initial commit

app.py

@@ -0,0 +1,166 @@
+import gradio as gr
+import os
+import spaces
+import torch
+import time
+import json
+from diffusers import BriaFiboPipeline
+from diffusers.modular_pipelines import ModularPipeline
+
+# resolutions=[
+#     "832 1248",
+#     "896 1152",
+#     "960 1088",
+#     "1024 1024",
+#     "1088 960",
+#     "1152 896",
+#     "1216 832",
+#     "1280 800",
+#     "1344 768",
+# ]
+
+dtype = torch.bfloat16
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+torch.set_grad_enabled(False)
+vlm_pipe = ModularPipeline.from_pretrained("briaai/FIBO-VLM-prompt-to-JSON", trust_remote_code=True).to(device)
+
+pipe = BriaFiboPipeline.from_pretrained(
+        "briaai/FIBO",
+        trust_remote_code=True,
+        torch_dtype=dtype).to(device)
+
+
+def handle_json(text):
+    try:
+        json.loads(text)
+        return text 
+    except:
+        return "Error"
+            
+
+@spaces.GPU()
+def infer(prompt,
+          negative_prompt="",
+          seed=42,
+          randomize_seed=False,
+          width=1024,
+          height=1024,
+          guidance_scale=5,
+          num_inference_steps=50,
+         ):
+    
+    if randomize_seed:
+        seed = random.randint(0, MAX_SEED)
+    
+    t=time.time()
+
+    
+    with torch.inference_mode():
+        # 1. Create a prompt to generate an initial image
+        output = vlm_pipe(prompt=prompt)
+        json_prompt_generate = output.values["json_prompt"]
+
+
+        image = pipe(prompt=json_prompt, 
+                                 num_inference_steps=num_inference_steps, 
+                                 negative_prompt=negative_prompt,
+                                 generator=generator,
+                                 width=width,height=height,
+                                 guidance_scale=guidance_scale).images[0]
+
+    
+    
+    return image
+
+css = """
+#col-container{
+    margin: 0 auto;
+    max-width: 750px;
+}
+"""
+with gr.Blocks(css=css) as demo:
+    with gr.Column(elem_id="col-container"):
+        gr.Markdown("## FOBI")
+        
+        with gr.Group():
+            with gr.Column():
+                with gr.Row():
+                    prompt_in = gr.Textbox(label="Prompt")
+                    prompt_in_json = gr.JSON(label="Json")
+
+                with gr.Accordion("Advanced Settings", open=False):
+                    with gr.Row():
+                        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():
+                        guidance_scale = gr.Slider(
+                            label="guidance scale",
+                            minimum=1.0,
+                            maximum=10.0,
+                            step=0.1,
+                            value=5.0
+                        )
+                        num_inference_steps = gr.Slider(
+                            label="number of inference steps",
+                            minimum=1,
+                            maximum=60,
+                            step=1,
+                            value=50,
+                        )
+                        height = gr.Slider(
+                            label="Height",
+                            minimum=768,
+                            maximum=1248,
+                            step=32,
+                            value=1024,
+                        )
+                        
+                        width = gr.Slider(
+                            label="Width",
+                            minimum=832,
+                            maximum=1344,
+                            step=64,
+                            value=1024,
+                        )
+                     with gr.Row():
+                        negative_prompt = gr.Textbox(label="negative prompt", value=json.dumps(''))
+                        negative_prompt_json = gr.JSON(label="json negative prompt", value=json.dumps(''))
+                        
+                
+                
+                submit_btn = gr.Button("Generate")
+        result = gr.Image(label="output")
+
+    prompt_in.change(
+        handle_json, 
+        inputs=prompt_in, 
+        outputs=prompt_in_json)
+
+    negative_prompt.change(handle_json, inputs=negative_prompt, outputs=negative_prompt_json)
+    
+    submit_btn.click(
+        fn = infer,
+        inputs = [
+            prompt_in,
+            negative_prompt,
+            seed,
+            randomize_seed,
+            width,
+            height,
+            guidance_scale,
+            num_inference_steps,
+        ],
+        outputs = [
+            result
+        ]
+    )
+demo.queue().launch()