Update app.py

app.py

@@ -1,159 +1,132 @@
 import gradio as gr
-import numpy as np
-import random
-
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
 import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+MODEL_ID = "lazarus19/AuroraImageGen"
 
+# Device setup
 device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "lazarus19/AuroraImageGen"  # Replace to the model you would like to use
+torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
 
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 
-pipe = DiffusionPipeline.from_pretrained(
-    model_repo_id,
-    torch_dtype=torch.float16
+# Load model
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID,
+    torch_dtype=torch_dtype,
+    device_map="auto"
 )
 
-pipe.enable_model_cpu_offload()
-pipe = pipe.to(device)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
-
-
-# @spaces.GPU #[uncomment to use ZeroGPU]
-def infer(
+# Generate function
+def generate(
     prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
-    width,
-    height,
-    guidance_scale,
-    num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
+    max_new_tokens,
+    temperature,
+    top_p,
 ):
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-
-    generator = torch.Generator(device=device).manual_seed(seed)
+    if not prompt.strip():
+        return "Please enter a prompt."
 
-    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]
+    inputs = tokenizer(
+        prompt,
+        return_tensors="pt"
+    )
 
-    return image, seed
+    inputs = {k: v.to(model.device) for k, v in inputs.items()}
+
+    with torch.no_grad():
+        outputs = model.generate(
+            **inputs,
+            max_new_tokens=max_new_tokens,
+            temperature=temperature,
+            top_p=top_p,
+            do_sample=True,
+            pad_token_id=tokenizer.eos_token_id,
+        )
+
+    response = tokenizer.decode(
+        outputs[0],
+        skip_special_tokens=True
+    )
 
+    return response
 
 examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
+    "Write a short story about a robot explorer.",
+    "Explain quantum computing in simple terms.",
+    "Create a fantasy character profile.",
 ]
 
 css = """
 #col-container {
     margin: 0 auto;
-    max-width: 640px;
+    max-width: 900px;
 }
 """
 
 with gr.Blocks(css=css) as demo:
     with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # Text-to-Image Gradio Template")
-
-        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, variant="primary")
+        gr.Markdown("# AuroraImageGen Chat")
 
-        result = gr.Image(label="Result", show_label=False)
+        prompt = gr.Textbox(
+            label="Prompt",
+            lines=6,
+            placeholder="Enter your prompt..."
+        )
+
+        output = gr.Textbox(
+            label="Response",
+            lines=20
+        )
 
         with gr.Accordion("Advanced Settings", open=False):
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
+
+            max_new_tokens = gr.Slider(
+                minimum=32,
+                maximum=2048,
+                value=512,
+                step=32,
+                label="Max New Tokens"
             )
 
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
+            temperature = gr.Slider(
+                minimum=0.1,
+                maximum=2.0,
+                value=0.7,
+                step=0.1,
+                label="Temperature"
             )
 
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-
-            with gr.Row():
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=512,  # Replace with defaults that work for your model
-                )
-
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
-                )
-
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=2,  # Replace with defaults that work for your model
-                )
-
-        gr.Examples(examples=examples, inputs=[prompt])
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
-        inputs=[
-            prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
-        ],
-        outputs=[result, seed],
-    )
+            top_p = gr.Slider(
+                minimum=0.1,
+                maximum=1.0,
+                value=0.9,
+                step=0.05,
+                label="Top-P"
+            )
+
+        run_button = gr.Button(
+            "Generate",
+            variant="primary"
+        )
+
+        gr.Examples(
+            examples=examples,
+            inputs=[prompt]
+        )
+
+        run_button.click(
+            fn=generate,
+            inputs=[
+                prompt,
+                max_new_tokens,
+                temperature,
+                top_p,
+            ],
+            outputs=output,
+        )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()