n {\n \"label\": \"模型\",\n \"name\": \"MODEL\",\n \"type\": \"MODEL\",\n \"slot_index\": 0,\n \"links\": [\n 23\n ]\n }\n ],\n \"properties\": {\n \"cnr_id\": \"comfy-core\",\n \"ver\": \"0.3.51\",\n \"widget_ue_connectable\": {},\n \"Node name for S&R\": \"UNETLoader\"\n },\n \"widgets_values\": [\n \"flux1-fill-dev.safetensors\",\n \"default\"\n ]\n },\n {\n \"id\": 18,\n \"type\": \"InpaintModelConditioning\",\n \"pos\": [\n 3103.51318359375,\n 561.2390747070312\n ],\n \"size\": [\n 302.4000244140625,\n 138\n ],\n \"flags\": {},\n \"order\": 16,\n \"mode\": 0,\n \"inputs\": [\n {\n \"label\": \"正面条件\",\n \"name\": \"positive\",\n \"type\": \"CONDITIONING\",\n \"link\": 18\n },\n {\n \"label\": \"负面条件\",\n \"name\": \"negative\",\n \"type\": \"CONDITIONING\",\n \"link\": 19\n },\n {\n \"label\": \"VAE\",\n \"name\": \"vae\",\n \"type\": \"VAE\",\n \"link\": 20\n },\n {\n \"label\": \"图像\",\n \"name\": \"pixels\",\n \"type\": \"IMAGE\",\n \"link\": 21\n },\n {\n \"label\": \"遮罩\",\n \"name\": \"mask\",\n \"type\": \"MASK\",\n \"link\": 22\n }\n ],\n \"outputs\": [\n {\n \"label\": \"正面条件\",\n \"name\": \"positive\",\n \"type\": \"CONDITIONING\",\n \"slot_index\": 0,\n \"links\": [\n 7\n ]\n },\n {\n \"label\": \"负面条件\",\n \"name\": \"negative\",\n \"type\": \"CONDITIONING\",\n \"slot_index\": 1,\n \"links\": [\n 8\n ]\n },\n {\n \"label\": \"Latent\",\n \"name\": \"latent\",\n \"type\": \"LATENT\",\n \"slot_index\": 2,\n \"links\": [\n 9\n ]\n }\n ],\n \"properties\": {\n \"cnr_id\": \"comfy-core\",\n \"ver\": \"0.3.51\",\n \"widget_ue_connectable\": {},\n \"Node name for S&R\": \"InpaintModelConditioning\"\n },\n \"widgets_values\": [\n false\n ]\n },\n {\n \"id\": 19,\n \"type\": \"LoraLoaderModelOnly\",\n \"pos\": [\n 3100.936767578125,\n 731.5386962890625\n ],\n \"size\": [\n 317.4976806640625,\n 84.57483673095703\n ],\n \"flags\": {\n \"collapsed\": false\n },\n \"order\": 9,\n \"mode\": 0,\n \"inputs\": [\n {\n \"label\": \"model\",\n \"name\": \"model\",\n \"type\": \"MODEL\",\n \"link\": 23\n }\n ],\n \"outputs\": [\n {\n \"label\": \"MODEL\",\n \"name\": \"MODEL\",\n \"type\": \"MODEL\",\n \"slot_index\": 0,\n \"links\": [\n 17\n ]\n }\n ],\n \"properties\": {\n \"cnr_id\": \"comfy-core\",\n \"ver\": \"0.3.51\",\n \"widget_ue_connectable\": {},\n \"Node name for S&R\": \"LoraLoaderModelOnly\"\n },\n \"widgets_values\": [\n \"FLUX.1-Turbo-Alpha.safetensors\",\n 1\n ]\n },\n {\n \"id\": 20,\n \"type\": \"ImagePadForOutpaint\",\n \"pos\": [\n 3051.916259765625,\n 916.375732421875\n ],\n \"size\": [\n 315,\n 174\n ],\n \"flags\": {},\n \"order\": 15,\n \"mode\": 0,\n \"inputs\": [\n {\n \"label\": \"图像\",\n \"name\": \"image\",\n \"type\": \"IMAGE\",\n \"link\": null\n },\n {\n \"name\": \"left\",\n \"type\": \"INT\",\n \"widget\": {\n \"name\": \"left\"\n },\n \"link\": 24\n },\n {\n \"name\": \"top\",\n \"type\": \"INT\",\n \"widget\": {\n \"name\": \"top\"\n },\n \"link\": 25\n },\n {\n \"name\": \"right\",\n \"type\": \"INT\",\n \"widget\": {\n \"name\": \"right\"\n },\n \"link\": 26\n },\n {\n \"name\": \"bottom\",\n \"type\": \"INT\",\n \"widget\": {\n \"name\": \"bottom\"\n },\n \"link\": 27\n }\n ],\n \"outputs\": [\n {\n \"label\": \"图像\",\n \"name\": \"IMAGE\",\n \"type\": \"IMAGE\",\n \"slot_index\": 0,\n \"links\": [\n 21\n ]\n },\n {\n \"label\": \"遮罩\",\n \"name\": \"MASK\",\n \"type\": \"MASK\",\n \"slot_index\": 1,\n \"links\": [\n 22\n ]\n }\n ],\n \"properties\": {\n \"cnr_id\": \"comfy-core\",\n \"ver\": \"0.3.51\",\n \"widget_ue_connectable\": {},\n \"Node name for S&R\": \"ImagePadForOutpaint\"\n },\n \"widgets_values\": [\n 0,\n 288,\n 0,\n 288,\n 40\n ]\n },\n {\n \"id\": 21,\n \"type\": \"Get resolution [Crystools]\",\n \"pos\": [\n 2687.459228515625,\n 1054.2020263671875\n ],\n \"size\": [\n 214.20001220703125,\n 96\n ],\n \"flags\": {},\n \"order\": 6,\n \"mode\": 0,\n \"inputs\": [\n {\n \"name\": \"image\",\n \"type\": \"IMAGE\",\n \"link\": null\n }\n ],\n \"outputs\": [\n {\n \"name\": \"width\",\n \"type\": \"INT\",\n \"slot_index\": 0,\n \"links\": [\n 13\n ]\n },\n {\n \"name\": \"height\",\n \"type\": \"INT\",\n \"slot_index\": 1,\n \"links\": [\n 11\n ]\n }\n ],\n \"properties\": {\n \"cnr_id\": \"ComfyUI-Crystools\",\n \"ver\": \"0820a7560bcc405ef6d0a7c5c53a83cc02ae7db2\",\n \"widget_ue_connectable\": {},\n \"Node name for S&R\": \"Get resolution [Crystools]\"\n }\n },\n {\n \"id\": 22,\n \"type\": \"Int\",\n \"pos\": [\n 3060.9716796875,\n 1135.92236328125\n ],\n \"size\": [\n 315,\n 58\n ],\n \"flags\": {},\n \"order\": 5,\n \"mode\": 0,\n \"inputs\": [],\n \"outputs\": [\n {\n \"name\": \"INT\",\n \"type\": \"INT\",\n \"slot_index\": 0,\n \"links\": [\n 10\n ]\n }\n ],\n \"properties\": {\n \"cnr_id\": \"ComfyLiterals\",\n \"ver\": \"bdddb08ca82d90d75d97b1d437a652e0284a32ac\",\n \"widget_ue_connectable\": {},\n \"Node name for S&R\": \"Int\"\n },\n \"widgets_values\": [\n \"1344\"\n ]\n },\n {\n \"id\": 23,\n \"type\": \"PreviewImage\",\n \"pos\": [\n 3666.00146484375,\n 908.7727661132812\n ],\n \"size\": [\n 229.00827026367188,\n 143.92103576660156\n ],\n \"flags\": {},\n \"order\": 19,\n \"mode\": 0,\n \"inputs\": [\n {\n \"label\": \"图像\",\n \"name\": \"images\",\n \"type\": \"IMAGE\",\n \"link\": 28\n }\n ],\n \"outputs\": [],\n \"properties\": {\n \"cnr_id\": \"comfy-core\",\n \"ver\": \"0.3.51\",\n \"widget_ue_connectable\": {},\n \"Node name for S&R\": \"PreviewImage\"\n }\n }\n ],\n \"links\": [\n [\n 1,\n 3,\n 0,\n 2,\n 0,\n \"CONDITIONING\"\n ],\n [\n 4,\n 7,\n 0,\n 6,\n 0,\n \"LATENT\"\n ],\n [\n 5,\n 