bubbliiiing commited on
Commit
3a7324b
·
1 Parent(s): a3e5080

Update README

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -32,7 +32,7 @@ library_name: videox_fun
32
 
33
  ## Model Features
34
  - This ControlNet is added on 15 layer blocks and 2 refiner layer blocks (Lite models are added on 3 layer blocks and 2 refiner blocks). It supports multiple control conditions—including Canny, HED, Depth, Pose and MLSD can be used like a standard ControlNet.
35
- - Inpainting mode is also supported.
36
  - Training Process:
37
  - 2.0: The model was trained from scratch for 70,000 steps on a dataset of 1 million high-quality images covering both general and human-centric content. Training was performed at 1328 resolution using BFloat16 precision, with a batch size of 64, a learning rate of 2e-5, and a text dropout ratio of 0.10.
38
  - 2.1: Version 2.1 is based on the version 2.0 weights and continued training for an additional 11,000 steps after the typo fix, using the same parameters and dataset.
@@ -40,7 +40,7 @@ library_name: videox_fun
40
  - Note on Steps:
41
  - 2.0 and 2.1: As you increase the control strength (higher control_context_scale values), it's recommended to appropriately increase the number of inference steps to achieve better results and maintain generation quality. This is likely because the control model has not been distilled.
42
  - 2.1-8-steps: Just use 8 steps in inference.
43
- - You can adjust control_context_scale for stronger control and better detail preservation. For better stability, we highly recommend using a detailed prompt. The optimal range for control_context_scale is from 0.65 to 0.90.
44
  - During testing, in versions 2.0 and 2.1, we found that applying ControlNet to Z-Image-Turbo caused the model to lose its acceleration capability and produce blurry images. For detailed information on strength and step count testing, please refer to Scale Test Results. These results were generated using version 2.0. For strength and step testing, please refer to [Scale Test Results](#scale-test-results). This was obtained by generating with version 2.0.
45
 
46
  ## Results
 
32
 
33
  ## Model Features
34
  - This ControlNet is added on 15 layer blocks and 2 refiner layer blocks (Lite models are added on 3 layer blocks and 2 refiner blocks). It supports multiple control conditions—including Canny, HED, Depth, Pose and MLSD can be used like a standard ControlNet.
35
+ - Inpainting mode is also supported. When using inpaint mode, please use a larger control_context_scale, as this will result in better image continuity.
36
  - Training Process:
37
  - 2.0: The model was trained from scratch for 70,000 steps on a dataset of 1 million high-quality images covering both general and human-centric content. Training was performed at 1328 resolution using BFloat16 precision, with a batch size of 64, a learning rate of 2e-5, and a text dropout ratio of 0.10.
38
  - 2.1: Version 2.1 is based on the version 2.0 weights and continued training for an additional 11,000 steps after the typo fix, using the same parameters and dataset.
 
40
  - Note on Steps:
41
  - 2.0 and 2.1: As you increase the control strength (higher control_context_scale values), it's recommended to appropriately increase the number of inference steps to achieve better results and maintain generation quality. This is likely because the control model has not been distilled.
42
  - 2.1-8-steps: Just use 8 steps in inference.
43
+ - You can adjust control_context_scale for stronger control and better detail preservation. For better stability, we highly recommend using a detailed prompt. The optimal range for control_context_scale is from 0.65 to 1.00.
44
  - During testing, in versions 2.0 and 2.1, we found that applying ControlNet to Z-Image-Turbo caused the model to lose its acceleration capability and produce blurry images. For detailed information on strength and step count testing, please refer to Scale Test Results. These results were generated using version 2.0. For strength and step testing, please refer to [Scale Test Results](#scale-test-results). This was obtained by generating with version 2.0.
45
 
46
  ## Results