666 version code

Updated README to highlight new Discord channel and features.

README.md

@@ -1,18 +1,38 @@
 <div align="center">
 
 # LanPaint: Universal Inpainting Sampler with "Think Mode"
-[![arXiv](https://img.shields.io/badge/Arxiv-2502.03491-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2502.03491)
+[![TMLR PDF](https://img.shields.io/badge/TMLR-PDF-8A2BE2?logo=openreview&logoColor=white)](https://openreview.net/pdf?id=JPC8JyOUSW)
 [![Python Benchmark](https://img.shields.io/badge/🐍-Python_Benchmark-3776AB?logo=python)](https://github.com/scraed/LanPaintBench)
 [![ComfyUI Extension](https://img.shields.io/badge/ComfyUI-Extension-7B5DFF)](https://github.com/comfyanonymous/ComfyUI)
 [![Hugging Face](https://img.shields.io/badge/Hugging%20Face-yellow?logo=huggingface&logoColor=white)](https://huggingface.co/charrywhite/LanPaint)
 [![Blog](https://img.shields.io/badge/📝-Blog-9cf)](https://scraed.github.io/scraedBlog/)
 [![GitHub stars](https://img.shields.io/github/stars/scraed/LanPaint)](https://github.com/scraed/LanPaint/stargazers)
+[![Discord](https://img.shields.io/badge/Discord-5865F2?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/aCGZutBV)
 </div>
 
 
 Universally applicable inpainting ability for every model. LanPaint sampler lets the model "think" through multiple iterations before denoising, enabling you to invest more computation time for superior inpainting quality.  
 
-This is the official implementation of ["Lanpaint: Training-Free Diffusion Inpainting with Exact and Fast Conditional Inference"](https://arxiv.org/abs/2502.03491), accepted by TMLR. The repository is for ComfyUI extension. Local Python benchmark code is published here: [LanPaintBench](https://github.com/scraed/LanPaintBench).
+This is the official implementation of ["LanPaint: Training-Free Diffusion Inpainting with Asymptotically Exact and Fast Conditional Sampling"](https://arxiv.org/abs/2502.03491), accepted by TMLR. The repository is for ComfyUI extension. Local Python benchmark code is published here: [LanPaintBench](https://github.com/scraed/LanPaintBench).
+
+## Citation
+
+```
+@article{
+zheng2025lanpaint,
+title={LanPaint: Training-Free Diffusion Inpainting with Asymptotically Exact and Fast Conditional Sampling},
+author={Candi Zheng and Yuan Lan and Yang Wang},
+journal={Transactions on Machine Learning Research},
+issn={2835-8856},
+year={2025},
+url={https://openreview.net/forum?id=JPC8JyOUSW},
+note={}
+}
+```
+**🎉 NEW 2026: Join our discord!**
+
+[Join our Discord](https://discord.gg/aCGZutBV) to share experiences, discuss features, and explore future development.
+
 **🎬 NEW: LanPaint now supports inpainting and outpainting based on Z-Image!**
 
 | Original | Masked | Inpainted |
@@ -46,11 +66,12 @@ Check our latest [Wan 2.2 Video Examples](#video-examples-beta), [Wan 2.2 Image
   - [Wan 2.2 Video Outpainting](#wan-22-video-outpainting)
   - [Resource Consumption](#resource-consumption)
 - [Image Examples](#image-examples)
+  - [Flux.2.Dev](#example-flux2dev-inpaintlanpaint-k-sampler-5-steps-of-thinking)
   - [Z-image](#example-z-image-inpaintlanpaint-k-sampler-5-steps-of-thinking)
   - [Hunyuan T2I](#example-hunyuan-t2i-inpaintlanpaint-k-sampler-5-steps-of-thinking)
   - [Wan 2.2 T2I](#example-wan22-inpaintlanpaint-k-sampler-5-steps-of-thinking)
   - [Wan 2.2 T2I with reference](#example-wan22-partial-inpaintlanpaint-k-sampler-5-steps-of-thinking)
-  - [Qwen Image Edit 2509](#example-qwen-edit-2509-inpaint)
+  - [Qwen Image Edit 2511 2509](#example-qwen-edit-2509-inpaint)
   - [Qwen Image Edit 2508](#example-qwen-edit-2508-inpaint)
   - [Qwen Image](#example-qwen-image-inpaintlanpaint-k-sampler-5-steps-of-thinking)
   - [HiDream](#example-hidream-inpaint-lanpaint-k-sampler-5-steps-of-thinking)
@@ -69,7 +90,7 @@ Check our latest [Wan 2.2 Video Examples](#video-examples-beta), [Wan 2.2 Image
 
 ## Features
 
-- **Universal Compatibility** – Works instantly with almost any model (**SD 1.5, XL, 3.5, Flux, HiDream, Qwen-Image, Wan2.2 or custom LoRAs**) and ControlNet.  
+- **Universal Compatibility** – Works instantly with almost any model (**Z-image, Hunyuan, Wan 2.2, Qwen Image/Edit, HiDream, SD 3.5, Flux-series, SDXL, SD 1.5 or custom LoRAs**) and ControlNet.  
 ![Inpainting Result 13](https://github.com/scraed/LanPaint/blob/master/examples/InpaintChara_13.jpg) 
 - **No Training Needed** – Works out of the box with your existing model.  
 - **Easy to Use** – Same workflow as standard ComfyUI KSampler.  
@@ -263,7 +284,7 @@ You need to follow the ComfyUI version of [Wan2.2 T2V workflow](https://docs.com
 
 
 ### Example Qwen Edit 2509: InPaint
-Check our latest updated [Mased Qwen Edit Workflow](https://github.com/scraed/LanPaint/tree/master/examples/Example_14) for Qwen Image Edit 2509. Download the model at [Qwen Image Edit 2509 Comfy](https://huggingface.co/Comfy-Org/Qwen-Image-Edit_ComfyUI/tree/main/split_files/diffusion_models).
+Check our latest updated [Mased Qwen Edit Workflow](https://github.com/scraed/LanPaint/tree/master/examples/Example_14) for Qwen Image Edit 2509. Download the model at [Qwen Image Edit 2509 Comfy](https://huggingface.co/Comfy-Org/Qwen-Image-Edit_ComfyUI/tree/main/split_files/diffusion_models). This workflow also supports Qwen Image Edit 2511.
 
