Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+preview/banner.png filter=lfs diff=lfs merge=lfs -text
+preview/input.png filter=lfs diff=lfs merge=lfs -text
+preview/result1.png filter=lfs diff=lfs merge=lfs -text
+preview/result2.png filter=lfs diff=lfs merge=lfs -text
+preview/result3.png filter=lfs diff=lfs merge=lfs -text
+preview/result4.png filter=lfs diff=lfs merge=lfs -text
+preview/result5.png filter=lfs diff=lfs merge=lfs -text

Qwen-Edit-MeiTu.json

@@ -0,0 +1,928 @@
+{
+  "id": "91f6bbe2-ed41-4fd6-bac7-71d5b5864ecb",
+  "revision": 0,
+  "last_node_id": 100,
+  "last_link_id": 166,
+  "nodes": [
+    {
+      "id": 38,
+      "type": "CLIPLoader",
+      "pos": [
+        -34.261653900146484,
+        198.56765747070312
+      ],
+      "size": [
+        330,
+        110
+      ],
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "slot_index": 0,
+          "links": [
+            75,
+            140
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.48",
+        "Node name for S&R": "CLIPLoader",
+        "models": [
+          {
+            "name": "qwen_2.5_vl_7b_fp8_scaled.safetensors",
+            "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors",
+            "directory": "text_encoders"
+          }
+        ],
+        "enableTabs": false,
+        "tabWidth": 65,
+        "tabXOffset": 10,
+        "hasSecondTab": false,
+        "secondTabText": "Send Back",
+        "secondTabOffset": 80,
+        "secondTabWidth": 65,
+        "widget_ue_connectable": {}
+      },
+      "widgets_values": [
+        "qwen_2.5_vl_7b_fp8_scaled.safetensors",
+        "qwen_image",
+        "default"
+      ]
+    },
+    {
+      "id": 39,
+      "type": "VAELoader",
+      "pos": [
+        -35.67443084716797,
+        346.28021240234375
+      ],
+      "size": [
+        330,
+        60
+      ],
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "VAE",
+          "type": "VAE",
+          "slot_index": 0,
+          "links": [
+            76,
+            139
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.48",
+        "Node name for S&R": "VAELoader",
+        "models": [
+          {
+            "name": "qwen_image_vae.safetensors",
+            "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/vae/qwen_image_vae.safetensors",
+            "directory": "vae"
+          }
+        ],
+        "enableTabs": false,
+        "tabWidth": 65,
+        "tabXOffset": 10,
+        "hasSecondTab": false,
+        "secondTabText": "Send Back",
+        "secondTabOffset": 80,
+        "secondTabWidth": 65,
+        "widget_ue_connectable": {}
+      },
+      "widgets_values": [
+        "qwen_image_vae.safetensors"
+      ]
+    },
+    {
+      "id": 7,
+      "type": "CLIPTextEncode",
+      "pos": [
+        334.2939758300781,
+        246.5434112548828
+      ],
+      "size": [
+        357.21307373046875,
+        172.22882080078125
+      ],
+      "flags": {
+        "collapsed": false
+      },
+      "order": 5,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 75
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "slot_index": 0,
+          "links": [
+            142
+          ]
+        }
+      ],
+      "title": "CLIP Text Encode (Negative Prompt)",
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.48",
+        "Node name for S&R": "CLIPTextEncode",
+        "enableTabs": false,
+        "tabWidth": 65,
+        "tabXOffset": 10,
+        "hasSecondTab": false,
+        "secondTabText": "Send Back",
+        "secondTabOffset": 80,
+        "secondTabWidth": 65,
+        "widget_ue_connectable": {}
+      },
+      "widgets_values": [
+        "",
+        [
+          false,
+          true
+        ]
+      ]
+    },
+    {
+      "id": 66,
+      "type": "ModelSamplingAuraFlow",
+      "pos": [
+        373.009765625,
+        -65.01009368896484
+      ],
+      "size": [
+        300,
+        58
+      ],
+      "flags": {},
+      "order": 10,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 130
+        }
+      ],
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            125
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.48",
+        "Node name for S&R": "ModelSamplingAuraFlow",
+        "enableTabs": false,
