comfyui-workflow-templates 0.1.83__py3-none-any.whl → 0.1.85__py3-none-any.whl

comfyui_workflow_templates/templates/image_qwen_image_edit_2509.json

@@ -212,32 +212,6 @@
         "default"
       ]
     },
-    {
-      "id": 99,
-      "type": "MarkdownNote",
-      "pos": [
-        -840,
-        -140
-      ],
-      "size": [
-        540,
-        550
-      ],
-      "flags": {},
-      "order": 2,
-      "mode": 0,
-      "inputs": [],
-      "outputs": [],
-      "title": "Model links",
-      "properties": {
-        "widget_ue_connectable": {}
-      },
-      "widgets_values": [
-        "[Tutorial](https://docs.comfy.org/tutorials/image/qwen/qwen-image-edit) | [教程](https://docs.comfy.org/zh-CN/tutorials/image/qwen/qwen-image-edit)\n\n\n## Model links\n\nYou can find all the models on [Comfy-Org/Qwen-Image_ComfyUI](https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main) and  [Comfy-Org/Qwen-Image-Edit_ComfyUI](https://huggingface.co/Comfy-Org/Qwen-Image-Edit_ComfyUI) \n\n**Diffusion model**\n\n- [qwen_image_edit_2509_fp8_e4m3fn.safetensors](https://huggingface.co/Comfy-Org/Qwen-Image-Edit_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_edit_2509_fp8_e4m3fn.safetensors)\n\n**LoRA**\n\n- [Qwen-Image-Lightning-4steps-V1.0.safetensors](https://huggingface.co/lightx2v/Qwen-Image-Lightning/resolve/main/Qwen-Image-Lightning-4steps-V1.0.safetensors)\n\n**Text encoder**\n\n- [qwen_2.5_vl_7b_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors)\n\n**VAE**\n\n- [qwen_image_vae.safetensors](https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/vae/qwen_image_vae.safetensors)\n\nModel Storage Location\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│   ├── 📂 diffusion_models/\n│   │   └── qwen_image_edit_2509_fp8_e4m3fn.safetensors\n│   ├── 📂 loras/\n│   │   └── Qwen-Image-Lightning-4steps-V1.0.safetensors\n│   ├── 📂 vae/\n│   │   └── qwen_image_vae.safetensors\n│   └── 📂 text_encoders/\n│       └── qwen_2.5_vl_7b_fp8_scaled.safetensors\n```\n"
-      ],
-      "color": "#432",
-      "bgcolor": "#653"
-    },
     {
       "id": 66,
       "type": "ModelSamplingAuraFlow",
@@ -426,7 +400,7 @@
         90
       ],
       "flags": {},
-      "order": 3,
+      "order": 2,
       "mode": 0,
       "inputs": [],
       "outputs": [
@@ -464,30 +438,6 @@
         "default"
       ]
     },
-    {
-      "id": 97,
-      "type": "MarkdownNote",
-      "pos": [
-        740,
-        610
-      ],
-      "size": [
-        300,
-        160
-      ],
-      "flags": {},
-      "order": 4,
-      "mode": 0,
-      "inputs": [],
-      "outputs": [],
-      "title": "KSampler settings",
-      "properties": {},
-      "widgets_values": [
-        "You can test and find the best setting by yourself. The following table is for reference.\n\n| Model            | Steps | CFG |\n|---------------------|---------------|---------------|\n| Offical             | 50               | 4.0               \n| fp8_e4m3fn             | 20                | 2.5               |\n| fp8_e4m3fn + 4steps LoRA    | 4               | 1.0               |\n"
-      ],
-      "color": "#432",
-      "bgcolor": "#653"
-    },
     {
       "id": 60,
       "type": "SaveImage",
@@ -539,7 +489,7 @@
         314.0000305175781
       ],
       "flags": {},
-      "order": 5,
+      "order": 3,
       "mode": 4,
       "inputs": [],
       "outputs": [
@@ -592,7 +542,7 @@
         314.0000305175781
       ],
       "flags": {},
-      "order": 6,
+      "order": 4,
       "mode": 4,
       "inputs": [],
       "outputs": [
@@ -645,7 +595,7 @@
         106
       ],
       "flags": {},
-      "order": 7,
+      "order": 5,
       "mode": 0,
       "inputs": [],
       "outputs": [
@@ -860,7 +810,7 @@
         314.0000305175781
       ],
       "flags": {},
-      "order": 8,
+      "order": 6,
       "mode": 0,
       "inputs": [],
       "outputs": [
@@ -956,38 +906,89 @@
       ]
     },
     {
-      "id": 96,
+      "id": 113,
       "type": "MarkdownNote",
       "pos": [
-        -240,
+        730,
         1030
       ],
       "size": [
-        290,
-        140
+        330,
+        90
       ],
       "flags": {},
-      "order": 9,
+      "order": 7,
       "mode": 0,
       "inputs": [],
       "outputs": [],
+      "title": "Note: About image size",
       "properties": {},
       "widgets_values": [
-        "This node is to avoid bad output results caused by excessively large input image sizes. Because when we input one image, we use the size of that input image.\n\nThe **TextEncodeQwenImageEditPlus** will scale your input to 1024×104 pixels. We use the size of your first input image. This node is to avoid having an input image size that is too large (such as 3000×3000 pixels), which could bring bad results."