 ![Qwen Result 3](https://github.com/scraed/LanPaint/blob/master/examples/LanPaintQwen_04.jpg) 
 
@@ -304,6 +325,23 @@ You need to follow the ComfyUI version of [HiDream workflow](https://docs.comfy.
 
 You need to follow the ComfyUI version of [SD 3.5 workflow](https://comfyui-wiki.com/en/tutorial/advanced/stable-diffusion-3-5-comfyui-workflow) to download and install the model.
 
+### Example Flux.2.Dev: InPaint(LanPaint K Sampler, 5 steps of thinking)
+
+<details open>
+<summary>View Original / Masked / Inpainted Comparison</summary>
+
+| Original | Masked | Inpainted |
+|:--------:|:------:|:---------:|
+| ![Original Flux.2.Dev](https://github.com/scraed/LanPaint/blob/master/examples/Example_23/Original_No_Mask.png) | ![Masked Flux.2.Dev](https://github.com/scraed/LanPaint/blob/master/examples/Example_23/Masked_Load_Me_in_Loader.png) | ![Inpainted Flux.2.Dev](https://github.com/scraed/LanPaint/blob/master/examples/Example_23/InPainted_Drag_Me_to_ComfyUI.png) |
+
+</details>
+
+[View Workflow & Masks](https://github.com/scraed/LanPaint/tree/master/examples/Example_23)
+
+[Model Used in This Example](https://huggingface.co/Comfy-Org/flux2-dev)
+
+(Note: Prompt First mode is disabled on Flux.2.Dev. As it does not use CFG guidance.)
+
 ### Example Flux: InPaint(LanPaint K Sampler, 5 steps of thinking)
 ![Inpainting Result 7](https://github.com/scraed/LanPaint/blob/master/examples/InpaintChara_10.jpg)  
 [View Workflow & Masks](https://github.com/scraed/LanPaint/tree/master/examples/Example_7)
@@ -451,17 +489,19 @@ Submit a PR to add your tutorial/video here, or open an [Issue](https://github.c
 - Try Implement Detailer
 - ~~Provide inference code on without GUI.~~ Check our local Python benchmark code [LanPaintBench](https://github.com/scraed/LanPaintBench).
 
+
 ## Citation
 
 ```
-@misc{zheng2025lanpainttrainingfreediffusioninpainting,
+@article{
-      title={Lanpaint: Training-Free Diffusion Inpainting with Exact and Fast Conditional Inference}, 
+zheng2025lanpaint,
-      author={Candi Zheng and Yuan Lan and Yang Wang},
+title={LanPaint: Training-Free Diffusion Inpainting with Asymptotically Exact and Fast Conditional Sampling},
-      year={2025},
+author={Candi Zheng and Yuan Lan and Yang Wang},
-      eprint={2502.03491},
+journal={Transactions on Machine Learning Research},
-      archivePrefix={arXiv},
+issn={2835-8856},
-      primaryClass={eess.IV},
+year={2025},
-      url={https://arxiv.org/abs/2502.03491}, 
+url={https://openreview.net/forum?id=JPC8JyOUSW},
+note={}
 }
 ```
 
@@ -469,4 +509,3 @@ Submit a PR to add your tutorial/video here, or open an [Issue](https://github.c
 
 
 