+        "tabWidth": 65,
+        "tabXOffset": 10,
+        "hasSecondTab": false,
+        "secondTabText": "Send Back",
+        "secondTabOffset": 80,
+        "secondTabWidth": 65,
+        "widget_ue_connectable": {}
+      },
+      "widgets_values": [
+        3.1000000000000005
+      ]
+    },
+    {
+      "id": 99,
+      "type": "Seed (rgthree)",
+      "pos": [
+        422.1023254394531,
+        469.1235046386719
+      ],
+      "size": [
+        210,
+        130
+      ],
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "dir": 4,
+          "label": "随机种",
+          "name": "SEED",
+          "shape": 3,
+          "type": "INT",
+          "links": [
+            162
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "rgthree-comfy",
+        "ver": "f044a9dbb3fc9de55c6244d616d386986add3072"
+      },
+      "widgets_values": [
+        -1,
+        "",
+        "",
+        ""
+      ]
+    },
+    {
+      "id": 8,
+      "type": "VAEDecode",
+      "pos": [
+        723.243896484375,
+        -57.642276763916016
+      ],
+      "size": [
+        210,
+        46
+      ],
+      "flags": {
+        "collapsed": false
+      },
+      "order": 12,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 128
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 76
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "slot_index": 0,
+          "links": [
+            161
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.48",
+        "Node name for S&R": "VAEDecode",
+        "enableTabs": false,
+        "tabWidth": 65,
+        "tabXOffset": 10,
+        "hasSecondTab": false,
+        "secondTabText": "Send Back",
+        "secondTabOffset": 80,
+        "secondTabWidth": 65,
+        "widget_ue_connectable": {}
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 80,
+      "type": "EmptySD3LatentImage",
+      "pos": [
+        52.017391204833984,
+        886.2059936523438
+      ],
+      "size": [
+        219.80580139160156,
+        106
+      ],
+      "flags": {},
+      "order": 9,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "width",
+          "type": "INT",
+          "widget": {
+            "name": "width"
+          },
+          "link": 164
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "widget": {
+            "name": "height"
+          },
+          "link": 165
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            146
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.50",
+        "Node name for S&R": "EmptySD3LatentImage"
+      },
+      "widgets_values": [
+        688,
+        1232,
+        1
+      ]
+    },
+    {
+      "id": 73,
+      "type": "LoraLoaderModelOnly",
+      "pos": [
+        16.05894660949707,
+        -68.63538360595703
+      ],
+      "size": [
+        270,
+        82
+      ],
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 129
+        }
+      ],
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            130
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.49",
+        "Node name for S&R": "LoraLoaderModelOnly",
+        "models": [
+          {
+            "name": "Qwen-Image-Lightning-8steps-V1.0.safetensors",
+            "url": "https://huggingface.co/lightx2v/Qwen-Image-Lightning/resolve/main/Qwen-Image-Lightning-8steps-V1.0.safetensors",
+            "directory": "loras"
+          }
+        ]
+      },
+      "widgets_values": [
+        "qwen-image/Qwen-Image-Edit-Lightning-4steps-V1.0-bf16.safetensors",
+        1
+      ]
+    },
+    {
+      "id": 76,
+      "type": "LoadImage",
+      "pos": [
+        -253.61351013183594,
+        623.075927734375
+      ],
+      "size": [
+        265.8947448730469,
+        329.90789794921875
+      ],
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            163
+          ]
+        },
+        {
+          "name": "MASK",
+          "type": "MASK",
+          "links": null
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.50",
+        "Node name for S&R": "LoadImage"
+      },
+      "widgets_values": [
+        "222.png",
+        "image"
+      ]
+    },
+    {
+      "id": 37,
+      "type": "UNETLoader",
+      "pos": [
+        -26.645963668823242,
+        64.23652648925781
+      ],
