Qwen-Image-Editを利用して画像編集の生成をローカルのPCで実行したいです。インストール手順を教えてほしいです。
UIはComfyUIを利用する想定でいます。
Qwen-Image Edit のインストール手順を紹介します。
ComfyUIをインストールします。最新版である必要があります。
インストール手順はこちらの記事のPortable版のインストールを参照してください
Qwen-Image-Edit をインストールする手順を紹介します。
以下の HuggingFaceのHubから、Qwen-Image-Editのfp8のモデル qwen_image_edit_2509_fp8_e4m3fn.safetensors をダウンロードします。
以下の HuggingFaceのHubから、Qwen-Image-Editのfp8のモデル qwen_image_edit_fp8_e4m3fn.safetensors をダウンロードします。
ダウンロードしたモデルを次のディレクトリに配置します。
(ComfyUIの配置ディレクトリ)\models\diffusion_models\
または
(ComfyUIの配置ディレクトリ)\models\diffusion_models\qwen-image-edit\
以下の HuggingFaceのHubから、Qwen-Imageのテキストエンコーダー qwen_2.5_vl_7b_fp8_scaled.safetensors をダウンロードします。(Qwen-Imageと同じです)
ダウンロードしたモデルを次のディレクトリに配置します。
(ComfyUIの配置ディレクトリ)\models\text_encoders\
または
(ComfyUIの配置ディレクトリ)\models\text_encoders\qwen-image\
以下の HuggingFaceのHubから、Qwen-ImageのVAE qwen_image_vae.safetensors をダウンロードします。(Qwen-Imageと同じです)
ダウンロードしたモデルを次のディレクトリに配置します。
(ComfyUIの配置ディレクトリ)\models\vae\
または
(ComfyUIの配置ディレクトリ)\models\vae\qwen-image\
ファイルの配置は以上です。
ComfyUIを起動し、以下のワークフローを作成します。
[TextEncoderQwenImageEditPlus]のノードは以下のメニューにあります。
[ノードを追加] > [高度な機能] > [条件付け] > [TextEncoderQwenImageEditPlus]
[CFGNorm]のノードは以下のメニューにあります。
[ノードを追加] > [高度な機能] > [ガイダンス] > [CFGNorm]
ワークフローのJSONは以下です。
{
"id": "6a5f7751-1158-4b96-98bc-e6736ab017f2",
"revision": 0,
"last_node_id": 134,
"last_link_id": 269,
"nodes": [
{
"id": 121,
"type": "CLIPLoader",
"pos": [
-259.2861633300781,
204.64100646972656
],
"size": [
500,
110
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "CLIP",
"type": "CLIP",
"links": [
262,
265
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.48",
"Node name for S&R": "CLIPLoader"
},
"widgets_values": [
"qwen-image\\qwen_2.5_vl_7b_fp8_scaled.safetensors",
"qwen_image",
"default"
]
},
{
"id": 5,
"type": "CLIPTextEncode",
"pos": [
329.2820129394531,
474.30780029296875
],
"size": [
500,
90
],
"flags": {
"collapsed": false
},
"order": 4,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 262
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"slot_index": 0,
"links": [
22
]
}
],
"title": "CLIP Text Encode (Negative)",
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.47",
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
""
]
},
{
"id": 21,
"type": "VAEDecode",
"pos": [
1342.4583740234375,
-68.53590393066406
],
"size": [
200,
60
],
"flags": {
"collapsed": false
},
"order": 12,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 115
},
{
"name": "vae",
"type": "VAE",
"link": 211
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"slot_index": 0,
"links": [
112
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.47",
"Node name for S&R": "VAEDecode"
},
"widgets_values": []
},
{
"id": 66,
"type": "SaveImage",
"pos": [
1589.38232421875,
-68.40391540527344
],
"size": [
518.892822265625,
429.1415100097656
],
"flags": {},
"order": 13,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 112
}
],
"outputs": [],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.47",
"Node name for S&R": "SaveImage"
},
"widgets_values": [
"%date:yyyyMMdd_hhmmss%_t2i_Qwen-Image-fp8_test"
]
},
{
"id": 124,
"type": "EmptySD3LatentImage",
"pos": [
598.39599609375,
620.0835571289062
],
"size": [
330,
110
],
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "width",
"type": "INT",
"widget": {
"name": "width"
},
"link": 259
},
{
"name": "height",
"type": "INT",
"widget": {
"name": "height"
},
"link": 260
},
{
"name": "batch_size",
"type": "INT",
"widget": {
"name": "batch_size"
},
"link": 261
}
],
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"links": [
250
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.48",
"Node name for S&R": "EmptySD3LatentImage"
},
"widgets_values": [
928,
1664,
1
]
},
{
"id": 128,
