GuardSkill commited on
Commit
51d09f5
·
verified ·
1 Parent(s): 7be088b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -1
README.md CHANGED
@@ -45,6 +45,7 @@ InstantCamera Triptych Results show off.
45
  ## Model Card for Model ID
46
 
47
  因为原生的Qwen-Edit-2509的多图输入的结果中人物一致性并不是很好,特别是在一些指定的场景和指定的分辨率下。本模型重新针对多图输入的合照场景对Qwen-Edit-2509进行重新训练,保持高度人物一致性,输入两张图的图像为他们生成合照。
 
48
  The native Qwen-Edit-2509 model often struggles with consistency in multi-image inputs, particularly at specific resolutions and scenes. This model is a fine-tuned version, specifically optimized for generating group photos from multiple portraits. It maintains high character consistency, allowing you to input individual photos and produce a coherent composite image.
49
 
50
 
@@ -55,10 +56,15 @@ The native Qwen-Edit-2509 model often struggles with consistency in multi-image
55
  ## Prompts phrase
56
 
57
  ```两人相互对视并牵手的照片,保持两人人脸、服饰、装扮高度一致,背景在温暖的客厅室内,95年代复古风格。整个画面具有老式照片的不清晰感,颗粒感,严重的晃动感,复古的滤镜。```
 
58
  ```两人相互接吻的照片,保持两人人脸、服饰、装扮高度一致,背景是平坦的高原山脉,80年代复古风格。整个画面具有老式照片的不清晰感,颗粒感,严重的晃动感,复古的滤镜。```
 
59
  ```两人相互对视并牵手的照片,保持两人人脸、服饰、装扮高度一致,背景在温暖的客厅室内,95年代复古风格。整个画面具有老式照片的不清晰感,颗粒感,严重的晃动感,复古的滤镜。```
 
60
  ```两人站在街头合照并挽着手的照片,保持两人人脸高度一致,男士穿着夹克外套,露出南瓜头的T恤,女士穿着时尚的偏橘黄色的装扮,背景是万圣节日的欧洲小镇的马路中央,万圣节节日风格```
 
61
  ```两人站在一个石头拱门墙前的酷酷合拍,保持两人人脸高度一致,两人穿着黑色的时尚帅气装扮,拱门后的天气阴暗,还有稀疏的枯木。```
 
62
  ```两人在室内的合照,保持两人人脸高度一致,两人穿着有万圣节节日气息的小饰品,背后有是奶油风的室内场景,有一些万圣节背景元素。```
63
 
64
  There is no fixed trigger word. The specific photous prompt needs to be tested more.
@@ -67,7 +73,7 @@ There is no fixed trigger word. The specific photous prompt needs to be tested m
67
 
68
  Weights for this model are available in Safetensors format.
69
 
70
- [Download](https://huggingface.co/valiantcat/Qwen-Image-Edit-2509-photous)
71
 
72
  ## Training at Chongqing Valiant Cat
73
 
 
45
  ## Model Card for Model ID
46
 
47
  因为原生的Qwen-Edit-2509的多图输入的结果中人物一致性并不是很好,特别是在一些指定的场景和指定的分辨率下。本模型重新针对多图输入的合照场景对Qwen-Edit-2509进行重新训练,保持高度人物一致性,输入两张图的图像为他们生成合照。
48
+
49
  The native Qwen-Edit-2509 model often struggles with consistency in multi-image inputs, particularly at specific resolutions and scenes. This model is a fine-tuned version, specifically optimized for generating group photos from multiple portraits. It maintains high character consistency, allowing you to input individual photos and produce a coherent composite image.
50
 
51
 
 
56
  ## Prompts phrase
57
 
58
  ```两人相互对视并牵手的照片,保持两人人脸、服饰、装扮高度一致,背景在温暖的客厅室内,95年代复古风格。整个画面具有老式照片的不清晰感,颗粒感,严重的晃动感,复古的滤镜。```
59
+
60
  ```两人相互接吻的照片,保持两人人脸、服饰、装扮高度一致,背景是平坦的高原山脉,80年代复古风格。整个画面具有老式照片的不清晰感,颗粒感,严重的晃动感,复古的滤镜。```
61
+
62
  ```两人相互对视并牵手的照片,保持两人人脸、服饰、装扮高度一致,背景在温暖的客厅室内,95年代复古风格。整个画面具有老式照片的不清晰感,颗粒感,严重的晃动感,复古的滤镜。```
63
+
64
  ```两人站在街头合照并挽着手的照片,保持两人人脸高度一致,男士穿着夹克外套,露出南瓜头的T恤,女士穿着时尚的偏橘黄色的装扮,背景是万圣节日的欧洲小镇的马路中央,万圣节节日风格```
65
+
66
  ```两人站在一个石头拱门墙前的酷酷合拍,保持两人人脸高度一致,两人穿着黑色的时尚帅气装扮,拱门后的天气阴暗,还有稀疏的枯木。```
67
+
68
  ```两人在室内的合照,保持两人人脸高度一致,两人穿着有万圣节节日气息的小饰品,背后有是奶油风的室内场景,有一些万圣节背景元素。```
69
 
70
  There is no fixed trigger word. The specific photous prompt needs to be tested more.
 
73
 
74
  Weights for this model are available in Safetensors format.
75
 
76
+ [Download](https://huggingface.co/valiantcat/Qwen-Image-Edit-2509-photous/blob/main/QwenEdit2509_photous_000010000.safetensors)
77
 
78
  ## Training at Chongqing Valiant Cat
79