14,\n 0,\n 6,\n 1,\n \"VAE\"\n ],\n [\n 6,\n 16,\n 0,\n 7,\n 0,\n \"MODEL\"\n ],\n [\n 7,\n 18,\n 0,\n 7,\n 1,\n \"CONDITIONING\"\n ],\n [\n 8,\n 18,\n 1,\n 7,\n 2,\n \"CONDITIONING\"\n ],\n [\n 9,\n 18,\n 2,\n 7,\n 3,\n \"LATENT\"\n ],\n [\n 10,\n 22,\n 0,\n 8,\n 0,\n \"*\"\n ],\n [\n 11,\n 21,\n 1,\n 8,\n 1,\n \"*\"\n ],\n [\n 12,\n 12,\n 0,\n 9,\n 0,\n \"*\"\n ],\n [\n 13,\n 21,\n 0,\n 9,\n 1,\n \"*\"\n ],\n [\n 14,\n 8,\n 0,\n 10,\n 0,\n \"*\"\n ],\n [\n 15,\n 9,\n 0,\n 11,\n 0,\n \"*\"\n ],\n [\n 16,\n 3,\n 0,\n 15,\n 0,\n \"CONDITIONING\"\n ],\n [\n 17,\n 19,\n 0,\n 16,\n 0,\n \"MODEL\"\n ],\n [\n 18,\n 2,\n 0,\n 18,\n 0,\n \"CONDITIONING\"\n ],\n [\n 19,\n 15,\n 0,\n 18,\n 1,\n \"CONDITIONING\"\n ],\n [\n 20,\n 14,\n 0,\n 18,\n 2,\n \"VAE\"\n ],\n [\n 21,\n 20,\n 0,\n 18,\n 3,\n \"IMAGE\"\n ],\n [\n 22,\n 20,\n 1,\n 18,\n 4,\n \"MASK\"\n ],\n [\n 23,\n 17,\n 0,\n 19,\n 0,\n \"MODEL\"\n ],\n [\n 24,\n 10,\n 0,\n 20,\n 1,\n \"INT\"\n ],\n [\n 25,\n 10,\n 0,\n 20,\n 2,\n \"INT\"\n ],\n [\n 26,\n 11,\n 0,\n 20,\n 3,\n \"INT\"\n ],\n [\n 27,\n 11,\n 0,\n 20,\n 4,\n \"INT\"\n ],\n [\n 28,\n 6,\n 0,\n 23,\n 0,\n \"IMAGE\"\n ]\n ],\n \"groups\": [],\n \"config\": {},\n \"extra\": {\n \"ue_links\": [],\n \"ds\": {\n \"scale\": 0.2741546770739379,\n \"offset\": [\n 429.4114980165041,\n 104.68989334051173\n ]\n },\n \"frontendVersion\": \"1.24.4\",\n \"VHS_latentpreview\": false,\n \"VHS_latentpreviewrate\": 0,\n \"VHS_MetadataImage\": true,\n \"VHS_KeepIntermediate\": true\n },\n \"version\": 0.4\n}"
|
||
},
|
||
{
|
||
"name": "智能抠图",
|
||
"description": "添加背景移除节点（如SAM、U²-Net等）",
|
||
"content": "- 添加背景移除或抠图节点\n {\n \"7\": {\n \"inputs\": {\n \"rem_mode\": \"RMBG-1.4\",\n \"image_output\": \"Preview\",\n \"save_prefix\": \"ComfyUI\",\n \"torchscript_jit\": false,\n \"add_background\": \"none\",\n \"refine_foreground\": false\n },\n \"class_type\": \"easy imageRemBg\",\n \"_meta\": {\n \"title\": \"Image Remove Bg\"\n }\n }\n}\n - 添加SAM抠图节点\n {\n \"8\": {\n \"inputs\": {\n \"prompt\": \"\",\n \"threshold\": 0.3,\n \"sam_model\": [\n \"9\",\n 0\n ],\n \"grounding_dino_model\": [\n \"10\",\n 0\n ]\n },\n \"class_type\": \"GroundingDinoSAMSegment (segment anything)\",\n \"_meta\": {\n \"title\": \"GroundingDinoSAMSegment (segment anything)\"\n }\n },\n \"9\": {\n \"inputs\": {\n \"model_name\": \"sam_vit_h (2.56GB)\"\n },\n \"class_type\": \"SAMModelLoader (segment anything)\",\n \"_meta\": {\n \"title\": \"SAMModelLoader (segment anything)\"\n }\n },\n \"10\": {\n \"inputs\": {\n \"model_name\": \"GroundingDINO_SwinT_OGC (694MB)\"\n },\n \"class_type\": \"GroundingDinoModelLoader (segment anything)\",\n \"_meta\": {\n \"title\": \"GroundingDinoModelLoader (segment anything)\"\n }\n }\n}"
|
||
},
|
||
{
|
||
"name": "kontext图像编辑",
|
||