"type": "FluxKontextImageScale",
"pos": [
80.96746826171875,
630.9010620117188
],
"size": [
187.75448608398438,
26
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"name": "image",
"type": "IMAGE",
"link": 256
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
258,
266
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.51",
"Node name for S&R": "FluxKontextImageScale"
},
"widgets_values": []
},
{
"id": 131,
"type": "GetImageSize",
"pos": [
366.3339538574219,
629.4735107421875
],
"size": [
140,
124
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "image",
"type": "IMAGE",
"link": 258
}
],
"outputs": [
{
"name": "width",
"type": "INT",
"links": [
259
]
},
{
"name": "height",
"type": "INT",
"links": [
260
]
},
{
"name": "batch_size",
"type": "INT",
"links": [
261
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.51",
"Node name for S&R": "GetImageSize"
},
"widgets_values": [
"width: 832, height: 1248\n batch size: 1"
]
},
{
"id": 126,
"type": "LoadImage",
"pos": [
-360.30859375,
628.9431762695312
],
"size": [
413.09088134765625,
406.1212463378906
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
256
]
},
{
"name": "MASK",
"type": "MASK",
"links": null
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.51",
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"08.png",
"image"
]
},
{
"id": 16,
"type": "KSampler",
"pos": [
979.0615844726562,
58.50777816772461
],
"size": [
330,
270
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 269
},
{
"name": "positive",
"type": "CONDITIONING",
"link": 267
},
{
"name": "negative",
"type": "CONDITIONING",
"link": 22
},
{
"name": "latent_image",
"type": "LATENT",
"link": 250
}
],
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"slot_index": 0,
"links": [
115
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.47",
"Node name for S&R": "KSampler"
},
"widgets_values": [
741661333780048,
"randomize",
20,
2.5,
"euler",
"simple",
1
]
},
{
"id": 75,
"type": "VAELoader",
"pos": [
-259.2861633300781,
-55.35899353027344
],
"size": [
500,
70
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"slot_index": 0,
"links": [
211,
264
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.47",
"Node name for S&R": "VAELoader"
},
"widgets_values": [
"qwen-image\\qwen_image_vae.safetensors"
]
},
{
"id": 132,
"type": "TextEncodeQwenImageEditPlus",
"pos": [
338.8173828125,
184.61123657226562
],
"size": [
486.5150146484375,
219.96499633789062
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 265
},
{
"name": "vae",
"shape": 7,
"type": "VAE",
"link": 264
},
{
"name": "image1",
"shape": 7,
"type": "IMAGE",
"link": 266
},
{
"name": "image2",
"shape": 7,
"type": "IMAGE",
"link": null
},
{
"name": "image3",
"shape": 7,
"type": "IMAGE",
"link": null
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
267
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.60",
"Node name for S&R": "TextEncodeQwenImageEditPlus"
},
"widgets_values": [
"sitting on stool.put feet forward,"
]
},
{
"id": 68,
"type": "UNETLoader",
"pos": [
-259.2861633300781,
64.64099884033203
],
"size": [
500,
90
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"slot_index": 0,
"links": [
246
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.47",
"Node name for S&R": "UNETLoader"
},
"widgets_values": [
"qwen-image-edit\\qwen_image_edit_2509_fp8_e4m3fn.safetensors",
"default"
]
},
{
"id": 122,
"type": "ModelSamplingAuraFlow",
"pos": [
348.7427062988281,
64.01853942871094
],
"size": [
250,
60
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 246
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
268
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.48",
"Node name for S&R": "ModelSamplingAuraFlow"
},
"widgets_values": [
3.5
]
},
{
"id": 134,