-

example_workflows/Z_image_Inpaint.json

@@ -2,7 +2,7 @@
   "id": "9ae6082b-c7f4-433c-9971-7a8f65a3ea65",
   "revision": 0,
   "last_node_id": 73,
-  "last_link_id": 93,
+  "last_link_id": 95,
   "nodes": [
     {
       "id": 39,
@@ -29,9 +29,9 @@
         }
       ],
       "properties": {
+        "Node name for S&R": "CLIPLoader",
         "cnr_id": "comfy-core",
         "ver": "0.3.73",
-        "Node name for S&R": "CLIPLoader",
         "models": [
           {
             "name": "qwen_3_4b.safetensors",
@@ -81,9 +81,9 @@
         }
       ],
       "properties": {
+        "Node name for S&R": "VAELoader",
         "cnr_id": "comfy-core",
         "ver": "0.3.73",
-        "Node name for S&R": "VAELoader",
         "models": [
           {
             "name": "ae.safetensors",
@@ -134,9 +134,9 @@
         }
       ],
       "properties": {
+        "Node name for S&R": "ConditioningZeroOut",
         "cnr_id": "comfy-core",
         "ver": "0.3.73",
-        "Node name for S&R": "ConditioningZeroOut",
         "enableTabs": false,
         "tabWidth": 65,
         "tabXOffset": 10,
@@ -147,54 +147,6 @@
       },
       "widgets_values": []
     },
-    {
-      "id": 46,
-      "type": "UNETLoader",
-      "pos": [
-        158.31605577680375,
-        332.3053621604172
-      ],
-      "size": [
-        323.734375,
-        145.390625
-      ],
-      "flags": {},
-      "order": 2,
-      "mode": 0,
-      "inputs": [],
-      "outputs": [
-        {
-          "name": "MODEL",
-          "type": "MODEL",
-          "links": [
-            54
-          ]
-        }
-      ],
-      "properties": {
-        "cnr_id": "comfy-core",
-        "ver": "0.3.73",
-        "Node name for S&R": "UNETLoader",
-        "models": [
-          {
-            "name": "z_image_turbo_bf16.safetensors",
-            "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/diffusion_models/z_image_turbo_bf16.safetensors",
-            "directory": "diffusion_models"
-          }
-        ],
-        "enableTabs": false,
-        "tabWidth": 65,
-        "tabXOffset": 10,
-        "hasSecondTab": false,
-        "secondTabText": "Send Back",
-        "secondTabOffset": 80,
-        "secondTabWidth": 65
-      },
-      "widgets_values": [
-        "z_image_turbo_bf16.safetensors",
-        "default"
-      ]
-    },
     {
       "id": 41,
       "type": "EmptySD3LatentImage",
@@ -207,7 +159,7 @@
         179.390625
       ],
       "flags": {},
-      "order": 3,
+      "order": 2,
       "mode": 0,
       "inputs": [],
       "outputs": [
@@ -219,9 +171,9 @@
         }
       ],
       "properties": {
+        "Node name for S&R": "EmptySD3LatentImage",
         "cnr_id": "comfy-core",
         "ver": "0.3.64",
-        "Node name for S&R": "EmptySD3LatentImage",
         "enableTabs": false,
         "tabWidth": 65,
         "tabXOffset": 10,
@@ -248,7 +200,7 @@
         111.390625
       ],
       "flags": {},
-      "order": 12,
+      "order": 13,
       "mode": 0,
       "inputs": [
         {
@@ -268,9 +220,9 @@
         }
       ],
       "properties": {
+        "Node name for S&R": "ModelSamplingAuraFlow",
         "cnr_id": "comfy-core",
         "ver": "0.3.64",
-        "Node name for S&R": "ModelSamplingAuraFlow",
         "enableTabs": false,
         "tabWidth": 65,
         "tabXOffset": 10,
@@ -321,9 +273,9 @@
         }
       ],
       "properties": {
+        "Node name for S&R": "VAEDecode",
         "cnr_id": "comfy-core",
         "ver": "0.3.64",
-        "Node name for S&R": "VAEDecode",
         "enableTabs": false,
         "tabWidth": 65,
         "tabXOffset": 10,
@@ -366,9 +318,9 @@
         }
       ],
       "properties": {
+        "Node name for S&R": "CLIPTextEncode",
         "cnr_id": "comfy-core",
         "ver": "0.3.73",
-        "Node name for S&R": "CLIPTextEncode",
         "enableTabs": false,
         "tabWidth": 65,
         "tabXOffset": 10,
@@ -395,7 +347,7 @@
         145.390625
       ],
       "flags": {},
-      "order": 8,
+      "order": 10,
       "mode": 4,
       "inputs": [
         {
@@ -414,9 +366,9 @@
         }
       ],
       "properties": {
+        "Node name for S&R": "LoraLoaderModelOnly",
         "cnr_id": "comfy-core",
         "ver": "0.3.75",
-        "Node name for S&R": "LoraLoaderModelOnly",
         "models": [
           {
             "name": "pixel_art_style_z_image_turbo.safetensors",
@@ -451,7 +403,7 @@
       "flags": {
         "collapsed": false
       },
-      "order": 4,
+      "order": 3,
       "mode": 0,
       "inputs": [],
       "outputs": [],
@@ -509,12 +461,12 @@
         }
       ],
       "properties": {
+        "Node name for S&R": "LanPaint_KSampler",
         "cnr_id": "LanPaint",
-        "ver": "6109df6591a4cf2bc9d3b113d03f7297fa9248e9",
+        "ver": "6109df6591a4cf2bc9d3b113d03f7297fa9248e9"
-        "Node name for S&R": "LanPaint_KSampler"
       },
       "widgets_values": [
-        454543748915702,
+        880311146947153,
         "randomize",
         9,
         1,
@@ -539,7 +491,7 @@
         686.171875
       ],
       "flags": {},
-      "order": 5,
+      "order": 4,
       "mode": 0,
       "inputs": [],
       "outputs": [
@@ -547,7 +499,6 @@
           "name": "IMAGE",
           "type": "IMAGE",
           "links": [
-            74,
             85,
             88
           ]
@@ -556,15 +507,14 @@
           "name": "MASK",
           "type": "MASK",
           "links": [
-            75,
             89
           ]
         }
       ],
       "properties": {
+        "Node name for S&R": "LoadImage",
         "cnr_id": "comfy-core",
         "ver": "0.3.59",
-        "Node name for S&R": "LoadImage",
         "ue_properties": {
           "widget_ue_connectable": {},
           "version": "7.1",
@@ -613,9 +563,9 @@
         }
       ],
       "properties": {
+        "Node name for S&R": "VAEEncode",
         "cnr_id": "comfy-core",
         "ver": "0.3.59",
-        "Node name for S&R": "VAEEncode",
         "ue_properties": {
           "widget_ue_connectable": {},
           "version": "7.1",
@@ -660,9 +610,9 @@
         }
       ],
       "properties": {
+        "Node name for S&R": "SetLatentNoiseMask",
         "cnr_id": "comfy-core",
         "ver": "0.3.59",
-        "Node name for S&R": "SetLatentNoiseMask",
         "ue_properties": {
           "widget_ue_connectable": {},
           "version": "7.1",
@@ -689,7 +639,7 @@
         {
           "name": "image1",
           "type": "IMAGE",
-          "link": 74
+          "link": 94
         },
         {
           "name": "image2",
@@ -699,7 +649,7 @@
         {
           "name": "mask",
           "type": "MASK",
-          "link": 75
+          "link": 95
         }
       ],
       "outputs": [
@@ -712,9 +662,9 @@
         }
       ],
       "properties": {
+        "Node name for S&R": "LanPaint_MaskBlend",
         "cnr_id": "LanPaint",
-        "ver": "4d3d5d17f0105b673df92da5b084cce567c9c712",
+        "ver": "4d3d5d17f0105b673df92da5b084cce567c9c712"
-        "Node name for S&R": "LanPaint_MaskBlend"
       },
       "widgets_values": [
         9
@@ -762,7 +712,7 @@
         101.421875
       ],
       "flags": {},
-      "order": 13,
+      "order": 12,
       "mode": 0,
       "inputs": [
         {
@@ -787,70 +737,12 @@
         }
       ],
       "properties": {
+        "Node name for S&R": "VAEDecode",
         "cnr_id": "comfy-core",
-        "ver": "0.3.23",
+        "ver": "0.3.23"
-        "Node name for S&R": "VAEDecode"
       },
       "widgets_values": []
     },
-    {
-      "id": 63,
-      "type": "ImageScale",
-      "pos": [
-        1283.837511214967,
-        1657.4367336671903
-      ],
-      "size": [
-        323.90625,
-        213.375
-      ],
-      "flags": {},
-      "order": 15,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "image",
-          "type": "IMAGE",
-          "link": 88
-        },
-        {
-          "name": "width",