+      "size": [
+        330,
+        90
+      ],
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "slot_index": 0,
+          "links": [
+            129
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.48",
+        "Node name for S&R": "UNETLoader",
+        "models": [
+          {
+            "name": "qwen_image_fp8_e4m3fn.safetensors",
+            "url": "https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/resolve/main/split_files/diffusion_models/qwen_image_fp8_e4m3fn.safetensors",
+            "directory": "diffusion_models"
+          }
+        ],
+        "enableTabs": false,
+        "tabWidth": 65,
+        "tabXOffset": 10,
+        "hasSecondTab": false,
+        "secondTabText": "Send Back",
+        "secondTabOffset": 80,
+        "secondTabWidth": 65,
+        "widget_ue_connectable": {}
+      },
+      "widgets_values": [
+        "qwen_image_edit_meitu_fp8_e4m3fn.safetensors",
+        "fp8_e4m3fn"
+      ]
+    },
+    {
+      "id": 77,
+      "type": "TextEncodeQwenImageEdit",
+      "pos": [
+        352.2713928222656,
+        48.01900863647461
+      ],
+      "size": [
+        337.4795227050781,
+        133
+      ],
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 140
+        },
+        {
+          "name": "vae",
+          "shape": 7,
+          "type": "VAE",
+          "link": 139
+        },
+        {
+          "name": "image",
+          "shape": 7,
+          "type": "IMAGE",
+          "link": 166
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            141
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.50",
+        "Node name for S&R": "TextEncodeQwenImageEdit"
+      },
+      "widgets_values": [
+        "Change the background to a beach by the sea",
+        [
+          false,
+          true
+        ]
+      ]
+    },
+    {
+      "id": 98,
+      "type": "PreviewImage",
+      "pos": [
+        1013.5062866210938,
+        -51.07883071899414
+      ],
+      "size": [
+        264.9378703815778,
+        414.4264674054348
+      ],
+      "flags": {},
+      "order": 13,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 161
+        }
+      ],
+      "outputs": [],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.50",
+        "Node name for S&R": "PreviewImage"
+      },
+      "widgets_values": []
+    },
+    {
+      "id": 100,
+      "type": "LayerUtility: ImageScaleByAspectRatio V2",
+      "pos": [
+        23.504955291748047,
+        503.9403076171875
+      ],
+      "size": [
+        274.9136657714844,
+        330
+      ],
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "shape": 7,
+          "type": "IMAGE",
+          "link": 163
+        },
+        {
+          "name": "mask",
+          "shape": 7,
+          "type": "MASK",
+          "link": null
+        }
+      ],
+      "outputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "links": [
+            166
+          ]
+        },
+        {
+          "name": "mask",
+          "type": "MASK",
+          "links": null
+        },
+        {
+          "name": "original_size",
+          "type": "BOX",
+          "links": null
+        },
+        {
+          "name": "width",
+          "type": "INT",
+          "links": [
+            164
+          ]
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "links": [
+            165
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfyui_layerstyle",
+        "ver": "c0fb64d0ebcb81c6c445a8af79ecee24bc3845b0",
+        "Node name for S&R": "LayerUtility: ImageScaleByAspectRatio V2"
+      },
+      "widgets_values": [
+        "original",
+        1,
+        1,
+        "letterbox",
+        "lanczos",
+        "16",
+        "longest",
+        1280,
+        "#000000"
+      ],
+      "color": "rgba(38, 73, 116, 0.7)"
+    },
+    {
+      "id": 3,
+      "type": "KSampler",
+      "pos": [
+        703.9965833986478,
+        39.88256421121094
+      ],
+      "size": [
+        253.9251708984375,
+        546.444091796875
+      ],
+      "flags": {},
+      "order": 11,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 125
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 141
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 142
+        },
+        {
