Create app.py

app.py

@@ -0,0 +1,154 @@
+import gradio as gr
+import numpy as np
+import random
+import spaces #[uncomment to use ZeroGPU]
+from diffusers import ChromaPipeline
+import torch
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model_repo_id = "lodestones/Chroma1-HD"
+
+if torch.cuda.is_available():
+    torch_dtype = torch.bfloat16
+else:
+    torch_dtype = torch.float32
+
+pipe = ChromaPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
+pipe = pipe.to(device)
+
+MAX_SEED = np.iinfo(np.int32).max
+MAX_IMAGE_SIZE = 1024
+
+@spaces.GPU(duration=75) #[uncomment to use ZeroGPU]
+def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, lora_model, progress=gr.Progress(track_tqdm=True)):
+
+    if randomize_seed:
+        seed = random.randint(0, MAX_SEED)
+        
+    generator = torch.Generator(device).manual_seed(seed)
+    
+    # Handle LoRA if needed (ChromaPipeline may not support LoRA by default)
+    # Uncomment and adapt if LoRA support is available
+    # if lora_model: 
+    #     pipe.load_lora_weights(lora_model)
+        
+    image = pipe(
+        prompt=prompt, 
+        negative_prompt=negative_prompt,
+        guidance_scale=guidance_scale, 
+        num_inference_steps=num_inference_steps, 
+        width=width, 
+        height=height,
+        generator=generator,
+        num_images_per_prompt=1
+    ).images[0] 
+    
+    return image, seed
+
+examples = [
+    "A high-fashion close-up portrait of a blonde woman in clear sunglasses. The image uses a bold teal and red color split for dramatic lighting. The background is a simple teal-green. The photo is sharp and well-composed, and is designed for viewing with anaglyph 3D glasses for optimal effect. It looks professionally done.",
+    "A surreal landscape with vibrant red and cyan color separation, featuring mountains and a lake, optimized for anaglyph 3D viewing",
+    "A futuristic cityscape at night with neon lights, rendered in stereoscopic 3D style with red-cyan color separation",
+]
+
+css="""
+#col-container {
+    margin: 0 auto;
+    max-width: 760px;
+}
+#button{
+    align-self: stretch;
+}
+"""
+
+with gr.Blocks(css=css) as demo:
+    
+    with gr.Column(elem_id="col-container"):
+        gr.Markdown(f"""
+        # Chroma1-HD - Anaglyph 3D Image Generation
+        Generate stereoscopic 3D images optimized for red-cyan anaglyph glasses
+        """)
+        
+        with gr.Row():
+            prompt = gr.Text(
+                label="Prompt",
+                max_lines=1,
+                placeholder="Enter your prompt",
+            )
+            negative_prompt = gr.Text(
+                label="Negative prompt",
+                max_lines=1,
+                placeholder="Enter a negative prompt",
+                value="low quality, ugly, unfinished, out of focus, deformed, disfigure, blurry, smudged, restricted palette, flat colors"
+            )
+        
+        with gr.Row():
+            run_button = gr.Button("Run", scale=1, elem_id="button")
+        
+        result = gr.Image(label="Result", show_label=False)
+
+        with gr.Accordion("Advanced Settings", open=False):
+            
+            lora_model = gr.Textbox(
+                label="LoRA model id (if supported)", 
+                placeholder="Leave empty if not using LoRA",
+                visible=False  # Hidden by default as ChromaPipeline may not support LoRA
+            )
+            
+            guidance_scale = gr.Slider(
+                label="Guidance Scale",
+                minimum=1.0,
+                maximum=10.0,
+                step=0.1,
+                value=3.0,  # Default from your example
+            )
+            
+            seed = gr.Slider(
+                label="Seed",
+                minimum=0,
+                maximum=MAX_SEED,
+                step=1,
+                value=433,  # Using the seed from your example
+            )
+            
+            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,  # Default resolution
+                )
+                
+                height = gr.Slider(
+                    label="Height",
+                    minimum=256,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=32,
+                    value=1024,  # Default resolution
+                )
+            
+            num_inference_steps = gr.Slider(
+                label="Number of inference steps",
+                minimum=1,
+                maximum=100,
+                step=1,
+                value=40,  # Default from your example
+            )
+        
+        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, lora_model],
+        outputs=[result, seed]
+    )
+
+demo.queue().launch()