Create app.py

app.py

@@ -0,0 +1,157 @@
+import gradio as gr
+import torch
+from diffusers import StableDiffusionXLPipeline, AutoencoderKL
+from blora_utils import BLOCKS, filter_lora, scale_lora
+
+vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
+pipeline = StableDiffusionXLPipeline.from_pretrained(
+        "stabilityai/stable-diffusion-xl-base-1.0",
+        vae=vae,
+        torch_dtype=torch.float16,
+    ).to("cuda")
+
+def load_b_lora_to_unet(pipe, content_lora_model_id: str = '', style_lora_model_id: str = '', content_alpha: float = 1.,
+                            style_alpha: float = 1.) -> None:
+        try:
+            # Get Content B-LoRA SD
+            if content_lora_model_id:
+                content_B_LoRA_sd, _ = pipe.lora_state_dict(content_lora_model_id)
+                content_B_LoRA = filter_lora(content_B_LoRA_sd, BLOCKS['content'])
+                content_B_LoRA = scale_lora(content_B_LoRA, content_alpha)
+            else:
+                content_B_LoRA = {}
+
+            # Get Style B-LoRA SD
+            if style_lora_model_id:
+                style_B_LoRA_sd, _ = pipe.lora_state_dict(style_lora_model_id)
+                style_B_LoRA = filter_lora(style_B_LoRA_sd, BLOCKS['style'])
+                style_B_LoRA = scale_lora(style_B_LoRA, style_alpha)
+            else:
+                style_B_LoRA = {}
+
+            # Merge B-LoRAs SD
+            res_lora = {**content_B_LoRA, **style_B_LoRA}
+
+            # Load
+            pipe.load_lora_into_unet(res_lora, None, pipe.unet)
+        except Exception as e:
+            raise type(e)(f'failed to load_b_lora_to_unet, due to: {e}')
+
+def main(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps):
+    content_B_LoRA_path = ''
+    style_B_LoRA_path = 'fffiloni/b_lora_trained_test_7'
+    content_alpha,style_alpha = 1,1.1
+
+    load_b_lora_to_unet(pipeline, content_B_LoRA_path, style_B_LoRA_path, content_alpha, style_alpha)
+    prompt = 'An eagle in [v42] style'
+    image = pipeline(
+        prompt,
+        generator=torch.Generator(device="cuda").manual_seed(48), 
+        num_images_per_prompt=1
+    ).images[0].resize((512,512))
+    
+    pipeline.unload_lora_weights()
+    
+    return image
+
+css="""
+#col-container {
+    margin: 0 auto;
+    max-width: 520px;
+}
+"""
+
+if torch.cuda.is_available():
+    power_device = "GPU"
+else:
+    power_device = "CPU"
+
+with gr.Blocks(css=css) as demo:
+    
+    with gr.Column(elem_id="col-container"):
+        gr.Markdown(f"""
+        # Text-to-Image Gradio Template
+        Currently running on {power_device}.
+        """)
+        
+        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",
+                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=512,
+                )
+                
+                height = gr.Slider(
+                    label="Height",
+                    minimum=256,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=32,
+                    value=512,
+                )
+            
+            with gr.Row():
+                
+                guidance_scale = gr.Slider(
+                    label="Guidance scale",
+                    minimum=0.0,
+                    maximum=10.0,
+                    step=0.1,
+                    value=0.0,
+                )
+                
+                num_inference_steps = gr.Slider(
+                    label="Number of inference steps",
+                    minimum=1,
+                    maximum=50,
+                    step=1,
+                    value=50,
+                )
+        
+        gr.Examples(
+            examples = examples,
+            inputs = [prompt]
+        )
+
+    run_button.click(
+        fn = main,
+        inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
+        outputs = [result]
+    )
+
+demo.queue().launch()