GUI

README.md

@@ -146,10 +146,10 @@ To evaluate the performance of HunyuanVideo, we selected five strong baselines f
 
 The following table shows the requirements for running HunyuanVideo model (batch size = 1) to generate videos:
 
-|     Model    |  Setting<br/>(height/width/frame) | GPU Peak Memory  |
-|:------------:|:--------------------------------:|:----------------:|
-| HunyuanVideo   |        720px1280px129f          |       60GB        |
-| HunyuanVideo   |        544px960px129f           |       45GB        |
+|     Model    |  Setting<br/>(height/width/frame) | Denoising step | GPU Peak Memory  |
+|:------------:|:--------------------------------:|:--------------:|:----------------:|
+| HunyuanVideo   |        720px1280px129f          |       30       |       60GB        |
+| HunyuanVideo   |        544px960px129f           |       30       |       45GB        |
 
 * An NVIDIA GPU with CUDA support is required. 
   * The model is tested on a single 80G GPU.

hunyuan-video-t2v-720p/transformers/mp_rank_00_model_states_fp8.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:99fbade8af80b5233194e4e8afcaa3ca68a412fce6403a440f962a432fc18a9c
-size 13185233506

hunyuan-video-t2v-720p/transformers/mp_rank_00_model_states_fp8_map.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9dd948e1717718f93ad5c23cbb32fe5fe14516c7acbe8b39b63cac2a7ab575cd
-size 103890