+          "name": "latent_image",
+          "type": "LATENT",
+          "link": 146
+        },
+        {
+          "name": "seed",
+          "type": "INT",
+          "widget": {
+            "name": "seed"
+          },
+          "link": 162
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "slot_index": 0,
+          "links": [
+            128
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.48",
+        "Node name for S&R": "KSampler",
+        "enableTabs": false,
+        "tabWidth": 65,
+        "tabXOffset": 10,
+        "hasSecondTab": false,
+        "secondTabText": "Send Back",
+        "secondTabOffset": 80,
+        "secondTabWidth": 65,
+        "widget_ue_connectable": {}
+      },
+      "widgets_values": [
+        875418790252312,
+        "randomize",
+        4,
+        1,
+        "euler",
+        "simple",
+        1
+      ]
+    }
+  ],
+  "links": [
+    [
+      75,
+      38,
+      0,
+      7,
+      0,
+      "CLIP"
+    ],
+    [
+      76,
+      39,
+      0,
+      8,
+      1,
+      "VAE"
+    ],
+    [
+      125,
+      66,
+      0,
+      3,
+      0,
+      "MODEL"
+    ],
+    [
+      128,
+      3,
+      0,
+      8,
+      0,
+      "LATENT"
+    ],
+    [
+      129,
+      37,
+      0,
+      73,
+      0,
+      "MODEL"
+    ],
+    [
+      130,
+      73,
+      0,
+      66,
+      0,
+      "MODEL"
+    ],
+    [
+      139,
+      39,
+      0,
+      77,
+      1,
+      "VAE"
+    ],
+    [
+      140,
+      38,
+      0,
+      77,
+      0,
+      "CLIP"
+    ],
+    [
+      141,
+      77,
+      0,
+      3,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      142,
+      7,
+      0,
+      3,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      146,
+      80,
+      0,
+      3,
+      3,
+      "LATENT"
+    ],
+    [
+      161,
+      8,
+      0,
+      98,
+      0,
+      "IMAGE"
+    ],
+    [
+      162,
+      99,
+      0,
+      3,
+      4,
+      "INT"
+    ],
+    [
+      163,
+      76,
+      0,
+      100,
+      0,
+      "IMAGE"
+    ],
+    [
+      164,
+      100,
+      3,
+      80,
+      0,
+      "INT"
+    ],
+    [
+      165,
+      100,
+      4,
+      80,
+      1,
+      "INT"
+    ],
+    [
+      166,
+      100,
+      0,
+      77,
+      2,
+      "IMAGE"
+    ]
+  ],
+  "groups": [
+    {
+      "id": 5,
+      "title": "模型加载",
+      "bounding": [
+        -45.6744270324707,
+        -142.2353515625,
+        359.0284729003906,
+        558.515625
+      ],
+      "color": "#3f789e",
+      "font_size": 24,
+      "flags": {}
+    },
+    {
+      "id": 6,
+      "title": "输入端",
+      "bounding": [
+        -253.14199829101562,
+        430.1003723144531,
+        561.5076293945312,
+        577.5477294921875
+      ],
+      "color": "#3f789e",
+      "font_size": 24,
+      "flags": {}
+    },
+    {
+      "id": 7,
+      "title": "Latent",
+      "bounding": [
+        324.2939758300781,
+        -138.61012268066406,
+        646.9595336914062,
+        741.6004028320312
+      ],
+      "color": "#3f789e",
+      "font_size": 24,
+      "flags": {}
+    }
+  ],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 1.0610764609500023,
+      "offset": [
+        253.1981291727586,
+        384.51883759259294
+      ]
+    },
+    "frontendVersion": "1.28.7",
+    "ue_links": [],
+    "links_added_by_ue": [],
+    "VHS_latentpreview": false,
+    "VHS_latentpreviewrate": 0,
+    "VHS_MetadataImage": true,
+    "VHS_KeepIntermediate": true
+  },
+  "version": 0.4
+}

README.md

@@ -0,0 +1,106 @@
+---
+license: apache-2.0
+language:
+- en
+- zh
+library_name: diffusers
+base_model:
+- Qwen/Qwen-Image-Edit
+pipeline_tag: image-to-image
+tags:
+- image-editing
+- consistency
+- aesthetics
+- DiT
+- Qwen-Image
+- ValiantCat
+---
+
+<p align="center">
+    <img src="https://ai.static.ad2.cc/banner.png" width="1000"/>
+</p>
+
+---
+
+# 🌈 Qwen-Image-Edit-MeiTu
+
+This model — **Qwen-Image-Edit-MeiTu** — is an improved variant of [Qwen/Qwen-Image-Edit](https://huggingface.co/valiantcat/Qwen-Image-Edit-MeiTu), built with **DiT-based architecture fine-tuning** to enhance **visual consistency**, **aesthetic quality**, and **structural alignment** in complex edits.