"type": "CFGNorm",
"pos": [
640.608642578125,
64.13288879394531
],
"size": [
270,
58
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 268
}
],
"outputs": [
{
"name": "patched_model",
"type": "MODEL",
"links": [
269
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.60",
"Node name for S&R": "CFGNorm"
},
"widgets_values": [
1
]
}
],
"links": [
[
22,
5,
0,
16,
2,
"CONDITIONING"
],
[
112,
21,
0,
66,
0,
"IMAGE"
],
[
115,
16,
0,
21,
0,
"LATENT"
],
[
211,
75,
0,
21,
1,
"VAE"
],
[
246,
68,
0,
122,
0,
"MODEL"
],
[
250,
124,
0,
16,
3,
"LATENT"
],
[
256,
126,
0,
128,
0,
"IMAGE"
],
[
258,
128,
0,
131,
0,
"IMAGE"
],
[
259,
131,
0,
124,
0,
"INT"
],
[
260,
131,
1,
124,
1,
"INT"
],
[
261,
131,
2,
124,
2,
"INT"
],
[
262,
121,
0,
5,
0,
"CLIP"
],
[
264,
75,
0,
132,
1,
"VAE"
],
[
265,
121,
0,
132,
0,
"CLIP"
],
[
266,
128,
0,
132,
2,
"IMAGE"
],
[
267,
132,
0,
16,
1,
"CONDITIONING"
],
[
268,
122,
0,
134,
0,
"MODEL"
],
[
269,
134,
0,
16,
0,
"MODEL"
]
],
"groups": [],
"config": {},
"extra": {
"ds": {
"scale": 0.6830134553650707,
"offset": [
412.60638590616935,
135.43195411893404
]
},
"frontendVersion": "1.26.13"
},
"version": 0.4
}
ComfyUIを起動し、以下のワークフローを作成します。
[画像を総ピクセル数にスケール]のノードは以下のメニューにあります。
[ノードを追加] > [画像] > [アップスケーリング] > [画像を総ピクセル数にスケール]
[VAEエンコード][VAEデコード]のノードは以下のメニューにあります。
[ノードを追加] > [潜在] > [VAEエンコード]
[ノードを追加] > [潜在] > [VAEデコード]
[TextEncoderQwenImageEdit]のノードは以下のメニューにあります。
[ノードを追加] > [高度な機能] > [条件付け] > [TextEncoderQwenImageEdit]
ワークフローのJSONは以下です。
{
"id": "6a5f7751-1158-4b96-98bc-e6736ab017f2",
"revision": 0,
"last_node_id": 134,
"last_link_id": 272,
"nodes": [
{
"id": 121,
"type": "CLIPLoader",
"pos": [
-259.2861633300781,
204.64100646972656
],
"size": [
500,
110
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "CLIP",
"type": "CLIP",
"links": [
263,
264
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.48",
"Node name for S&R": "CLIPLoader"
},
"widgets_values": [
"qwen-image\\qwen_2.5_vl_7b_fp8_scaled.safetensors",
"qwen_image",
"default"
]
},
{
"id": 134,
"type": "VAEEncode",
"pos": [
586.6044311523438,
656.461181640625
],
"size": [
140,
46
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "pixels",
"type": "IMAGE",
"link": 267
},
{
"name": "vae",
"type": "VAE",
"link": 272
}
],
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"links": [
268
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.51",
"Node name for S&R": "VAEEncode"
},
"widgets_values": []
},
{
"id": 132,
"type": "TextEncodeQwenImageEdit",
"pos": [
334.2413330078125,
462.22906494140625
],
"size": [
394.5230712890625,
130.1999969482422
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 264
},
{
"name": "vae",
"shape": 7,
"type": "VAE",
"link": null
},
{
"name": "image",
"shape": 7,
"type": "IMAGE",
"link": null
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
271
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.51",
"Node name for S&R": "TextEncodeQwenImageEdit"
},
"widgets_values": [
""
]
},
{
"id": 68,
"type": "UNETLoader",
"pos": [
-259.2861633300781,
64.64099884033203
],
"size": [
500,
90
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"slot_index": 0,
"links": [
246
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.47",
"Node name for S&R": "UNETLoader"
},
"widgets_values": [
"qwen-image-edit\\qwen_image_edit_fp8_e4m3fn.safetensors",
"default"
]
},
{
"id": 75,
"type": "VAELoader",
"pos": [
-259.2861633300781,
-55.35899353027344
],
"size": [
500,
70
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"slot_index": 0,
"links": [
211,
254,
272
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.47",
"Node name for S&R": "VAELoader"
},
"widgets_values": [
"qwen-image\\qwen_image_vae.safetensors"
]
},
{
"id": 133,
"type": "ImageScaleToTotalPixels",
"pos": [
3.769843101501465,