"description": "添加kontext系列节点(这个系列是文生图和图生图场景应用的模型和节点,适合用针对图像的融合，二次编辑,包括但不限于去水印、擦除物体、多元素融合、图片元素提取等)",
|
||
"content": "{\n \"6\": {\n \"inputs\": {\n \"text\": \"\",\n \"clip\": [\n \"38\",\n 0\n ]\n },\n \"class_type\": \"CLIPTextEncode\",\n \"_meta\": {\n \"title\": \"CLIP Text Encode (Prompt)\"\n }\n },\n \"8\": {\n \"inputs\": {\n \"samples\": [\n \"31\",\n 0\n ],\n \"vae\": [\n \"39\",\n 0\n ]\n },\n \"class_type\": \"VAEDecode\",\n \"_meta\": {\n \"title\": \"VAE Decode\"\n }\n },\n \"31\": {\n \"inputs\": {\n \"seed\": 584043043142251,\n \"steps\": 30,\n \"cfg\": 1.5,\n \"sampler_name\": \"euler\",\n \"scheduler\": \"simple\",\n \"denoise\": 1,\n \"model\": [\n \"37\",\n 0\n ],\n \"positive\": [\n \"35\",\n 0\n ],\n \"negative\": [\n \"135\",\n 0\n ],\n \"latent_image\": [\n \"124\",\n 0\n ]\n },\n \"class_type\": \"KSampler\",\n \"_meta\": {\n \"title\": \"KSampler\"\n }\n },\n \"35\": {\n \"inputs\": {\n \"guidance\": 2.5,\n \"conditioning\": [\n \"177\",\n 0\n ]\n },\n \"class_type\": \"FluxGuidance\",\n \"_meta\": {\n \"title\": \"FluxGuidance\"\n }\n },\n \"37\": {\n \"inputs\": {\n \"unet_name\": \"flux1-dev-kontext_fp8_scaled.safetensors\",\n \"weight_dtype\": \"fp8_e4m3fn\"\n },\n \"class_type\": \"UNETLoader\",\n \"_meta\": {\n \"title\": \"Load Diffusion Model\"\n }\n },\n \"38\": {\n \"inputs\": {\n \"clip_name1\": \"clip_l.safetensors\",\n \"clip_name2\": \"t5xxl_fp16.safetensors\",\n \"type\": \"flux\",\n \"device\": \"default\"\n },\n \"class_type\": \"DualCLIPLoader\",\n \"_meta\": {\n \"title\": \"DualCLIPLoader\"\n }\n },\n \"39\": {\n \"inputs\": {\n \"vae_name\": \"ae.safetensors\"\n },\n \"class_type\": \"VAELoader\",\n \"_meta\": {\n \"title\": \"Load VAE\"\n }\n },\n \"42\": {\n \"inputs\": {\n \"image\": [\n \"194\",\n 0\n ]\n },\n \"class_type\": \"FluxKontextImageScale\",\n \"_meta\": {\n \"title\": \"FluxKontextImageScale\"\n }\n },\n \"124\": {\n \"inputs\": {\n \"pixels\": [\n \"42\",\n 0\n ],\n \"vae\": [\n \"39\",\n 0\n ]\n },\n \"class_type\": \"VAEEncode\",\n \"_meta\": {\n \"title\": \"VAE Encode\"\n }\n },\n \"135\": {\n \"inputs\": {\n \"conditioning\": [\n \"6\",\n 0\n ]\n },\n \"class_type\": \"ConditioningZeroOut\",\n \"_meta\": {\n \"title\": \"ConditioningZeroOut\"\n }\n },\n \"177\": {\n \"inputs\": {\n \"conditioning\": [\n \"6\",\n 0\n ],\n \"latent\": [\n \"124\",\n 0\n ]\n },\n \"class_type\": \"ReferenceLatent\",\n \"_meta\": {\n \"title\": \"ReferenceLatent\"\n }\n },\n \"193\": {\n \"inputs\": {\n \"filename_prefix\": \"ComfyUI\",\n \"images\": [\n \"8\",\n 0\n ]\n },\n \"class_type\": \"SaveImage\",\n \"_meta\": {\n \"title\": \"Save Image\"\n }\n },\n \"194\": {\n \"inputs\": {\n \"image\": \"021175655C8A2A86C831C96855F3EF23.png\"\n },\n \"class_type\": \"LoadImage\",\n \"_meta\": {\n \"title\": \"Load Image\"\n }\n }\n}"
