test gradio

app.py

@@ -1,58 +1,44 @@
 import gradio as gr
 import torch
-from diffusers import AnimateDiffPipeline, DDIMScheduler, MotionAdapter
-from diffusers.utils import export_to_gif
+from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
 
-# Set device to CPU
-device = torch.device("cpu")
+# Load Stable Diffusion model and ControlNet reference-only model
+model_id = "runwayml/stable-diffusion-v1-5"
+controlnet_id = "lllyasviel/control_v11p_sd15_inpaint"  # Use an appropriate ControlNet variant
 
-# Load the motion adapter on CPU
-adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-2", torch_dtype=torch.float32).to(device)
-model_id = "SG161222/Realistic_Vision_V5.1_noVAE"
-pipe = AnimateDiffPipeline.from_pretrained(
-    model_id, motion_adapter=adapter, torch_dtype=torch.float32
-).to(device)
-
-scheduler = DDIMScheduler.from_pretrained(
+# Initialize the pipeline on CPU
+controlnet = ControlNetModel.from_pretrained(controlnet_id, torch_dtype=torch.float32)
+pipeline = StableDiffusionControlNetPipeline.from_pretrained(
     model_id,
-    subfolder="scheduler",
-    clip_sample=False,
-    timestep_spacing="linspace",
-    beta_schedule="linear",
-    steps_offset=1,
-)
-pipe.scheduler = scheduler
-
-pipe.enable_vae_slicing()
+    controlnet=controlnet,
+    torch_dtype=torch.float32
+).to("cpu")
 
-# Define the animation function
-def generate_animation(prompt, negative_prompt, num_frames, guidance_scale, num_inference_steps):
-    output = pipe(
+# Define the Gradio interface function
+def generate_image(prompt, reference_image):
+    # Process reference image
+    reference_image = reference_image.resize((512, 512))
+    # Generate image with reference-only style transfer
+    generated_image = pipeline(
         prompt=prompt,
-        negative_prompt=negative_prompt,
-        num_frames=num_frames,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        generator=torch.Generator("cpu").manual_seed(42),
-    )
-    frames = output.frames[0]
-    gif_path = "animation.gif"
-    export_to_gif(frames, gif_path)
-    return gif_path
+        image=reference_image,
+        controlnet_conditioning_scale=1.0,
+        guidance_scale=7.5,
+        num_inference_steps=50
+    ).images[0]
+    return generated_image
 
-# Gradio Interface
-iface = gr.Interface(
-    fn=generate_animation,
+# Set up Gradio interface
+interface = gr.Interface(
+    fn=generate_image,
     inputs=[
-        gr.Textbox(value="masterpiece, best quality, highly detailed...", label="Prompt"),
-        gr.Textbox(value="bad quality, worse quality", label="Negative Prompt"),
-        gr.Slider(1, 24, value=16, label="Number of Frames"),
-        gr.Slider(1.0, 10.0, value=7.5, step=0.1, label="Guidance Scale"),
-        gr.Slider(1, 50, value=25, label="Inference Steps"),
+        gr.Textbox(label="Prompt"),
+        gr.Image(type="pil", label="Reference Image (Style)")
     ],
-    outputs=gr.Image(label="Generated Animation"),
-    title="Animated Stable Diffusion",
-    description="Generate animations based on your prompt using Stable Diffusion.",
+    outputs="image",
+    title="Image Generation with Reference-Only Style Transfer",
+    description="Generate an image based on a text prompt and style reference image using Stable Diffusion 3.5 with ControlNet (reference-only mode)."
 )
 
-iface.launch()
+# Launch the Gradio interface
+interface.launch()