Initial commit of Wan2.1 Text-to-Video model

.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
+Wan2.1/checkpoints/* filter=lfs diff=lfs merge=lfs -text

Wan2.1

@@ -0,0 +1 @@
+Subproject commit 9fb884500990c22bf8527ca057010f94b2445fd2

app.py

@@ -0,0 +1,25 @@
+import gradio as gr
+import torch
+from Wan2.1.wan.pipeline import WanPipeline
+
+# Initialize the pipeline
+pipe = WanPipeline(
+    model_dir="Wan2.1/checkpoints",
+    device="cuda" if torch.cuda.is_available() else "cpu"
+)
+
+def generate_video(prompt):
+    video_frames = pipe.generate(prompt)
+    return video_frames
+
+# Gradio interface
+iface = gr.Interface(
+    fn=generate_video,
+    inputs=gr.Textbox(label="Prompt"),
+    outputs=gr.Video(label="Generated Video"),
+    title="Wan2.1 Text-to-Video Generation",
+    description="Generate videos from text prompts using the Wan2.1 model."
+)
+
+if __name__ == "__main__":
+    iface.launch()

requirements.txt

@@ -0,0 +1,5 @@
+torch>=1.13.0
+transformers
+einops
+accelerate
+gradio