wangqixun commited on
Commit
191ae1f
1 Parent(s): d8df565

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -13
README.md CHANGED
@@ -16,18 +16,7 @@ base_model: black-forest-labs/FLUX.1-dev
16
  until the next Diffusers pypi release, please install Diffusers from source and use [this PR](xxxxxx) to be able to use.
17
  TODO: change when new version.
18
 
19
-
20
- ## Checkpoint
21
-
22
- The training of union controlnet requires a significant amount of computational power.
23
- The current release is only an alpha version checkpoint that has not been fully trained.
24
- The beta version is in the training process.
25
- We have conducted ablation studies that have demonstrated the validity of the code.
26
- The open-source release of the alpha version is solely to facilitate the rapid growth of the open-source community and the Flux ecosystem;
27
- it is common to encounter bad cases (please accept my apologies).
28
- It is worth noting that we have found that even a fully trained Union model may not perform as well as specialized models, such as pose control.
29
- However, as training progresses, the performance of the Union model will continue to approach that of specialized models.
30
-
31
  | Control Mode | Description |
32
  |:------------:|:-----------:|
33
  |0|canny|
@@ -38,16 +27,33 @@ However, as training progresses, the performance of the Union model will continu
38
  |5|gray|
39
  |6|lq|
40
 
41
-
42
  <img src="./images/image_demo_canny.jpg" width = "800" />
 
43
  <img src="./images/image_demo_tile.jpg" width = "800" />
 
44
  <img src="./images/image_demo_depth.jpg" width = "800" />
 
45
  <img src="./images/image_demo_blur.jpg" width = "800" />
 
46
  <img src="./images/image_demo_pose.jpg" width = "800" />
 
47
  <img src="./images/image_demo_gray.jpg" width = "800" />
 
48
  <img src="./images/image_demo_lq.jpg" width = "800" />
49
 
50
 
 
 
 
 
 
 
 
 
 
 
 
51
 
52
 
53
  # Demo
 
16
  until the next Diffusers pypi release, please install Diffusers from source and use [this PR](xxxxxx) to be able to use.
17
  TODO: change when new version.
18
 
19
+ ## Control Mode
 
 
 
 
 
 
 
 
 
 
 
20
  | Control Mode | Description |
21
  |:------------:|:-----------:|
22
  |0|canny|
 
27
  |5|gray|
28
  |6|lq|
29
 
30
+ ### canny
31
  <img src="./images/image_demo_canny.jpg" width = "800" />
32
+ ### tile
33
  <img src="./images/image_demo_tile.jpg" width = "800" />
34
+ ### depth
35
  <img src="./images/image_demo_depth.jpg" width = "800" />
36
+ ### blur
37
  <img src="./images/image_demo_blur.jpg" width = "800" />
38
+ ### pose
39
  <img src="./images/image_demo_pose.jpg" width = "800" />
40
+ ### gray
41
  <img src="./images/image_demo_gray.jpg" width = "800" />
42
+ ### low quality
43
  <img src="./images/image_demo_lq.jpg" width = "800" />
44
 
45
 
46
+ ## Checkpoint
47
+
48
+ The training of union controlnet requires a significant amount of computational power.
49
+ The current release is only an alpha version checkpoint that has not been fully trained.
50
+ The beta version is in the training process.
51
+ We have conducted ablation studies that have demonstrated the validity of the code.
52
+ The open-source release of the alpha version is solely to facilitate the rapid growth of the open-source community and the Flux ecosystem;
53
+ it is common to encounter bad cases (please accept my apologies).
54
+ It is worth noting that we have found that even a fully trained Union model may not perform as well as specialized models, such as pose control.
55
+ However, as training progresses, the performance of the Union model will continue to approach that of specialized models.
56
+
57
 
58
 
59
  # Demo