Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/teaser2.gif filter=lfs diff=lfs merge=lfs -text

base.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71132d9d1bcbc10f0a04030c1cd3b8b0325bb285a589f1631b1527a25221dc1a
+size 5944885692

lora.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86da74fbe9a852404824f5e162b088d3f084860c0e4834c518c90d1ddc751cb
+size 699995008

readme.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+base_model:
+  - Wan-AI/Wan2.1-T2V-1.3B
+tags:
+  - image-to-video
+---
+# LivePhoto-Wan2.1
+
+[Code Repository](https://github.com/XavierCHEN34/LivePhoto) | [Project Page](https://xavierchen34.github.io/LivePhoto-Page/) | [Wan2.1 Model](https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B) | [Paper](https://arxiv.org/abs/2312.02928)
+
+**LivePhoto-Wan2.1** supports text-guided image-to-video generation with control over motion intensity levels. Built upon the **Wan2.1-T2V-1.3B** architecture, it is adapted for image-to-video tasks using **Pusa** fine-tuning strategy. A **motion intensity module** is plugged in to adjust the movement strength in the generated videos.
+
+  <table align="center">
+    <tr>
+    <td>
+      <img src="./assets/teaser2.gif">
+    </td>
+    </tr>
+    <tr>
+  </table>
+
+### Installation
+```
+conda create -n livephoto python=3.10 -y
+conda activate livephoto
+cd ./LivePhoto-Wan2.1/PusaV1
+pip install -e .
+pip install xfuser>=0.4.3 absl-py peft lightning pandas deepspeed wandb av 
+```
+
+### Model Preparation
+```
+pip install -U "huggingface_hub[cli]"
+huggingface-cli download https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B/resolve/main/Wan2.1_VAE.pth ./model_zoo/Wan2.1/base/Wan2.1_VAE.pth
+huggingface-cli download https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B/resolve/main/models_t5_umt5-xxl-enc-bf16.pth ./model_zoo/Wan2.1/base/models_t5_umt5-xxl-enc-bf16.pth
+huggingface-cli download shirley430316/LivePhoto-Wan2.1 --local-dir ./model_zoo/LivePhoto-Wan2.1/
+```
+
+After proper preparation, the directory looks like:
+```
+./model_zoo
+  - LivePhoto-Wan2.1
+    - Wan2.1-T2V-1.3B
+    - base.safetensors
+    - lora.safetensors
+```
+### Usage Example
+#### I2V with Motion Intensity Levels
+```
+# make sure you are in ~/LivePhoto-Wan2.1/PusaV1
+CUDA_VISIBLE_DEVICES=0 python examples/pusavideo/wan_14b_multi_frames_pusa.py \
+  --image_paths "./demos/input_image.jpg" \
+  --prompt "A cute orange kitten with big round eyes stands upright on its hind legs on a smooth wooden floor. The kitten begins to move its tiny front paws up and down rhythmically, swaying its body left and right as if dancing. Its fluffy tail flicks slightly behind it, and the soft lighting creates a warm, cozy indoor atmosphere. The kitten’s ears twitch gently as it keeps its balance, adding to the charm of its playful little dance. The background stays softly blurred, keeping focus on the kitten’s adorable movements." \
+  --cond_position "0" \
+  --noise_multipliers "0" \
+  --dit_path "./model_zoo/Wan2.1/base.safetensors" \
+  --lora_path "./model_zoo/Wan2.1/lora.safetensors" \
+  --lora_alpha 1.2 \
+  --num_inference_steps 30 \
+  --motion_intensity 5 \  # valid motion intensity levels from 1 through 6
+```
+
+### Acknowledgement
+This version is developped on the codebase of [Pusa-VidGen](https://github.com/Yaofang-Liu/Pusa-VidGen). Much appreciation for the insightful project.