| [Feature] Hunyuanvideo1.5 add infer config
Co-authored-by: z_yaoxue<zhouyaoxue@huawei.com>
# message auto-generated for no-merge-commit merge:
!2236 merge infer into master
[Feature] Hunyuanvideo1.5 add infer config
Created-by: z_yaoxue
Commit-by: z_yaoxue
Merged-by: ascend-robot
Description: ## What this PR does / why we need it?
混元视频1.5：添加推理流程
新增文件：
- i2v：推理配置、启动脚本、图片地址、文本描述地址、图片示例；
- t2v：推理配置、启动脚本、文本描述地址；
- 推理pipeline：hunyuanvideo_15_pipeline.py；
修改文件：
- hunyuanvideo_utils 新增部分图片剪裁、尺寸适配等功能；
- text_encoder.encode: 适配推理流程
## Does this PR introduce any user-facing change?
无
## How was this patch tested?
Please explain how to verify the correctness and effectiveness of this feature, as well as its usage constraints and limitations.
See merge request: Ascend/MindSpeed-MM!2236 | 2 个月前 |
