test gradio

app.py

@@ -3,7 +3,7 @@ from huggingface_hub import login
 import os
 import spaces,tempfile
 import torch
-from diffusers import AnimateDiffSparseControlNetPipeline
+from diffusers import AnimateDiffControlNetPipeline
 from diffusers.models import AutoencoderKL, MotionAdapter, SparseControlNetModel
 from diffusers.schedulers import DPMSolverMultistepScheduler
 from diffusers.utils import export_to_gif, load_image
@@ -68,7 +68,7 @@ scheduler = DPMSolverMultistepScheduler.from_pretrained(
     algorithm_type="dpmsolver++",
     use_karras_sigmas=True,
 )
-gif_pipe = AnimateDiffSparseControlNetPipeline.from_pretrained(
+gif_pipe = AnimateDiffControlNetPipeline.from_pretrained(
     model_id,
     motion_adapter=motion_adapter,
     controlnet=controlnet,
@@ -160,7 +160,7 @@ This way, each frame represents a distinct scene, and there’s no redundancy be
     ).frames[0]
     export_to_gif(video, "output.gif")
 
-    return "animation.gif"
+    return conditioning_frames,"animation.gif"
 
 # Set up Gradio interface
 interface = gr.Interface(
@@ -173,7 +173,7 @@ interface = gr.Interface(
         gr.Slider(label="Number of frames", minimum=0, maximum=100.0, step=1.0, value=10.0),
 
     ],
-    outputs="image",
+    outputs=["gallery","image"],
     title="Image Generation with Stable Diffusion 3 medium and ControlNet",
     description="Generates an image based on a text prompt and a reference image using Stable Diffusion 3 medium with ControlNet."