-          "type": "INT",
-          "widget": {
-            "name": "width"
-          },
-          "link": 77
-        },
-        {
-          "name": "height",
-          "type": "INT",
-          "widget": {
-            "name": "height"
-          },
-          "link": 78
-        }
-      ],
-      "outputs": [
-        {
-          "name": "IMAGE",
-          "type": "IMAGE",
-          "links": [
-            90
-          ]
-        }
-      ],
-      "properties": {
-        "cnr_id": "comfy-core",
-        "ver": "0.3.52",
-        "Node name for S&R": "ImageScale"
-      },
-      "widgets_values": [
-        "area",
-        512,
-        512,
-        "center"
-      ]
-    },
     {
       "id": 64,
       "type": "MaskToImage",
@@ -863,7 +755,7 @@
         77.421875
       ],
       "flags": {},
-      "order": 10,
+      "order": 9,
       "mode": 0,
       "inputs": [
         {
@@ -882,51 +774,12 @@
         }
       ],
       "properties": {
+        "Node name for S&R": "MaskToImage",
         "cnr_id": "comfy-core",
-        "ver": "0.3.51",
+        "ver": "0.3.51"
-        "Node name for S&R": "MaskToImage"
       },
       "widgets_values": []
     },
-    {
-      "id": 65,
-      "type": "ImageToMask",
-      "pos": [
-        1274.556170930292,
-        2196.94755423526
-      ],
-      "size": [
-        323.90625,
-        111.390625
-      ],
-      "flags": {},
-      "order": 18,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "image",
-          "type": "IMAGE",
-          "link": 79
-        }
-      ],
-      "outputs": [
-        {
-          "name": "MASK",
-          "type": "MASK",
-          "links": [
-            91
-          ]
-        }
-      ],
-      "properties": {
-        "cnr_id": "comfy-core",
-        "ver": "0.3.51",
-        "Node name for S&R": "ImageToMask"
-      },
-      "widgets_values": [
-        "red"
-      ]
-    },
     {
       "id": 67,
       "type": "VAEEncode",
@@ -939,7 +792,7 @@
         101.421875
       ],
       "flags": {},
-      "order": 9,
+      "order": 8,
       "mode": 0,
       "inputs": [
         {
@@ -963,9 +816,9 @@
         }
       ],
       "properties": {
+        "Node name for S&R": "VAEEncode",
         "cnr_id": "comfy-core",
         "ver": "0.3.50",
-        "Node name for S&R": "VAEEncode",
         "enableTabs": false,
         "tabWidth": 65,
         "tabXOffset": 10,
@@ -1026,9 +879,9 @@
         }
       ],
       "properties": {
+        "Node name for S&R": "ImageScale",
         "cnr_id": "comfy-core",
-        "ver": "0.3.52",
+        "ver": "0.3.52"
-        "Node name for S&R": "ImageScale"
       },
       "widgets_values": [
         "nearest-exact",
@@ -1082,18 +935,196 @@
         }
       ],
       "properties": {
+        "Node name for S&R": "GetImageSize",
         "cnr_id": "comfy-core",
-        "ver": "0.3.52",
+        "ver": "0.3.52"
-        "Node name for S&R": "GetImageSize"
+      },
+      "widgets_values": [
+        "width: 1024, height: 1024\n batch size: 1"
+      ]
+    },
+    {
+      "id": 73,
+      "type": "PreviewImage",
+      "pos": [
+        2226.506787053337,
+        107.57278250350078
+      ],
+      "size": [
+        225,
+        246
+      ],
+      "flags": {},
+      "order": 23,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 93
+        }
+      ],
+      "outputs": [],
+      "properties": {
+        "Node name for S&R": "PreviewImage",
+        "cnr_id": "comfy-core",
+        "ver": "0.3.76"
       },
       "widgets_values": []
     },
+    {
+      "id": 63,
+      "type": "ImageScale",
+      "pos": [
+        1283.837511214967,
+        1657.4367336671903
+      ],
+      "size": [
+        323.90625,
+        213.375
+      ],
+      "flags": {},
+      "order": 15,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 88
+        },
+        {
+          "name": "width",
+          "type": "INT",
+          "widget": {
+            "name": "width"
+          },
+          "link": 77
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "widget": {
+            "name": "height"
+          },
+          "link": 78
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            90,
+            94
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ImageScale",
+        "cnr_id": "comfy-core",
+        "ver": "0.3.52"
+      },
+      "widgets_values": [
+        "area",
+        512,
+        512,
+        "center"
+      ]
+    },
+    {
+      "id": 65,
+      "type": "ImageToMask",
+      "pos": [
+        1274.556170930292,
+        2196.94755423526
+      ],
+      "size": [
+        323.90625,
+        111.390625
+      ],
+      "flags": {},
+      "order": 18,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 79
+        }
+      ],
+      "outputs": [
+        {
+          "name": "MASK",
+          "type": "MASK",
+          "links": [
+            91,
+            95
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ImageToMask",
+        "cnr_id": "comfy-core",
+        "ver": "0.3.51"
+      },
+      "widgets_values": [
+        "red"
+      ]
+    },
+    {
+      "id": 46,
+      "type": "UNETLoader",
+      "pos": [
+        159.05646022112083,
+        288.62105108441466
+      ],
+      "size": [
+        323.734375,
+        145.390625
+      ],
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            54
+          ]
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "UNETLoader",
+        "cnr_id": "comfy-core",
+        "ver": "0.3.73",
+        "models": [
+          {
+            "name": "z_image_turbo_bf16.safetensors",
+            "url": "https://huggingface.co/Comfy-Org/z_image_turbo/resolve/main/split_files/diffusion_models/z_image_turbo_bf16.safetensors",
+            "directory": "diffusion_models"
+          }
+        ],
+        "enableTabs": false,
+        "tabWidth": 65,
+        "tabXOffset": 10,
+        "hasSecondTab": false,
+        "secondTabText": "Send Back",
+        "secondTabOffset": 80,
+        "secondTabWidth": 65
+      },
+      "widgets_values": [
+        "z_image_turbo_bf16.safetensors",
+        "default"
+      ]
+    },
     {
       "id": 72,
       "type": "Note",
       "pos": [
-        1266.1247223180148,
+        1288.7909707861209,
-        1534.1298096819087
+        1503.5796522859714
       ],
       "size": [
         225,
@@ -1110,35 +1141,6 @@
       ],
       "color": "#432",
       "bgcolor": "#653"
-    },
-    {
-      "id": 73,
-      "type": "PreviewImage",
-      "pos": [
-        2226.506787053337,
-        107.57278250350078
-      ],
-      "size": [
-        225,
-        77.421875
-      ],
-      "flags": {},
-      "order": 23,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "images",
-          "type": "IMAGE",
-          "link": 93
-        }
-      ],
-      "outputs": [],
-      "properties": {
-        "cnr_id": "comfy-core",
-        "ver": "0.3.76",
-        "Node name for S&R": "PreviewImage"
-      },
-      "widgets_values": []
     }
   ],
   "links": [
@@ -1254,22 +1256,6 @@
       1,
       "IMAGE"
     ],
-    [
-      74,
-      57,
-      0,
-      60,
-      0,
-      "IMAGE"
-    ],
-    [
-      75,
-      57,
-      1,
-      60,
-      2,
-      "MASK"
-    ],
     [
       76,
       67,
@@ -1397,6 +1383,22 @@
       73,
       0,
       "IMAGE"
+    ],
+    [
+      94,
+      63,
+      0,
+      60,
+      0,
+      "IMAGE"
+    ],
+    [
+      95,
+      65,
+      0,
+      60,
+      2,
+      "MASK"
     ]
   ],
   "groups": [
@@ -1456,13 +1458,13 @@
   "config": {},
   "extra": {
     "ds": {
-      "scale": 0.17731177475370102,
+      "scale": 0.3800835362432756,
       "offset": [
-        2305.975484371013,
+        -902.897494105397,
-        1284.903135448736
+        -396.4805064253962
       ]
     },
-    "frontendVersion": "1.32.10",
+    "frontendVersion": "1.33.14",
     "VHS_latentpreview": false,
     "VHS_latentpreviewrate": 0,
     "VHS_MetadataImage": true,