|
||
},
|
||
{
|
||
"name": "qwen image图像生成",
|
||
"description": "基于Qwen-Image多模态大模型的文生图解决方案，支持中英文提示词，擅长生成包含复杂文本的图像内容。适用于海报设计、广告创意、logo生成、字体设计、人像生成，也可以直接制作PPT和多种艺术风格图片的生成，当用户提及需要上述的类似需求和qwen_image图像生成时优先推荐该类型工作流。",
|
||
"content": "这里要特别注意：qwen_image的工作流类型对应专属的模型和节点，当用户画布已经存在其他工作流时不能与其他工作流的model节点和dual_clip节点共用，需要额外加载专属节点，以下是专属的节点和模型示例：\n{\n \"3\": {\n \"inputs\": {\n \"seed\": 619243763350601,\n \"steps\": 20,\n \"cfg\": 4,\n \"sampler_name\": \"euler\",\n \"scheduler\": \"simple\",\n \"denoise\": 1,\n \"model\": [\n \"66\",\n 0\n ],\n \"positive\": [\n \"6\",\n 0\n ],\n \"negative\": [\n \"7\",\n 0\n ],\n \"latent_image\": [\n \"58\",\n 0\n ]\n },\n \"class_type\": \"KSampler\",\n \"_meta\": {\n \"title\": \"KSampler\"\n }\n },\n \"6\": {\n \"inputs\": {\n \"text\": \"cute anime girl with massive fennec ears and a big fluffy fox tail with long wavy blonde hair between eyes and large blue eyes blonde colored eyelashes chubby wearing oversized clothes summer uniform long blue maxi skirt happy sitting on the side of the road in a run down dark gritty cyberpunk city with neon and a futuristic car in the rain at night while dipping her feet in a river of water with a single street light illuminating her, she is holding a sign that says \\"ComfyUI is the best\\" in cursive\",\n \"clip\": [\n \"38\",\n 0\n ]\n },\n \"class_type\": \"CLIPTextEncode\",\n \"_meta\": {\n \"title\": \"CLIP Text Encode (Positive Prompt)\"\n }\n },\n \"7\": {\n \"inputs\": {\n \"text\": \" \",\n \"clip\": [\n \"38\",\n 0\n ]\n },\n \"class_type\": \"CLIPTextEncode\",\n \"_meta\": {\n \"title\": \"CLIP Text Encode (Negative Prompt)\"\n }\n },\n \"8\": {\n \"inputs\": {\n \"samples\": [\n \"3\",\n 0\n ],\n \"vae\": [\n \"39\",\n 0\n ]\n },\n \"class_type\": \"VAEDecode\",\n \"_meta\": {\n \"title\": \"VAE Decode\"\n }\n },\n \"37\": {\n \"inputs\": {\n \"unet_name\": \"qwen_image_fp8_e4m3fn.safetensors\",\n \"weight_dtype\": \"default\"\n },\n \"class_type\": \"UNETLoader\",\n \"_meta\": {\n \"title\": \"Load Diffusion Model\"\n }\n },\n \"38\": {\n \"inputs\": {\n \"clip_name\": \"qwen_2.5_vl_7b_fp8_scaled.safetensors\",\n \"type\": \"qwen_image\",\n \"device\": \"default\"\n },\n \"class_type\": \"CLIPLoader\",\n \"_meta\": {\n \"title\": \"Load CLIP\"\n }\n },\n \"39\": {\n \"inputs\": {\n \"vae_name\": \"qwen_image_vae.safetensors\"\n },\n \"class_type\": \"VAELoader\",\n \"_meta\": {\n \"title\": \"Load VAE\"\n }\n },\n \"58\": {\n \"inputs\": {\n \"width\": 1328,\n \"height\": 1328,\n \"batch_size\": 1\n },\n \"class_type\": \"EmptySD3LatentImage\",\n \"_meta\": {\n \"title\": \"EmptySD3LatentImage\"\n }\n },\n \"66\": {\n \"inputs\": {\n \"shift\": 3.500000000000001,\n \"model\": [\n \"37\",\n 0\n ]\n },\n \"class_type\": \"ModelSamplingAuraFlow\",\n \"_meta\": {\n \"title\": \"ModelSamplingAuraFlow\"\n }\n }\n}"
