Update app.py

app.py

@@ -1,154 +1,68 @@
-import gradio as gr
-import numpy as np
-import random
-
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
 import torch
+import gradio as gr
+from diffusers import StableDiffusionXLPipeline, DPMSolverMultistepScheduler
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
-
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
-
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
-
+# Step 1: Define models
+base_model_sdxl = "stabilityai/stable-diffusion-xl-base-1.0"  
+lora_repo = "freshcodestech/LingoSpace"      
+lora_file = "LingoSpace-10.safetensors"      
 
-# @spaces.GPU #[uncomment to use ZeroGPU]
-def infer(
-    prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
-    width,
-    height,
-    guidance_scale,
-    num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
-):
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
+# Step 2: Load SDXL pipeline
+pipe = StableDiffusionXLPipeline.from_pretrained(
+    base_model_sdxl,
+    torch_dtype=torch.float16,
+    use_safetensors=True
+)
 
-    generator = torch.Generator().manual_seed(seed)
+# Replace scheduler for better quality
+pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
 
-    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]
+# Move to GPU
+pipe = pipe.to("cuda")
 
-    return image, seed
+# Step 3: Load LoRA weights
+pipe.load_lora_weights(lora_repo, weight_name=lora_file)
 
+# LoRA scaling factor (strength)
+lora_strength = 0.8   # Try 0.6–1.0
 
-examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
+# Step 4: Fixed prompts
+prompts = [
+    "A cartoon raccoon in a space suit with some rice food, highly detailed, vibrant, futuristic art style",
+    "A cartoon bear in a space suit with some meat food, cinematic lighting, sci-fi background",
+    "A cartoon giraffe in a space suit with some pizza food, whimsical, colorful, space kitchen scene"
 ]
 
-css = """
-#col-container {
-    margin: 0 auto;
-    max-width: 640px;
-}
-"""
-
-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")
-
-        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",
-                visible=False,
-            )
-
-            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=32,
-                    value=1024,  # 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=[
+# Step 5: Generation settings
+num_steps = 30       # inference steps
+cfg = 7.5            # classifier-free guidance scale
+seed = 12345         # base seed for reproducibility
+
+# Inference function (returns list of images)
+def generate_images():
+    results = []
+    for idx, prompt in enumerate(prompts):
+        generator = torch.manual_seed(seed + idx)  # unique seed for each prompt
+        image = pipe(
             prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
-        ],
-        outputs=[result, seed],
-    )
+            num_inference_steps=num_steps,
+            guidance_scale=cfg,
+            cross_attention_kwargs={"scale": lora_strength},
+            generator=generator,
+            height=1024,
+            width=1024
+        ).images[0]
+        results.append(image)
+    return results
+
+# Step 6: Gradio UI
+demo = gr.Interface(
+    fn=generate_images,
+    inputs=None,
+    outputs=[gr.Image(label=f"Image {i+1}") for i in range(len(prompts))],
+    title="SDXL + LoRA: Cartoon Animals in Space Suits",
+    description="Generates fixed set of images using LoRA fine-tuning."
+)
 
 if __name__ == "__main__":
     demo.launch()