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "LanPaint"
-version = "1.4.6"
+version = "1.4.9"
 description = "Achieve seamless inpainting results without needing a specialized inpainting model."
 authors = [
   {name = "LanPaint", email = "czhengac@connect.ust.hk"}

src/LanPaint/nodes.py

@@ -12,8 +12,28 @@ from comfy.model_base import ModelType
 from .utils import *
 from .lanpaint import LanPaint
 from comfy.model_base import WAN22
+import comfyui_version 
+import comfy.nested_tensor 
 
 def reshape_mask(input_mask, output_shape,video_inpainting=False):
+
+    import comfy.nested_tensor
+    
+    # 修改这里的判断条件，不能只用 hasattr("unbind")
+    if isinstance(input_mask, comfy.nested_tensor.NestedTensor):
+        masks = input_mask.unbind()
+        
+        # 如果 output_shape 也是嵌套的（通常 noise.shape 在 NestedTensor 下返回 tuple of shapes）
+        if isinstance(output_shape, (list, tuple)) and len(output_shape) > 0 and not isinstance(output_shape[0], int):
+            reshaped_parts = []
+            for i in range(len(masks)):
+                # 递归处理每一个子部分，并传入对应的子 shape
+                reshaped_parts.append(reshape_mask(masks[i], output_shape[i], video_inpainting))
+            return comfy.nested_tensor.NestedTensor(tuple(reshaped_parts))
+        else:
+            # 如果 output_shape 是单一形状（降级处理）
+            return comfy.nested_tensor.NestedTensor(tuple(reshape_mask(m, output_shape, video_inpainting) for m in masks))
+        
     dims = len(output_shape) - 2
     print('output shape',output_shape)
     scale_mode = "nearest-exact"
@@ -22,43 +42,81 @@ def reshape_mask(input_mask, output_shape,video_inpainting=False):
     print('input_mask.ndim:', input_mask.ndim, 'output_shape len:', len(output_shape))
     
     # Handle video case with temporal dimension
-    if video_inpainting:  # Video case: (batch, channels, frames, height, width)
+    # if video_inpainting:  # Video case: (batch, channels, frames, height, width)
-        target_frames = output_shape[2]
+    #     target_frames = output_shape[2]
-        target_height, target_width = output_shape[-2:]
+    #     target_height, target_width = output_shape[-2:]
         
-        print('Video case - input_mask initial shape:', input_mask.shape)
+    #     print('Video case - input_mask initial shape:', input_mask.shape)
         
-        # First reshape input_mask to have proper dimensions for video processing
+    #     # First reshape input_mask to have proper dimensions for video processing
-        # Assume input is (frames, channels, height, width) -> (1, channels, frames, height, width)
+    #     # Assume input is (frames, channels, height, width) -> (1, channels, frames, height, width)
-        input_mask = input_mask.permute(1, 0, 2, 3).unsqueeze(0)
+    #     ## if comfy version < 0.6.0
-        print('Video case - input_mask after reshaping:', input_mask.shape)
+    #     if comfyui_version.__version__ < "0.6.0":
-        # Ensure we have the correct 5D shape: (batch, channels, frames, height, width)
+    #         input_mask = input_mask.permute(1, 0, 2, 3).unsqueeze(0)
-        batch_size, channels, frames, height, width = input_mask.shape
+    #     print('Video case - input_mask after reshaping:', input_mask.shape)
-        print('Video case - dimensions: batch_size={}, channels={}, frames={}, height={}, width={}'.format(batch_size, channels, frames, height, width))
+    #     # Ensure we have the correct 5D shape: (batch, channels, frames, height, width)
-        print('Video case - target size:', (target_frames, target_height, target_width))
+    #     batch_size, channels, frames, height, width = input_mask.shape
+    #     print('Video case - dimensions: batch_size={}, channels={}, frames={}, height={}, width={}'.format(batch_size, channels, frames, height, width))
+    #     print('Video case - target size:', (target_frames, target_height, target_width))
         
