Upload folder using huggingface_hub

Wan2.2-T2V-A14B-4steps-lora-rank64-Seko-V1/README.md

@@ -0,0 +1,19 @@
+
+![Lightx2V](https://github.com/ModelTC/LightX2V)
+<!-- ![Lightx2V ComfyUI](https://github.com/ModelTC/LightX2V) -->
+
+![Example Video 1](https://github.com/user-attachments/assets/29ded349-9ebd-4de4-aa3c-7cdc1089fc86)
+![Example Video 2](https://github.com/user-attachments/assets/04101a92-9c19-4b47-a3fc-934f6aa2932c)
+![Example Video 3](https://github.com/user-attachments/assets/d41cb4c5-3ee5-46fa-b1ef-016b69fdd58e)
+
+
+# ComfyUI
+[See kijai github](https://github.com/kijai/ComfyUI-WanVideoWrapper) for comfy ui workflows.
+
+# Training details
+High_noise_model and low_noise_model are distilled simultaneously. On 81x720x1280, 81x1280x720, 81x480x832, 81x832x480 size options.
+
+# Tips on usage
+In the distillation process, euler scheduler is used, with time_shift = 5. Specifically, the timesetps should be [1000.0000,  937.5001,  833.3333,  625.0000]
+
+In inference, please set the scheduler accordingly. Besides, please set cfg = 1.0 so that NFE = 4 but not 8.

Wan2.2-T2V-A14B-4steps-lora-rank64-Seko-V1/high_noise_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bdf6a230a9b830de506f2b608450143480644390f8eacec20118a32ffb42959
+size 1226958224

Wan2.2-T2V-A14B-4steps-lora-rank64-Seko-V1/low_noise_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56cab2cc10ab0edf1070b5526a5ab4cbaed9c311bc58c2bc3fc5c2a0a2002321
+size 1226958224