Update app.py

app.py

@@ -1,28 +1,28 @@
-# app.py for Hugging Face Space
+import torch
+from diffusers.utils import export_to_video
+from diffusers import AutoencoderKLWan, WanPipeline
+from diffusers.schedulers.scheduling_unipc_multistep import UniPCMultistepScheduler
 
-import gradio as gr
-from transformers import GPT2LMHeadModel, GPT2Tokenizer
-from huggingface_hub import login
+model_id = "Wan-AI/Wan2.1-T2V-14B-Diffusers"
+vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
+pipe = WanPipeline.from_pretrained(model_id, vae=vae, torch_dtype=torch.bfloat16)
+flow_shift = 3.0  # 5.0 for 720P, 3.0 for 480P
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=flow_shift)
+pipe.to("cuda")
 
-# Load the fine-tuned model from Hugging Face Model Hub
-model_name = "rahul7star/Rahul-FineTunedLLM-v03"  # Replace with-- yuuour model's path on Hugging Face Hub
-tokenizer = GPT2Tokenizer.from_pretrained(model_name)
-model = GPT2LMHeadModel.from_pretrained(model_name)
+pipe.load_lora_weights("noahsolomon/wan2.1-yumemono")
 
-# Function to generate a response based on user input
-def generate_response(query):
-    inputs = tokenizer(query, return_tensors="pt")
-    outputs = model.generate(**inputs)
-    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+pipe.enable_model_cpu_offload() #for low-vram environments
 
-# Gradio Interface
-interface = gr.Interface(
-    fn=generate_response,
-    inputs=gr.Textbox(label="Enter a query"),
-    outputs=gr.Textbox(label="Model Response"),
-    title="Fine-Tuned GPT-2 Model",
-    description="This model generates responses based on user input. It was fine-tuned with real-time web search data."
-)
+prompt = "Yumemono"
+negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards"
 
-# Launch the Gradio interface
-interface.launch()
+output = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=480,
+    width=832,
+    num_frames=81,
+    guidance_scale=5.0,
+).frames[0]
+export_to_video(output, "output.mp4", fps=16)