-        # 3D nearest-exact interpolation: (batch, channels, frames, height, width) -> (batch, channels, target_frames, target_height, target_width)
+    #     # 3D nearest-exact interpolation: (batch, channels, frames, height, width) -> (batch, channels, target_frames, target_height, target_width)
-        temp_mask = torch.nn.functional.interpolate(
+    #     temp_mask = torch.nn.functional.interpolate(
-            input_mask, 
+    #         input_mask, 
-            size=(target_frames, target_height, target_width), 
+    #         size=(target_frames, target_height, target_width), 
-            mode=scale_mode, 
+    #         mode=scale_mode, 
-        )
+    #     )
         
-        # temp_mask is already 5D: (batch, channels, target_frames, target_height, target_width)
+    #     # temp_mask is already 5D: (batch, channels, target_frames, target_height, target_width)
-        mask = temp_mask
+    #     mask = temp_mask
-        print('after mask',mask.shape)
+    #     print('after mask',mask.shape)
-        # Handle channel dimension expansion if needed
+    #     # Handle channel dimension expansion if needed
-        if mask.shape[1] < output_shape[1]:
+    #     if mask.shape[1] < output_shape[1]:
-            mask = mask.repeat(1, output_shape[1], 1, 1, 1)[:, :output_shape[1]]
+    #         mask = mask.repeat(1, output_shape[1], 1, 1, 1)[:, :output_shape[1]]
-        # Handle batch dimension
+    #     # Handle batch dimension
-        mask = repeat_to_batch_size(mask, output_shape[0])
+    #     mask = repeat_to_batch_size(mask, output_shape[0])
+    if video_inpainting:
+        # 如果是 3D Token 序列 (LTXV 压平后的情况)
+        if input_mask.ndim == 3 and len(output_shape) == 3:
+            mask = torch.nn.functional.interpolate(
+                input_mask, 
+                size=output_shape[2], 
+                mode=scale_mode
+            )
+            return mask
+            
+        # 只有在确认为 5D 视频张量时才执行原有逻辑
+        if input_mask.ndim == 5:
+            target_frames = output_shape[2]
+            target_height, target_width = output_shape[-2:]
+            
+            # (这里保留你原有的 permute 和 unsqueeze 逻辑，但要确保它是针对非 5D 输入的补救)
+            if input_mask.ndim < 5:
+                # 假设输入是 (F, C, H, W) -> (1, C, F, H, W)
+                if hasattr(comfyui_version, "__version__") and comfyui_version.__version__ < "0.6.0":
+                    input_mask = input_mask.permute(1, 0, 2, 3).unsqueeze(0)
+            
+            # 现在可以安全地解包 5D 形状了
+            batch_size, channels, frames, height, width = input_mask.shape
+            mask = torch.nn.functional.interpolate(
+                input_mask, 
+                size=(target_frames, target_height, target_width), 
+                mode=scale_mode, 
+            )
+            
+            if mask.shape[1] < output_shape[1]:
+                mask = mask.repeat(1, output_shape[1], 1, 1, 1)[:, :output_shape[1]]
+            mask = repeat_to_batch_size(mask, output_shape[0])
+            return mask
     else:  # Original 2D image case
-        mask = torch.nn.functional.interpolate(input_mask, size=output_shape[-2:], mode=scale_mode)
+        if comfyui_version.__version__ < "0.6.0":
+            mask = torch.nn.functional.interpolate(input_mask, size=output_shape[-2:], mode=scale_mode)
+        else:
+            mask = torch.nn.functional.interpolate(input_mask, size=output_shape[2:], mode=scale_mode)
         if mask.shape[1] < output_shape[1]:
             mask = mask.repeat((1, output_shape[1]) + (1,) * dims)[:,:output_shape[1]]
         mask = repeat_to_batch_size(mask, output_shape[0])
     
-    print('resize mask',mask.shape,type(mask),torch.max(mask),torch.min(mask))
+
     return mask
 def prepare_mask(noise_mask, shape, device,video_inpainting=False):
     return reshape_mask(noise_mask, shape,video_inpainting).to(device)
@@ -88,9 +146,9 @@ class CFGGuider_LanPaint:
         if isinstance(self.inner_model, WAN22):
             print("WAN22 detected")
             self.inner_model.extra_conds = super(WAN22, self.inner_model).extra_conds
-
         if denoise_mask is not None:
             video_inpainting = self.model_options.get("video_inpainting", False)
+            print('denoise_mask',denoise_mask.shape,type(denoise_mask))
             denoise_mask = prepare_mask(denoise_mask, noise.shape, device, video_inpainting)
 
         noise = noise.to(device)
@@ -138,8 +196,6 @@ class KSamplerX0Inpaint:
             abt = (1 - Flow_t)**2 / ((1 - Flow_t)**2 + Flow_t**2 )
             VE_Sigma = Flow_t / (1 - Flow_t)
             #print("t", torch.mean( sigma ).item(), "VE_Sigma", torch.mean( VE_Sigma ).item())
-            
-
         else:
             VE_Sigma = sigma 
             abt = 1/( 1+VE_Sigma**2 )
@@ -149,6 +205,31 @@ class KSamplerX0Inpaint:
             if "denoise_mask_function" in model_options:
                 denoise_mask = model_options["denoise_mask_function"](sigma, denoise_mask, extra_options={"model": self.inner_model, "sigmas": self.sigmas})
 
