test gradio

app.py

@@ -77,6 +77,7 @@ gif_pipe = AnimateDiffSparseControlNetPipeline.from_pretrained(
     torch_dtype=torch.float16,
 ).to(device)
 gif_pipe.load_lora_weights(lora_adapter_id, adapter_name="motion_lora")
+gif_pipe.enable_free_noise(context_length=16, context_stride=4)
 
 
 
@@ -143,12 +144,14 @@ This way, each frame represents a distinct scene, and there’s no redundancy be
     frames = ask_gpt(massage_history,return_str=False)['frames']
     conditioning_frames = []
     controlnet_frame_indices =[]
+    long_prompt = {}
     for frame in frames:
         conditioning_frames.append(generate_image(frame['description'], reference_image, float(controlnet_conditioning_scale)))
         controlnet_frame_indices.append(frame['frame_index'])
+        long_prompt[frame['frame_index']] = frame['description']
 
     video = gif_pipe(
-        prompt=prompt,
+        prompt=long_prompt,
         negative_prompt="low quality, worst quality",
         num_inference_steps=25,
         conditioning_frames=conditioning_frames,
@@ -159,9 +162,26 @@ This way, each frame represents a distinct scene, and there’s no redundancy be
 
     return "animation.gif"
 
+# Set up Gradio interface
+interface = gr.Interface(
+    fn=generate_gif,
+    inputs=[
+        gr.Textbox(label="Prompt"),
+        # gr.Image( type= "filepath",label="Reference Image (Style)"),
+        gr.File(type="filepath",file_count="multiple",label="Reference Image (Style)"),
+        gr.Slider(label="Control Net Conditioning Scale", minimum=0, maximum=1.0, step=0.1, value=1.0),
+        gr.Slider(label="Number of frames", minimum=0, maximum=100.0, step=1.0, value=10.0),
+
+    ],
+    outputs="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."
+
+)
+
 # # Set up Gradio interface
 # interface = gr.Interface(
-#     fn=generate_gif,
+#     fn=generate_frames,
 #     inputs=[
 #         gr.Textbox(label="Prompt"),
 #         # gr.Image( type= "filepath",label="Reference Image (Style)"),
@@ -170,29 +190,12 @@ This way, each frame represents a distinct scene, and there’s no redundancy be
 #         gr.Slider(label="Number of frames", minimum=0, maximum=1.0, step=0.1, value=1.0),
 #
 #     ],
-#     outputs="image",
+#     outputs="gallery",
 #     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."
 #
 # )
 
-# Set up Gradio interface
-interface = gr.Interface(
-    fn=generate_frames,
-    inputs=[
-        gr.Textbox(label="Prompt"),
-        # gr.Image( type= "filepath",label="Reference Image (Style)"),
-        gr.File(type="filepath",file_count="multiple",label="Reference Image (Style)"),
-        gr.Slider(label="Control Net Conditioning Scale", minimum=0, maximum=1.0, step=0.1, value=1.0),
-        gr.Slider(label="Number of frames", minimum=0, maximum=1.0, step=0.1, value=1.0),
-
-    ],
-    outputs="gallery",
-    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."
-
-)
-
 interface.launch()