Update app.py

app.py

@@ -1,7 +1,6 @@
 import torch
 import gradio as gr
-from diffusers import AnimateDiffSparseControlNetPipeline, AutoencoderKL, MotionAdapter, SparseControlNetModel, AnimateDiffPipeline, EulerAncestralDiscreteScheduler
-from diffusers.schedulers import DPMSolverMultistepScheduler
+from diffusers import AnimateDiffPipeline, MotionAdapter, DPMSolverMultistepScheduler, AutoencoderKL, EulerAncestralDiscreteScheduler
 from diffusers.utils import export_to_gif, load_image
 
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
@@ -11,8 +10,8 @@ def generate_video(prompt, negative_prompt, num_inference_steps, conditioning_fr
     controlnet = SparseControlNetModel.from_pretrained("guoyww/animatediff-sparsectrl-scribble", torch_dtype=torch.float16).to(device)
     vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse", torch_dtype=torch.float16).to(device)
     
-    pipe = AnimateDiffSparseControlNetPipeline.from_pretrained(
-        "SG161222/Realistic_Vision_V5.1_noVAE",
+    pipe = AnimateDiffPipeline.from_pretrained(
+        "SG161222/Realistic_Vision_V6.0_B1_noVAE",
         motion_adapter=motion_adapter,
         controlnet=controlnet,
         vae=vae,
@@ -59,10 +58,10 @@ def generate_simple_video(prompt):
 
     frames = pipe(
         prompt,
-        num_frames=64,
-        num_inference_steps=50,  # Increased for higher quality
-        guidance_scale=10.0,     # Increased for stronger guidance
-        decode_chunk_size=1,     # Reduced for finer details
+        num_frames=128,  # Increased for smoother video
+        num_inference_steps=100,  # Increased for higher quality
+        guidance_scale=15.0,  # Increased for stronger guidance
+        decode_chunk_size=1,
     ).frames[0]
     
     export_to_gif(frames, "simple_output.gif")
@@ -73,7 +72,7 @@ demo1 = gr.Interface(
     inputs=[
         gr.Textbox(label="Prompt", value="an aerial view of a cyberpunk city, night time, neon lights, masterpiece, high quality"),
         gr.Textbox(label="Negative Prompt", value="low quality, worst quality, letterboxed"),
-        gr.Slider(label="Number of Inference Steps", minimum=1, maximum=100, step=1, value=50),  # Increased default value
+        gr.Slider(label="Number of Inference Steps", minimum=1, maximum=200, step=1, value=100),  # Increased default value
         gr.Textbox(label="Conditioning Frame Indices", value="[0, 8, 15]"),
         gr.Slider(label="ControlNet Conditioning Scale", minimum=0.1, maximum=2.0, step=0.1, value=1.0)
     ],
@@ -92,5 +91,6 @@ demo2 = gr.Interface(
 
 demo = gr.TabbedInterface([demo1, demo2], ["Advanced Video Generation", "Simple Video Generation"])
 
+
 demo.launch()
 #demo.launch(server_name="0.0.0.0", server_port=7910)