Yuxuan Zhang
commited on
Commit
·
fdddd50
1
Parent(s):
6405360
update
Browse files- README.md +13 -13
- text_encoder/config.json +1 -1
README.md
CHANGED
@@ -78,19 +78,19 @@ image.save("cogview4.png")
|
|
78 |
|
79 |
We've tested on multiple benchmarks and achieved the following scores:
|
80 |
|
81 |
-
####
|
82 |
-
|
83 |
-
| Model
|
84 |
-
|
85 |
-
| SDXL
|
86 |
-
| PixArt-alpha
|
87 |
-
| SD3-Medium
|
88 |
-
| DALL-E 3
|
89 |
-
| Flux.1-dev
|
90 |
-
| Janus-Pro-7B
|
91 |
| **CogView4-6B** | **85.13** | 83.85 | 90.35 | **91.17** | **91.14** | 87.29 |
|
92 |
|
93 |
-
####
|
94 |
|
95 |
| Model | Overall | Single Obj. | Two Obj. | Counting | Colors | Position | Color attribution |
|
96 |
|-----------------|----------|-------------|----------|----------|----------|----------|-------------------|
|
@@ -102,7 +102,7 @@ We've tested on multiple benchmarks and achieved the following scores:
|
|
102 |
| Janus-Pro-7B | **0.80** | **0.99** | 0.89 | 0.59 | **0.90** | **0.79** | **0.66** |
|
103 |
| **CogView4-6B** | 0.73 | **0.99** | 0.86 | 0.66 | 0.79 | 0.48 | 0.58 |
|
104 |
|
105 |
-
####
|
106 |
|
107 |
| Model | Color | Shape | Texture | 2D-Spatial | 3D-Spatial | Numeracy | Non-spatial Clip | Complex 3-in-1 |
|
108 |
|-----------------|------------|------------|------------|------------|------------|------------|------------------|----------------|
|
@@ -116,7 +116,7 @@ We've tested on multiple benchmarks and achieved the following scores:
|
|
116 |
|
117 |
## Chinese Text Accuracy Evaluation
|
118 |
|
119 |
-
| Model | Precision | Recall | F1 Score |
|
120 |
|-----------------|------------|------------|------------|------------|
|
121 |
| Kolors | 0.6094 | 0.1886 | 0.2880 | 0.1633 |
|
122 |
| **CogView4-6B** | **0.6969** | **0.5532** | **0.6168** | **0.3265** |
|
|
|
78 |
|
79 |
We've tested on multiple benchmarks and achieved the following scores:
|
80 |
|
81 |
+
#### DPG-Bench
|
82 |
+
|
83 |
+
| Model | Overall | Global | Entity | Attribute | Relation | Other |
|
84 |
+
|-----------------|-----------|-----------|-----------|-----------|-----------|-----------|
|
85 |
+
| SDXL | 74.65 | 83.27 | 82.43 | 80.91 | 86.76 | 80.41 |
|
86 |
+
| PixArt-alpha | 71.11 | 74.97 | 79.32 | 78.60 | 82.57 | 76.96 |
|
87 |
+
| SD3-Medium | 84.08 | 87.90 | **91.01** | 88.83 | 80.70 | 88.68 |
|
88 |
+
| DALL-E 3 | 83.50 | **90.97** | 89.61 | 88.39 | 90.58 | 89.83 |
|
89 |
+
| Flux.1-dev | 83.79 | 85.80 | 86.79 | 89.98 | 90.04 | **89.90** |
|
90 |
+
| Janus-Pro-7B | 84.19 | 86.90 | 88.90 | 89.40 | 89.32 | 89.48 |
|
91 |
| **CogView4-6B** | **85.13** | 83.85 | 90.35 | **91.17** | **91.14** | 87.29 |
|
92 |
|
93 |
+
#### GenEval
|
94 |
|
95 |
| Model | Overall | Single Obj. | Two Obj. | Counting | Colors | Position | Color attribution |
|
96 |
|-----------------|----------|-------------|----------|----------|----------|----------|-------------------|
|
|
|
102 |
| Janus-Pro-7B | **0.80** | **0.99** | 0.89 | 0.59 | **0.90** | **0.79** | **0.66** |
|
103 |
| **CogView4-6B** | 0.73 | **0.99** | 0.86 | 0.66 | 0.79 | 0.48 | 0.58 |
|
104 |
|
105 |
+
#### T2I-CompBench
|
106 |
|
107 |
| Model | Color | Shape | Texture | 2D-Spatial | 3D-Spatial | Numeracy | Non-spatial Clip | Complex 3-in-1 |
|
108 |
|-----------------|------------|------------|------------|------------|------------|------------|------------------|----------------|
|
|
|
116 |
|
117 |
## Chinese Text Accuracy Evaluation
|
118 |
|
119 |
+
| Model | Precision | Recall | F1 Score | Pick@4 |
|
120 |
|-----------------|------------|------------|------------|------------|
|
121 |
| Kolors | 0.6094 | 0.1886 | 0.2880 | 0.1633 |
|
122 |
| **CogView4-6B** | **0.6969** | **0.5532** | **0.6168** | **0.3265** |
|
text_encoder/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/
|
3 |
"architectures": [
|
4 |
"GlmModel"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "THUDM/glm-4-9b-hf",
|
3 |
"architectures": [
|
4 |
"GlmModel"
|
5 |
],
|