+        "You can use the latent from the **EmptySD3LatentImage** to replace **VAE Encode**, so you can customize the image size."
       ],
       "color": "#432",
       "bgcolor": "#653"
     },
     {
-      "id": 113,
+      "id": 97,
       "type": "MarkdownNote",
       "pos": [
-        730,
+        740,
+        610
+      ],
+      "size": [
+        300,
+        160
+      ],
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [],
+      "title": "Note: KSampler settings",
+      "properties": {},
+      "widgets_values": [
+        "You can test and find the best setting by yourself. The following table is for reference.\n\n| Model            | Steps | CFG |\n|---------------------|---------------|---------------|\n| Offical             | 50               | 4.0               \n| fp8_e4m3fn             | 20                | 2.5               |\n| fp8_e4m3fn + 4steps LoRA    | 4               | 1.0               |\n"
+      ],
+      "color": "#432",
+      "bgcolor": "#653"
+    },
+    {
+      "id": 99,
+      "type": "MarkdownNote",
+      "pos": [
+        -840,
+        -140
+      ],
+      "size": [
+        550,
+        550
+      ],
+      "flags": {},
+      "order": 9,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [],
+      "title": "Model links",
+      "properties": {
+        "widget_ue_connectable": {}
+      },
+      "widgets_values": [
+        "[Tutorial](https://docs.comfy.org/tutorials/image/qwen/qwen-image-edit) | [教程](https://docs.comfy.org/zh-CN/tutorials/image/qwen/qwen-image-edit)\n\n\n## Model links\n\nYou can find all the models on [Comfy-Org/Qwen-Image_ComfyUI](https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main) and  [Comfy-Org/Qwen-Image-Edit_ComfyUI](https://huggingface.co/Comfy-Org/Qwen-Image-Edit_ComfyUI) \n\n**Diffusion model**\n\n- [qwen_image_edit_2509_fp8_e4m3fn.safetensors](https://huggingface.co/Comfy-Org/Qwen-Image-Edit_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_edit_2509_fp8_e4m3fn.safetensors)\n\n**LoRA**\n\n- [Qwen-Image-Lightning-4steps-V1.0.safetensors](https://huggingface.co/lightx2v/Qwen-Image-Lightning/resolve/main/Qwen-Image-Lightning-4steps-V1.0.safetensors)\n\n**Text encoder**\n\n- [qwen_2.5_vl_7b_fp8_scaled.safetensors](https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors)\n\n**VAE**\n\n- [qwen_image_vae.safetensors](https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/vae/qwen_image_vae.safetensors)\n\nModel Storage Location\n\n```\n📂 ComfyUI/\n├── 📂 models/\n│   ├── 📂 diffusion_models/\n│   │   └── qwen_image_edit_2509_fp8_e4m3fn.safetensors\n│   ├── 📂 loras/\n│   │   └── Qwen-Image-Lightning-4steps-V1.0.safetensors\n│   ├── 📂 vae/\n│   │   └── qwen_image_vae.safetensors\n│   └── 📂 text_encoders/\n│       └── qwen_2.5_vl_7b_fp8_scaled.safetensors\n```\n"
+      ],
+      "color": "#432",
+      "bgcolor": "#653"
+    },
+    {
+      "id": 96,
+      "type": "MarkdownNote",
+      "pos": [
+        -240,
         1030
       ],
       "size": [
-        330,
-        90
+        290,
+        140
       ],
       "flags": {},
       "order": 10,
@@ -996,7 +997,7 @@
       "outputs": [],
       "properties": {},
       "widgets_values": [
-        "You can use the latent from the **EmptySD3LatentImage** to replace **VAE Encode**, so you can customize the image size."
+        "This node is to avoid bad output results caused by excessively large input image sizes. Because when we input one image, we use the size of that input image.\n\nThe **TextEncodeQwenImageEditPlus** will scale your input to 1024×104 pixels. We use the size of your first input image. This node is to avoid having an input image size that is too large (such as 3000×3000 pixels), which could bring bad results."
       ],
       "color": "#432",
       "bgcolor": "#653"
@@ -1245,10 +1246,10 @@
   "config": {},
   "extra": {
     "ds": {
-      "scale": 0.6413348663336487,
+      "scale": 0.5300288151517762,
       "offset": [
-        1036.839241485038,
-        412.30160240147245
+        1236.5826111125436,
+        518.8996996799999
       ]
     },
     "frontendVersion": "1.28.1",