658.942626953125
],
"size": [
281.8999938964844,
82
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "image",
"type": "IMAGE",
"link": 266
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
267,
269
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.51",
"Node name for S&R": "ImageScaleToTotalPixels"
},
"widgets_values": [
"nearest-exact",
1
]
},
{
"id": 122,
"type": "ModelSamplingAuraFlow",
"pos": [
470.9951171875,
62.554443359375
],
"size": [
250,
60
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 246
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
247
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.48",
"Node name for S&R": "ModelSamplingAuraFlow"
},
"widgets_values": [
3.5
]
},
{
"id": 16,
"type": "KSampler",
"pos": [
824.5587158203125,
62.22126770019531
],
"size": [
330,
270
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 247
},
{
"name": "positive",
"type": "CONDITIONING",
"link": 270
},
{
"name": "negative",
"type": "CONDITIONING",
"link": 271
},
{
"name": "latent_image",
"type": "LATENT",
"link": 268
}
],
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"slot_index": 0,
"links": [
115
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.47",
"Node name for S&R": "KSampler"
},
"widgets_values": [
1040342518450219,
"randomize",
20,
4,
"euler",
"simple",
1
]
},
{
"id": 21,
"type": "VAEDecode",
"pos": [
1193.985595703125,
-71.69037628173828
],
"size": [
200,
60
],
"flags": {
"collapsed": false
},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 115
},
{
"name": "vae",
"type": "VAE",
"link": 211
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"slot_index": 0,
"links": [
112
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.47",
"Node name for S&R": "VAEDecode"
},
"widgets_values": []
},
{
"id": 66,
"type": "SaveImage",
"pos": [
1427.2532958984375,
-70.22738647460938
],
"size": [
518.892822265625,
429.1415100097656
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 112
}
],
"outputs": [],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.47",
"Node name for S&R": "SaveImage"
},
"widgets_values": [
"%date:yyyyMMdd_hhmmss%_t2i_Qwen-Image-fp8_test"
]
},
{
"id": 127,
"type": "TextEncodeQwenImageEdit",
"pos": [
335.15234375,
211.72129821777344
],
"size": [
392.6794738769531,
200
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 263
},
{
"name": "vae",
"shape": 7,
"type": "VAE",
"link": 254
},
{
"name": "image",
"shape": 7,
"type": "IMAGE",
"link": 269
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
270
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.51",
"Node name for S&R": "TextEncodeQwenImageEdit"
},
"widgets_values": [
"change from back image"
]
},
{
"id": 126,
"type": "LoadImage",
"pos": [
-469.4084777832031,
660.1057739257812
],
"size": [
413.09088134765625,
406.1212463378906
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
266
]
},
{
"name": "MASK",
"type": "MASK",
"links": null
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.51",
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"example.png",
"image"
]
}
],
"links": [
[
112,
21,
0,
66,
0,
"IMAGE"
],
[
115,
16,
0,
21,
0,
"LATENT"
],
[
211,
75,
0,
21,
1,
"VAE"
],
[
246,
68,
0,
122,
0,
"MODEL"
],
[
247,
122,
0,
16,
0,
"MODEL"
],
[
254,
75,
0,
127,
1,
"VAE"
],
[
263,
121,
0,
127,
0,
"CLIP"
],
[
264,
121,
0,
132,
0,
"CLIP"
],
[
266,
126,
0,
133,
0,
"IMAGE"
],
[
267,
133,
0,
134,
0,
"IMAGE"
],
[
268,
134,
0,
16,
3,
"LATENT"
],
[
269,
133,
0,
127,
2,
"IMAGE"
],
[
270,
127,
0,
16,
1,
"CONDITIONING"
],
[
271,
132,
0,
16,
2,
"CONDITIONING"
],
[
272,
75,
0,
134,
1,
"VAE"
]
],
"groups": [],
"config": {},
"extra": {
"ds": {
"scale": 0.6209213230591552,
"offset": [
484.01674713948194,
195.91119463371578
]
},
"frontendVersion": "1.25.9"