|
||
},
|
||
{
|
||
"name": "wan2.2图生视频",
|
||
"description": "wan2.2是图像生成视频的模型，主要用来帮助用户根据图片加提示词来生成视频。",
|
||
"content": "{\n \"11\": {\n \"inputs\": {\n \"model_name\": \"umt5-xxl-enc-bf16.safetensors\",\n \"precision\": \"bf16\",\n \"load_device\": \"offload_device\",\n \"quantization\": \"disabled\"\n },\n \"class_type\": \"LoadWanVideoT5TextEncoder\",\n \"_meta\": {\n \"title\": \"WanVideo T5 Text Encoder Loader\"\n }\n },\n \"16\": {\n \"inputs\": {\n \"positive_prompt\": \"猫咪的头部猛的向前一探\",\n \"negative_prompt\": \"色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走\",\n \"force_offload\": true,\n \"use_disk_cache\": false,\n \"device\": \"gpu\",\n \"t5\": [\n \"11\",\n 0\n ]\n },\n \"class_type\": \"WanVideoTextEncode\",\n \"_meta\": {\n \"title\": \"WanVideo TextEncode\"\n }\n },\n \"28\": {\n \"inputs\": {\n \"enable_vae_tiling\": false,\n \"tile_x\": 272,\n \"tile_y\": 272,\n \"tile_stride_x\": 144,\n \"tile_stride_y\": 128,\n \"normalization\": \"default\",\n \"vae\": [\n \"38\",\n 0\n ],\n \"samples\": [\n \"90\",\n 0\n ]\n },\n \"class_type\": \"WanVideoDecode\",\n \"_meta\": {\n \"title\": \"WanVideo Decode\"\n }\n },\n \"38\": {\n \"inputs\": {\n \"model_name\": \"Wan2_1_VAE_bf16.safetensors\",\n \"precision\": \"bf16\"\n },\n \"class_type\": \"WanVideoVAELoader\",\n \"_meta\": {\n \"title\": \"WanVideo VAE Loader\"\n }\n },\n \"39\": {\n \"inputs\": {\n \"blocks_to_swap\": 20,\n \"offload_img_emb\": false,\n \"offload_txt_emb\": false,\n \"use_non_blocking\": false,\n \"vace_blocks_to_swap\": 1\n },\n \"class_type\": \"WanVideoBlockSwap\",\n \"_meta\": {\n \"title\": \"WanVideo Block Swap\"\n }\n },\n \"56\": {\n \"inputs\": {\n \"lora\": \"Wan21_I2V_14B_lightx2v_cfg_step_distill_lora_rank64.safetensors\",\n \"strength\": 3,\n \"low_mem_load\": true,\n \"merge_loras\": false\n },\n \"class_type\": \"WanVideoLoraSelect\",\n \"_meta\": {\n \"title\": \"WanVideo Lora Select\"\n }\n },\n \"89\": {\n \"inputs\": {\n \"width\": 832,\n \"height\": 480,\n \"num_frames\": 81,\n \"noise_aug_strength\": 0,\n \"start_latent_strength\": 1,\n \"end_latent_strength\": 1,\n \"force_offload\": true,\n \"fun_or_fl2v_model\": false,\n \"tiled_vae\": false,\n \"vae\": [\n \"38\",\n 0\n ]\n },\n \"class_type\": \"WanVideoImageToVideoEncode\",\n \"_meta\": {\n \"title\": \"WanVideo ImageToVideo Encode\"\n }\n },\n \"90\": {\n \"inputs\": {\n \"steps\": 8,\n \"cfg\": 1,\n \"shift\": 8,\n \"seed\": 652251640766870,\n \"force_offload\": true,\n \"scheduler\": \"unipc\",\n \"riflex_freq_index\": 0,\n \"denoise_strength\": 1,\n \"batched_cfg\": false,\n \"rope_function\": \"comfy\",\n \"start_step\": 4,\n \"end_step\": -1,\n \"image_embeds\": [\n \"89\",\n 0\n ],\n \"text_embeds\": [\n \"16\",\n 0\n ]\n },\n \"class_type\": \"WanVideoSampler\",\n \"_meta\": {\n \"title\": \"WanVideo Sampler\"\n }\n },\n \"150\": {\n \"inputs\": {\n \"lora\": [\n \"56\",\n 0\n ]\n },\n \"class_type\": \"WanVideoSetLoRAs\",\n \"_meta\": {\n \"title\": \"WanVideo Set LoRAs\"\n }\n }\n}"