+
+Developed by **Valiant Cat AI Lab**, this version aims to further close the gap between high-fidelity semantic editing and coherent artistic rendering, achieving a more natural and professional output across a wide range of prompts and subjects.
+
+---
+
+## ✨ Key Improvements
+
+* **Enhanced Consistency**:  
+  Utilizes DiT (Diffusion Transformer) fine-tuning to ensure **structural stability** between input and edited regions, maintaining global spatial coherence.
+
+* **Aesthetic Optimization**:  
+  Trained with aesthetic discriminators and curated aesthetic score datasets, producing more **pleasing colors, contrast, and light balance**.
+
+* **Better Detail Preservation**:  
+  Improved low-level reconstruction for fine details such as **textures, faces, and typography**.
+
+* **Broader Scene Adaptability**:  
+  Performs well on **portraits, environments, product photos, and illustrations**, supporting both **semantic** and **appearance-based** editing.
+
+---
+
+## 🖼️ Showcase
+
+Below are examples of **consistency and aesthetic improvement** in complex editing scenarios:
+
+| Input & Output |
+|----------------|
+| <img src="preview/result1.png" width="800"/> |
+| <img src="preview/result2.png" width="800"/> |
+| <img src="preview/result3.png" width="800"/> |
+| <img src="preview/result4.png" width="800"/> |
+| <img src="preview/result5.png" width="800"/> |
+
+
+
+## 💬 Recommended Prompts
+
+Try these prompts to explore the model’s strengths:
+
+* “make the lighting soft and cinematic with better balance”  
+* “enhance the photo’s composition and maintain realism”  
+* “refine skin tone and texture consistency”  
+* “improve the global color tone and aesthetic harmony”  
+* “increase photo realism and clarity without changing content”
+
+---
+
+## 🧩 Integration with ComfyUI
+
+This model works seamlessly with a modified [ComfyUI Qwen-Image-Edit workflow](https://huggingface.co/valiantcat/Qwen-Image-Edit-MeiTu/blob/main/Qwen-Edit-MeiTu.json).  
+Just use this model in the **Unet node** to workflow for edit image.
+
+---
+
+## 📥 Download Model
+
+Weights available in **Safetensors** format:
+
+👉 [Download Qwen-Image-Edit-MeiTu](https://huggingface.co/valiantcat/Qwen-Image-Edit-MeiTu)
+
+
+## 🧠 Training
+
+This model was trained and optimized by the  
+**AI Laboratory of Chongqing Valiant Cat Technology Co., LTD.**  
+Visit [https://vvicat.com/](https://vvicat.com/) for business collaborations or research partnerships.
+
+
+## 📜 License
+
+Licensed under **Apache 2.0**.
+
+
+## 💼 Join Us
+
+We are hiring research engineers and creative ML practitioners at  
+**Chongqing Valiant Cat Technology Co., LTD** — reach out via  
+📧 **[email protected]**
+

qwen_image_edit_meitu_fp8_e4m3fn.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2e35116218210ff971ed6eb998d7aad71ee6f5ea8450c35f9c8964aac29c69e
+size 20430677664