},
"version": 0.4
}
Qwen-Image-Editを実行します。作成したワークフローの[画像を読み込む]ノードに入力画像を設定します。
[TextEncodeQwenImageEdit]ノードのプロンプトに以下を入力します。
[実行]ボタンをクリックして画像生成を実行します。VRAMは10GB程度利用されます。
下図の生成結果が表示されます。入力画像に対する後姿の画像が生成できました。
ComfyUIを起動し、以下のワークフローを作成します。
[TextEncodeQwenImageEdit]のノードは以下のメニューにあります。
[ノードを追加] > [高度な機能] > [条件付け] > [TextEncodeQwenImageEdit]
[FluxKontextImageScale]のノードは以下のメニューにあります。
[ノードを追加] > [高度な機能] > [条件付け] > [flux] > [FluxKontextImageScale]
[Get Image Size]のノードは以下のメニューにあります。
[ノードを追加] > [画像] > [Get Image Size]
[モデルサンプリングオーラフロー (Model Sampling Auraflow)]のノード、
[空のSD3潜在画像]のノードについては、Qwen-Imageの記事を参照してください。
ワークフローのJSONは以下です。
{
"id": "3a7e25d6-98b1-41e2-8b14-46d22e5c77e4",
"revision": 0,
"last_node_id": 131,
"last_link_id": 263,
"nodes": [
{
"id": 68,
"type": "UNETLoader",
"pos": [
-259.2861633300781,
64.64099884033203
],
"size": [
500,
90
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"slot_index": 0,
"links": [
246
]
}
],
"properties": {
"Node name for S&R": "UNETLoader",
"cnr_id": "comfy-core",
"ver": "0.3.47"
},
"widgets_values": [
"qwen-image-edit\\qwen_image_edit_fp8_e4m3fn.safetensors",
"default"
]
},
{
"id": 121,
"type": "CLIPLoader",
"pos": [
-259.2861633300781,
204.64100646972656
],
"size": [
500,
110
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "CLIP",
"type": "CLIP",
"links": [
262,
263
]
}
],
"properties": {
"Node name for S&R": "CLIPLoader",
"cnr_id": "comfy-core",
"ver": "0.3.48"
},
"widgets_values": [
"qwen-image\\qwen_2.5_vl_7b_fp8_scaled.safetensors",
"qwen_image",
"default"
]
},
{
"id": 75,
"type": "VAELoader",
"pos": [
-259.2861633300781,
-55.35899353027344
],
"size": [
500,
70
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"slot_index": 0,
"links": [
211,
254
]
}
],
"properties": {
"Node name for S&R": "VAELoader",
"cnr_id": "comfy-core",
"ver": "0.3.47"
},
"widgets_values": [
"qwen-image\\qwen_image_vae.safetensors"
]
},
{
"id": 5,
"type": "CLIPTextEncode",
"pos": [
329.2820129394531,
474.30780029296875
],
"size": [
500,
90
],
"flags": {
"collapsed": false
},
"order": 5,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 262
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"slot_index": 0,
"links": [
22
]
}
],
"title": "CLIP Text Encode (Negative)",
"properties": {
"Node name for S&R": "CLIPTextEncode",
"cnr_id": "comfy-core",
"ver": "0.3.47"
},
"widgets_values": [
""
]
},
{
"id": 122,
"type": "ModelSamplingAuraFlow",
"pos": [
527.3628540039062,
62.554447174072266
],
"size": [
250,
60
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 246
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
247
]
}
],
"properties": {
"Node name for S&R": "ModelSamplingAuraFlow",
"cnr_id": "comfy-core",
"ver": "0.3.48"
},
"widgets_values": [
3.5
]
},
{
"id": 127,
"type": "TextEncodeQwenImageEdit",
"pos": [
335.15234375,
211.72129821777344
],
"size": [
490.774169921875,
200
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 263
},
{
"name": "vae",
"shape": 7,
"type": "VAE",
"link": 254
},
{
"name": "image",
"shape": 7,
"type": "IMAGE",
"link": 257
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
253
]
}
],
"properties": {
"Node name for S&R": "TextEncodeQwenImageEdit"
},
"widgets_values": [
"change from back imaage"
]
},
{
"id": 16,
"type": "KSampler",
"pos": [
979.0615844726562,
58.50777816772461
],
"size": [
330,
270
],
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 247
},
{
"name": "positive",
"type": "CONDITIONING",
"link": 253
},
{
"name": "negative",
"type": "CONDITIONING",
"link": 22
},
{
"name": "latent_image",
"type": "LATENT",
"link": 250
}
],
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"slot_index": 0,
"links": [
115
]
}
],
"properties": {
"Node name for S&R": "KSampler",
"cnr_id": "comfy-core",
