Update app.py

app.py

@@ -1,63 +1,138 @@
+import spaces
 import gradio as gr
-from huggingface_hub import InferenceClient
+import numpy as np
+import random
+import torch
+from diffusers import StableDiffusion3Pipeline, SD3Transformer2DModel, FlowMatchEulerDiscreteScheduler
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+device = "cuda" if torch.cuda.is_available() else "cpu"
+dtype = torch.float16
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+repo = "Infinirc/stable-diffusion-3-medium-diffusers"
+pipe = StableDiffusion3Pipeline.from_pretrained(repo, torch_dtype=torch.float16).to(device)
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+MAX_SEED = np.iinfo(np.int32).max
+MAX_IMAGE_SIZE = 1920
 
-    messages.append({"role": "user", "content": message})
+@spaces.GPU
+def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, progress=gr.Progress(track_tqdm=True)):
 
-    response = ""
+    if randomize_seed:
+        seed = random.randint(0, MAX_SEED)
+        
+    generator = torch.Generator().manual_seed(seed)
+    
+    image = pipe(
+        prompt = prompt, 
+        negative_prompt = negative_prompt,
+        guidance_scale = guidance_scale, 
+        num_inference_steps = num_inference_steps, 
+        width = width, 
+        height = height,
+        generator = generator
+    ).images[0] 
+    
+    return image, seed
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+examples = [
+    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
+    "An astronaut riding a green horse",
+    "A delicious ceviche cheesecake slice",
+]
 
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+css="""
+#col-container {
+    margin: 0 auto;
+    max-width: 580px;
+}
 """
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+
+with gr.Blocks(css=css) as demo:
+    
+    with gr.Column(elem_id="col-container"):
+        gr.Markdown(f"""
+        # Infinirc [Stable Diffusion 3 Medium](https://huggingface.co/Infinirc/stable-diffusion-3-medium-diffusers)
+        [HuggingFace](https://huggingface.co/Infinirc)
+        """)
+        
+        with gr.Row():
+            
+            prompt = gr.Text(
+                label="Prompt",
+                show_label=False,
+                max_lines=1,
+                placeholder="Enter your prompt",
+                container=False,
+            )
+            
+            run_button = gr.Button("Run", scale=0)
+        
+        result = gr.Image(label="Result", show_label=False)
+
+        with gr.Accordion("Advanced Settings", open=False):
+            
+            negative_prompt = gr.Text(
+                label="Negative prompt",
+                max_lines=1,
+                placeholder="Enter a negative prompt",
+            )
+            
+            seed = gr.Slider(
+                label="Seed",
+                minimum=0,
+                maximum=MAX_SEED,
+                step=1,
+                value=0,
+            )
+            
+            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+            
+            with gr.Row():
+                
+                width = gr.Slider(
+                    label="Width",
+                    minimum=256,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=64,
+                    value=1024,
+                )
+                
+                height = gr.Slider(
+                    label="Height",
+                    minimum=256,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=64,
+                    value=1024,
+                )
+            
+            with gr.Row():
+                
+                guidance_scale = gr.Slider(
+                    label="Guidance scale",
+                    minimum=0.0,
+                    maximum=10.0,
+                    step=0.1,
+                    value=5.0,
+                )
+                
+                num_inference_steps = gr.Slider(
+                    label="Number of inference steps",
+                    minimum=1,
+                    maximum=50,
+                    step=1,
+                    value=12,
+                )
+        
+        gr.Examples(
+            examples = examples,
+            inputs = [prompt]
+        )
+    gr.on(
+        triggers=[run_button.click, prompt.submit, negative_prompt.submit],
+        fn = infer,
+        inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
+        outputs = [result, seed]
+    )
+
+demo.launch()