+            if isinstance(denoise_mask, comfy.nested_tensor.NestedTensor):
+                masks = denoise_mask.unbind()
+                xs = x.unbind()
+                latent_imgs = self.latent_image.unbind()
+                noises = self.noise.unbind()
+                
+                outs = []
+                # 针对 LTXV，通常 i=0 是视频，i=1 是音频
+                for i in range(len(xs)):
+                    m = (masks[i] > 0.5).float()
+                    lm = 1 - m
+                    # 这里的 PaintMethod 通常只支持普通 Tensor，所以我们分块处理
+                    # 注意：如果音频部分不需要 Inpaint，可以增加判断
+                    current_times = (VE_Sigma, abt, Flow_t)
+                    
+                    # 只有视频部分 (i=0) 应用 LanPaint 逻辑，音频部分通常直接 pass 或原样返回
+                    if i == 0:
+                        out_part = self.PaintMethod(xs[i], latent_imgs[i], noises[i], sigma, lm, current_times, model_options, seed)
+                    else:
+                        # 音频部分如果没有对应的 Inpaint 逻辑，通常直接调用 inner_model
+                        out_part, _ = self.inner_model(xs[i], sigma, model_options=model_options, seed=seed)
+                    outs.append(out_part)
+                    
+                return comfy.nested_tensor.NestedTensor(tuple(outs))
+            
             denoise_mask = (denoise_mask > 0.5).float()
 
             latent_mask = 1 - denoise_mask
@@ -183,6 +264,7 @@ class KSAMPLER(comfy.samplers.KSAMPLER):
         #noise here is a randn noise from comfy.sample.prepare_noise
         #latent_image is the latent image as input of the KSampler node. For inpainting, it is the masked latent image. Otherwise it is zero tensor.
         extra_args["denoise_mask"] = denoise_mask
+        print("LanPaint KSampler start sampler_function",denoise_mask.shape if denoise_mask is not None else None)
         model_k = KSamplerX0Inpaint(model_wrap, sigmas)
         model_k.latent_image = latent_image
         if self.inpaint_options.get("random", False): #TODO: Should this be the default?
@@ -447,6 +529,77 @@ class MaskBlend:
 
         return kernel
 
+class MaskBlendAlpha:
+    """
+    Create an RGBA image by writing the mask into the PNG alpha channel.
+
+    Requirement:
+    - inpaint region: alpha = 0 (transparent)
+    - other region:   alpha = 1 (opaque)
+
+    This node writes the mask into the PNG alpha channel.
+    Current default behavior matches the previous `invert_mask=True` behavior:
+    alpha = mask.
+    """
+    def __init__(self):
+        pass
+
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {
+                "image": ("IMAGE", {"tooltip": "VAE-decoded image (RGB)."}),
+                "mask": ("MASK", {"tooltip": "Mask used as alpha channel (alpha = mask)."}),
+            },
+        }
+
+    RETURN_TYPES = ("IMAGE",)
+    FUNCTION = "to_rgba"
+    CATEGORY = "image/postprocessing"
+
+    def to_rgba(self, image: torch.Tensor, mask: torch.Tensor):
+        """
+        image: [B,H,W,3] float in [0,1]
+        mask:  [B,H,W] (or [H,W]) float in [0,1] used as alpha
+        returns RGBA image: [B,H,W,4] float in [0,1]
+        """
+        if image.ndim != 4 or image.shape[-1] != 3:
+            raise ValueError(f"Expected IMAGE tensor [B,H,W,3], got {tuple(image.shape)}")
+
+        # Normalize mask shape to [B,H,W]
+        if mask.ndim == 2:
+            mask = mask.unsqueeze(0)
+        elif mask.ndim == 3:
+            pass
+        else:
+            # Some pipelines may carry mask as [B,1,H,W]
+            if mask.ndim == 4 and mask.shape[1] == 1:
+                mask = mask[:, 0, :, :]
+            else:
+                raise ValueError(f"Expected MASK tensor [B,H,W] or [H,W], got {tuple(mask.shape)}")
+
+        b, h, w, _ = image.shape
+
+        # Batch align
+        if mask.shape[0] != b:
+            if mask.shape[0] == 1:
+                mask = mask.repeat(b, 1, 1)
+            else:
+                raise ValueError(f"Batch mismatch: image batch={b}, mask batch={mask.shape[0]}")
+
+        # Spatial align (resize mask to image resolution if needed)
+        if mask.shape[1] != h or mask.shape[2] != w:
+            mask_4d = mask.unsqueeze(1)  # [B,1,H,W]
+            mask_4d = torch.nn.functional.interpolate(mask_4d, size=(h, w), mode="nearest")
+            mask = mask_4d[:, 0, :, :]
+
+        mask = mask.float().clamp(0.0, 1.0)
+
+        # Default behavior (matches previous invert_mask=True path):
+        # alpha = mask
+        rgba = torch.cat([image, mask.unsqueeze(-1)], dim=-1)
+        return (rgba,)
+
 class Noise_EmptyNoise:
     def generate_noise(self, latent):
         return torch.zeros_like(latent["samples"])
@@ -475,6 +628,7 @@ class LanPaint_SamplerCustom:
                      "LanPaint_NumSteps": ("INT", {"default": 5, "min": 0, "max": 100, "tooltip": "Number of steps for Langevin dynamics, representing turns of thinking per step."}),
                      "LanPaint_PromptMode": (["Image First", "Prompt First"], {"tooltip": "Image First: prioritizes image quality; Prompt First: prioritizes prompt adherence."}),
                      "LanPaint_Info": ("STRING", {"default": "LanPaint Custom Sampler. For more info, visit https://github.com/scraed/LanPaint. If you find it useful, please give a star ⭐️!", "multiline": True}),
+                     "Inpainting_mode": (["🖼️ Image Inpainting", "🎬 Video Inpainting"], {"default": "🖼️ Image Inpainting", "tooltip": "Choose Image mode for photos or Video mode for video frames with temporal consistency"}),
                       }
                }
 
