Hugging Face's logo

legekka
/
AI-Anime-Image-Detector-ViT

Image Classification
Transformers
Safetensors
vit
image-detection
ai-image-generation
anime
ai-anime
human-detection
art
Inference Endpoints
Model card Files Community
legekka commited on
Commit
9b9c2cd
•
1 Parent(s): e08643e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -15
README.md CHANGED
@@ -31,21 +31,21 @@ It seems like using random crops helped the model to generalize better, however,
31
 
32
  We did a small comparison with the current available AI image detectors. Note that these models were not specificly trained on anime images.
33
 
34
- | Image | Nahrawy/AIorNot | umm-maybe/AI-image-detector | Organika/sdxl-detector | mmanikanta/VIT_AI_image_detector | Ours |
35
- |--------------------|-----------------|-----------------------------|------------------------|-----------------------------------|------------|
36
- | D:\test\ai_1.jpg | ai (100%) | human (86%) | artificial (100%) | FAKE (89%) | ai (100%) |
37
- | D:\test\ai_2.jpg | ai (99%) | human (96%) | artificial (100%) | FAKE (89%) | ai (100%) |
38
- | D:\test\ai_3.jpg | ai (77%) | human (98%) | artificial (100%) | REAL (100%) | ai (100%) |
39
- | D:\test\ai_4.jpg | real (66%) | human (100%) | human (100%) | REAL (100%) | real (100%)|
40
- | D:\test\ai_5.jpg | ai (51%) | human (99%) | artificial (55%) | REAL (99%) | real (65%) |
41
- | D:\test\ai_6.jpg | ai (100%) | human (98%) | artificial (100%) | FAKE (60%) | ai (84%) |
42
- | D:\test\real_1.jpg | ai (99%) | human (99%) | artificial (100%) | REAL (98%) | ai (55%) |
43
- | D:\test\real_2.jpg | ai (88%) | human (100%) | artificial (100%) | REAL (100%) | real (85%) |
44
- | D:\test\real_3.jpg | ai (95%) | human (96%) | artificial (100%) | REAL (100%) | real (97%) |
45
- | D:\test\real_4.jpg | real (90%) | human (100%) | artificial (97%) | REAL (100%) | real (94%) |
46
- | D:\test\real_5.jpg | ai (75%) | human (100%) | human (57%) | REAL (100%) | real (100%)|
47
- | D:\test\real_6.jpg | ai (89%) | human (98%) | human (100%) | REAL (100%) | real (99%) |
48
- | **Accuracy:** | 50% | 50% | 58% | **75%** | **75%** |
49
 
50
 
51
 
 
31
 
32
  We did a small comparison with the current available AI image detectors. Note that these models were not specificly trained on anime images.
33
 
34
+ | Image | Nahrawy/AIorNot | umm-maybe/AI-image-detector | Organika/sdxl-detector | mmanikanta/VIT_AI_image_detector | Ours |
35
+ |--------------|-----------------|-----------------------------|------------------------|-----------------------------------|------------|
36
+ | ai_1.jpg | ai (100%) | human (86%) | artificial (100%) | FAKE (89%) | ai (100%) |
37
+ | ai_2.jpg | ai (99%) | human (96%) | artificial (100%) | FAKE (89%) | ai (100%) |
38
+ | ai_3.jpg | ai (77%) | human (98%) | artificial (100%) | REAL (100%) | ai (100%) |
39
+ | ai_4.jpg | real (66%) | human (100%) | human (100%) | REAL (100%) | real (100%)|
40
+ | ai_5.jpg | ai (51%) | human (99%) | artificial (55%) | REAL (99%) | real (65%) |
41
+ | ai_6.jpg | ai (100%) | human (98%) | artificial (100%) | FAKE (60%) | ai (84%) |
42
+ | real_1.jpg | ai (99%) | human (99%) | artificial (100%) | REAL (98%) | ai (55%) |
43
+ | real_2.jpg | ai (88%) | human (100%) | artificial (100%) | REAL (100%) | real (85%) |
44
+ | real_3.jpg | ai (95%) | human (96%) | artificial (100%) | REAL (100%) | real (97%) |
45
+ | real_4.jpg | real (90%) | human (100%) | artificial (97%) | REAL (100%) | real (94%) |
46
+ | real_5.jpg | ai (75%) | human (100%) | human (57%) | REAL (100%) | real (100%)|
47
+ | real_6.jpg | ai (89%) | human (98%) | human (100%) | REAL (100%) | real (99%) |
48
+ | **Accuracy:**| 50% | 50% | 58% | **75%** | **75%** |
49
 
50
 
51