test gradio

app.py

@@ -1,4 +1,7 @@
 import gradio as gr
+import torch
+from diffusers import StableDiffusionPipeline, EulerDiscreteScheduler
+import gradio as gr
 from huggingface_hub import login
 import os
 import spaces,tempfile
@@ -14,108 +17,25 @@ import openai,json
 
 token = os.getenv("HF_TOKEN")
 login(token=token)
-openai_token = os.getenv("OPENAI_TOKEN")
-openai.api_key = openai_token
-openaiclient = openai.OpenAI(api_key=openai.api_key)
-
-def ask_gpt(massage_history,model="gpt-4o-mini",return_str=True,response_format={"type": "json_object"}):
-    response = openaiclient.chat.completions.create(
-      model=model,
-      messages=massage_history,
-      response_format=response_format,
-      max_tokens=4000,    )
-
-    if return_str:
-        return response.choices[0].message.content
-    else:
-        return json.loads(response.choices[0].message.content)
-
-
-image_pipeline = AutoPipelineForText2Image.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16).to("cuda")
-image_pipeline.load_ip_adapter("h94/IP-Adapter", subfolder="sdxl_models", weight_name="ip-adapter_sdxl.bin")
-
-
-
-@spaces.GPU
-def generate_image(prompt, reference_image, controlnet_conditioning_scale):
-    style_images = [load_image(f.name) for f in reference_image]
-
-    image_pipeline.set_ip_adapter_scale(controlnet_conditioning_scale)
-
-    image = image_pipeline(
-        prompt=prompt,
-        ip_adapter_image=[style_images],
-        negative_prompt="",
-        guidance_scale=5,
-        num_inference_steps=30,
-    ).images[0]
-
-    return image
-
-model_id = "Lykon/DreamShaper"
-motion_adapter_id = "guoyww/animatediff-motion-adapter-v1-5-3"
-controlnet_id = "guoyww/animatediff-sparsectrl-rgb"
-lora_adapter_id = "guoyww/animatediff-motion-lora-v1-5-3"
-vae_id = "stabilityai/sd-vae-ft-mse"
-device = "cuda"
-
-motion_adapter = MotionAdapter.from_pretrained(motion_adapter_id, torch_dtype=torch.float16).to(device)
-controlnet = SparseControlNetModel.from_pretrained(controlnet_id, torch_dtype=torch.float16).to(device)
-vae = AutoencoderKL.from_pretrained(vae_id, torch_dtype=torch.float16).to(device)
-scheduler = DPMSolverMultistepScheduler.from_pretrained(
-    model_id,
-    subfolder="scheduler",
-    beta_schedule="linear",
-    algorithm_type="dpmsolver++",
-    use_karras_sigmas=True,
-)
-gif_pipe = AnimateDiffSparseControlNetPipeline.from_pretrained(
-    model_id,
-    motion_adapter=motion_adapter,
-    controlnet=controlnet,
-    vae=vae,
-    scheduler=scheduler,
-    torch_dtype=torch.float16,
-).to(device)
-gif_pipe.load_lora_weights(lora_adapter_id, adapter_name="motion_lora")
-
-
-@spaces.GPU
-def generate_gif(prompt, reference_image, controlnet_conditioning_scale,style_conditioning_scale,num_frames):
-    style_image = generate_image(prompt, reference_image, float(style_conditioning_scale))
-
-    video = gif_pipe(
-        prompt=prompt,
-        negative_prompt="low quality, worst quality",
-        num_inference_steps=25,
-        conditioning_frames=[style_image],
-        controlnet_frame_indices=[0],
-        controlnet_conditioning_scale=float(controlnet_conditioning_scale),
-        num_frames=int(num_frames)
-    ).frames[0]
-    export_to_gif(video, "output.gif")
-
-    yield ([style_image], "output.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="Style Scale", minimum=0, maximum=1.0, step=0.1, value=0.6),
-        gr.Slider(label="Number of frames", minimum=0, maximum=100.0, step=1.0, value=10.0),
-
-    ],
-    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."
+model_id = "stabilityai/stable-diffusion-2-base"
+scheduler = EulerDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler")
+pipe = StableDiffusionPipeline.from_pretrained(model_id, scheduler=scheduler, torch_dtype=torch.float16)
 
-)
+lora_path = "Jl-wei/ui-diffuser-v2"
+pipe.load_lora_weights(lora_path)
+pipe.to("cuda")
 
-interface.launch()
 
+def gui_generation(text, num_imgs):
+    prompt = f"Mobile app: {text}"
+    images = pipe(prompt, num_inference_steps=30, guidance_scale=7.5, height=512, width=288, num_images_per_prompt=num_imgs).images
+    yield images
 
+with gr.Blocks() as demo:
+    gallery = gr.Gallery(columns=[3], rows=[1], object_fit="contain", height="auto")
+    number_slider = gr.Slider(1, 30, value=2, step=1, label="Batch size")
+    prompt_box = gr.Textbox(label="Prompt", placeholder="Health monittoring report")
+    gr.Interface(gui_generation, inputs=[prompt_box, number_slider], outputs=gallery)
 
+if __name__ == "__main__":
+    demo.launch()