@@ -483,7 +637,7 @@ class LanPaint_SamplerCustom:
     FUNCTION = "sample"
     CATEGORY = "sampling/custom_sampling"
 
-    def sample(self, model, sampler, sigmas, add_noise, noise_seed, cfg, positive, negative, latent_image, LanPaint_NumSteps, LanPaint_PromptMode, LanPaint_Info=""):
+    def sample(self, model, sampler, sigmas, add_noise, noise_seed, cfg, positive, negative, latent_image, LanPaint_NumSteps, LanPaint_PromptMode, LanPaint_Info="",Inpainting_mode="🖼️ Image Inpainting"):
         model.LanPaint_StepSize = 0.2
         model.LanPaint_Lambda = 16.0
         model.LanPaint_Beta = 1.
@@ -494,6 +648,10 @@ class LanPaint_SamplerCustom:
             model.LanPaint_cfg_BIG = cfg
         else:
             model.LanPaint_cfg_BIG = 0 * cfg - 0.5
+        video_inpainting = (Inpainting_mode == "🎬 Video Inpainting")
+        if not hasattr(model, 'model_options') or model.model_options is None:
+            model.model_options = {}
+        model.model_options["video_inpainting"] = video_inpainting
         with override_sample_function():
             latent = latent_image.copy()
             latent_image = latent["samples"]
@@ -541,6 +699,7 @@ class LanPaint_SamplerCustomAdvanced:
                      "LanPaint_PromptMode": (["Image First", "Prompt First"], {"tooltip": "Image First: prioritizes image quality; Prompt First: prioritizes prompt adherence."}),
                      "LanPaint_EarlyStop": ("INT", {"default": 1, "min": 0, "max": 10000, "tooltip": "Steps to stop LanPaint early, preventing irregular patterns."}),
                      "LanPaint_Info": ("STRING", {"default": "LanPaint Custom Sampler Adv. For more info, visit https://github.com/scraed/LanPaint. If you find it useful, please give a star ⭐️!", "multiline": True}),
+                     "Inpainting_mode": (["🖼️ Image Inpainting", "🎬 Video Inpainting"], {"default": "🖼️ Image Inpainting", "tooltip": "Choose Image mode for photos or Video mode for video frames with temporal consistency"}),
                     }
                }
 
@@ -551,7 +710,7 @@ class LanPaint_SamplerCustomAdvanced:
 
     CATEGORY = "sampling/custom_sampling"
 
-    def sample(self, noise, guider, sampler, sigmas, latent_image, LanPaint_NumSteps, LanPaint_Lambda, LanPaint_StepSize, LanPaint_Beta, LanPaint_Friction, LanPaint_PromptMode, LanPaint_EarlyStop, LanPaint_Info=""):
+    def sample(self, noise, guider, sampler, sigmas, latent_image, LanPaint_NumSteps, LanPaint_Lambda, LanPaint_StepSize, LanPaint_Beta, LanPaint_Friction, LanPaint_PromptMode, LanPaint_EarlyStop, LanPaint_Info="",Inpainting_mode="🖼️ Image Inpainting"):
         model = guider.model_patcher
         model.LanPaint_StepSize = LanPaint_StepSize
         model.LanPaint_Lambda = LanPaint_Lambda
@@ -563,16 +722,25 @@ class LanPaint_SamplerCustomAdvanced:
             model.LanPaint_cfg_BIG = guider.cfg
         else:
             model.LanPaint_cfg_BIG = 0 * guider.cfg - 0.5
+        
+        video_inpainting = (Inpainting_mode == "🎬 Video Inpainting")
+        if not hasattr(model, 'model_options') or model.model_options is None:
+            model.model_options = {}
+        model.model_options["video_inpainting"] = video_inpainting
         with override_sample_function():
             latent = latent_image
             latent_image = latent["samples"]
+            print('before fix_empty_latent_channels latent_image shape',latent_image.shape)
             latent = latent.copy()
             latent_image = comfy.sample.fix_empty_latent_channels(guider.model_patcher, latent_image)
             latent["samples"] = latent_image
-
+            print('latent_image shape',latent_image.shape)
+            print('outside noise_mask',latent["noise_mask"].shape if "noise_mask" in latent else 'no noise_mask')
+            print('latent keys',latent.keys())
             noise_mask = None
             if "noise_mask" in latent:
                 noise_mask = latent["noise_mask"]
+                print('inside noise_mask shape',noise_mask.shape)
 
             x0_output = {}
             callback = latent_preview.prepare_callback(guider.model_patcher, sigmas.shape[-1] - 1, x0_output)
@@ -588,6 +756,7 @@ class LanPaint_SamplerCustomAdvanced:
                 out_denoised["samples"] = guider.model_patcher.model.process_latent_out(x0_output["x0"].cpu())
             else:
                 out_denoised = out
+            # print('output',out.keys(),out["samples"].shape,out['noise_mask'].shape)
             return (out, out_denoised)
 
 
@@ -599,6 +768,7 @@ NODE_CLASS_MAPPINGS = {
     "LanPaint_SamplerCustom" : LanPaint_SamplerCustom,
     "LanPaint_SamplerCustomAdvanced" : LanPaint_SamplerCustomAdvanced,
     "LanPaint_MaskBlend": MaskBlend,
+    "LanPaint_MaskBlendAlpha": MaskBlendAlpha,
 #    "LanPaint_UpSale_LatentNoiseMask": LanPaint_UpSale_LatentNoiseMask,
 }
 
@@ -609,5 +779,6 @@ NODE_DISPLAY_NAME_MAPPINGS = {
     "LanPaint_SamplerCustom" : "LanPaint Sampler Custom",
     "LanPaint_SamplerCustomAdvanced" : "LanPaint Sampler Custom (Advanced)",
     "LanPaint_MaskBlend": "LanPaint Mask Blend",
+    "LanPaint_MaskBlendAlpha": "MaskBlend (alpha)",
 #    "LanPaint_UpSale_LatentNoiseMask": "LanPaint UpSale Latent Noise Mask"
 }