"ver": "0.3.47"
},
"widgets_values": [
46193712770199,
"randomize",
20,
4,
"euler",
"simple",
1
]
},
{
"id": 21,
"type": "VAEDecode",
"pos": [
1342.4583740234375,
-68.53590393066406
],
"size": [
200,
60
],
"flags": {
"collapsed": false
},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 115
},
{
"name": "vae",
"type": "VAE",
"link": 211
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"slot_index": 0,
"links": [
112
]
}
],
"properties": {
"Node name for S&R": "VAEDecode",
"cnr_id": "comfy-core",
"ver": "0.3.47"
},
"widgets_values": []
},
{
"id": 66,
"type": "SaveImage",
"pos": [
1589.38232421875,
-68.40391540527344
],
"size": [
518.892822265625,
429.1415100097656
],
"flags": {},
"order": 12,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 112
}
],
"outputs": [],
"properties": {
"Node name for S&R": "SaveImage",
"cnr_id": "comfy-core",
"ver": "0.3.47"
},
"widgets_values": [
"%date:yyyyMMdd_hhmmss%_t2i_Qwen-Image-fp8_test"
]
},
{
"id": 124,
"type": "EmptySD3LatentImage",
"pos": [
598.39599609375,
620.0835571289062
],
"size": [
330,
110
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [
{
"name": "width",
"type": "INT",
"widget": {
"name": "width"
},
"link": 259
},
{
"name": "height",
"type": "INT",
"widget": {
"name": "height"
},
"link": 260
},
{
"name": "batch_size",
"type": "INT",
"widget": {
"name": "batch_size"
},
"link": 261
}
],
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"links": [
250
]
}
],
"properties": {
"Node name for S&R": "EmptySD3LatentImage",
"cnr_id": "comfy-core",
"ver": "0.3.48"
},
"widgets_values": [
928,
1664,
1
]
},
{
"id": 128,
"type": "FluxKontextImageScale",
"pos": [
80.96746826171875,
630.9010620117188
],
"size": [
187.75448608398438,
26
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "image",
"type": "IMAGE",
"link": 256
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
257,
258
]
}
],
"properties": {
"Node name for S&R": "FluxKontextImageScale"
},
"widgets_values": []
},
{
"id": 126,
"type": "LoadImage",
"pos": [
-360.30859375,
628.9431762695312
],
"size": [
413.09088134765625,
406.1212463378906
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
256
]
},
{
"name": "MASK",
"type": "MASK",
"links": null
}
],
"properties": {
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"example.png",
"image"
]
},
{
"id": 131,
"type": "GetImageSize",
"pos": [
366.3339538574219,
629.4735107421875
],
"size": [
140,
124
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [
{
"name": "image",
"type": "IMAGE",
"link": 258
}
],
"outputs": [
{
"name": "width",
"type": "INT",
"links": [
259
]
},
{
"name": "height",
"type": "INT",
"links": [
260
]
},
{
"name": "batch_size",
"type": "INT",
"links": [
261
]
}
],
"properties": {
"Node name for S&R": "GetImageSize"
},
"widgets_values": []
}
],
"links": [
[
22,
5,
0,
16,
2,
"CONDITIONING"
],
[
112,
21,
0,
66,
0,
"IMAGE"
],
[
115,
16,
0,
21,
0,
"LATENT"
],
[
211,
75,
0,
21,
1,
"VAE"
],
[
246,
68,
0,
122,
0,
"MODEL"
],
[
247,
122,
0,
16,
0,
"MODEL"
],
[
250,
124,
0,
16,
3,
"LATENT"
],
[
253,
127,
0,
16,
1,
"CONDITIONING"
],
[
254,
75,
0,
127,
1,
"VAE"
],
[
256,
126,
0,
128,
0,
"IMAGE"
],
[
257,
128,
0,
127,
2,
"IMAGE"
],
[
258,
128,
0,
131,
0,
"IMAGE"
],
[
259,
131,
0,
124,
0,
"INT"
],
[
260,
131,
1,
124,
1,
"INT"
],
[
261,
131,
2,
124,
2,
"INT"
],
[
262,
121,
0,
5,
0,
"CLIP"
],
[
263,
121,
0,
127,
0,
"CLIP"
]
],
"groups": [],
"config": {},
"extra": {
"ds": {
"scale": 0.6830134553650707,
"offset": [
384.6166376973953,
158.54167400660108
]
},
"frontendVersion": "1.25.9"
},
"version": 0.4
}
Qwen-Image-Editを実行します。作成したワークフローの[画像を読み込む]ノードに入力画像を設定します。
[TextEncodeQwenImageEdit]ノードのプロンプトに以下を入力します。
[実行]ボタンをクリックして画像生成を実行します。VRAMは10GB程度利用されます。
下図の生成結果が表示されます。入力画像に対する後姿の画像が生成できました。