|
||
},
|
||
{
|
||
"name": "qwen_image_edit",
|
||
"description": "qwen_image_edit是qwen_image文生图所延展的图片编辑功能的工作流，其功能类似于flux_kontext的能力,主要应用在对于图片的修改。当用户提及到需要对生成图进行二次编辑、修改图片内容、改变图片中的某些元素、根据图片图片中的某些特征进行二次延展时，优先推荐该类工作流。",
|
||
"content": "特别注意qwen_image_deit有特定的一套\"difussion model\"和\"clip\"、\"vae\"模型，分别是\"difussion model:qwen_image_edit.safetensor\"、\"clip:qwen_2.5vl_7b_fp8_scaled.safetensors\"和\"qwen_image type\",\"vae:qwen_image_vae\"。另外，对于qwen_image_edit的文本输入节点需要使用专属的\"textencoedqwenimageedit\"除此之外该类工作流不与画布上其他的model共用需单独添加上述专属节点和model。 {\n \"37\": {\n \"inputs\": {\n \"unet_name\": \"qwen_image_edit_fp8_e4m3fn.safetensors\",\n \"weight_dtype\": \"default\"\n },\n \"class_type\": \"UNETLoader\",\n \"_meta\": {\n \"title\": \"Load Diffusion Model\"\n }\n },\n \"38\": {\n \"inputs\": {\n \"clip_name\": \"qwen_2.5_vl_7b_fp8_scaled.safetensors\",\n \"type\": \"qwen_image\",\n \"device\": \"default\"\n },\n \"class_type\": \"CLIPLoader\",\n \"_meta\": {\n \"title\": \"Load CLIP\"\n }\n },\n \"39\": {\n \"inputs\": {\n \"vae_name\": \"qwen_image_vae.safetensors\"\n },\n \"class_type\": \"VAELoader\",\n \"_meta\": {\n \"title\": \"Load VAE\"\n }\n },\n \"66\": {\n \"inputs\": {\n \"shift\": 3,\n \"model\": [\n \"37\",\n 0\n ]\n },\n \"class_type\": \"ModelSamplingAuraFlow\",\n \"_meta\": {\n \"title\": \"ModelSamplingAuraFlow\"\n }\n },\n \"75\": {\n \"inputs\": {\n \"strength\": 1,\n \"model\": [\n \"66\",\n 0\n ]\n },\n \"class_type\": \"CFGNorm\",\n \"_meta\": {\n \"title\": \"CFGNorm\"\n }\n },\n \"76\": {\n \"inputs\": {\n \"prompt\": \"\",\n \"clip\": [\n \"38\",\n 0\n ],\n \"vae\": [\n \"39\",\n 0\n ],\n \"image\": [\n \"93\",\n 0\n ]\n },\n \"class_type\": \"TextEncodeQwenImageEdit\",\n \"_meta\": {\n \"title\": \"TextEncodeQwenImageEdit\"\n }\n },\n \"77\": {\n \"inputs\": {\n \"prompt\": \"\",\n \"clip\": [\n \"38\",\n 0\n ],\n \"vae\": [\n \"39\",\n 0\n ],\n \"image\": [\n \"93\",\n 0\n ]\n },\n \"class_type\": \"TextEncodeQwenImageEdit\",\n \"_meta\": {\n \"title\": \"TextEncodeQwenImageEdit\"\n }\n },\n \"88\": {\n \"inputs\": {\n \"pixels\": [\n \"93\",\n 0\n ],\n \"vae\": [\n \"39\",\n 0\n ]\n },\n \"class_type\": \"VAEEncode\",\n \"_meta\": {\n \"title\": \"VAE Encode\"\n }\n },\n \"93\": {\n \"inputs\": {\n \"upscale_method\": \"lanczos\",\n \"megapixels\": 1\n },\n \"class_type\": \"ImageScaleToTotalPixels\",\n \"_meta\": {\n \"title\": \"Scale Image to Total Pixels\"\n }\n }\n}"
|
||
}
|
||
] |