Add Wan (qwen-image) to tested models
This commit is contained in:
@@ -33,6 +33,7 @@ The core insight: color and structure are **orthogonal** in the latent patch spa
|
||||
| FLUX2.klein | Tested |
|
||||
| z-image | Tested |
|
||||
| z-image-turbo | Tested |
|
||||
| Wan (qwen-image) | Tested |
|
||||
|
||||
|
||||
LCS calibrates per-VAE, so it should work with any model using a compatible VAE. Feel free to report results with other models.
|
||||
|
||||
@@ -33,6 +33,7 @@ LCS 在扩散采样**过程中**操作,而非生成之后——这是与传统
|
||||
| FLUX2.klein | 已测试 |
|
||||
| z-image | 已测试 |
|
||||
| z-image-turbo | 已测试 |
|
||||
| Wan (qwen-image) | 已测试 |
|
||||
|
||||
LCS 按 VAE 校准,理论上适用于任何使用兼容 VAE 架构的模型。欢迎反馈其他模型的测试结果。
|
||||
|
||||
|
||||
Reference in New Issue
Block a user