multi image gen

app.py

@@ -1,27 +1,69 @@
 import gradio as gr
 import numpy as np
 import random
-
-import spaces
-from diffusers import DiffusionPipeline
 import torch
+from diffusers import (
+    DiffusionPipeline, FluxPipeline, PixArtSigmaPipeline,
+    AuraFlowPipeline, Kandinsky3Pipeline, HunyuanDiTPipeline,
+    LuminaText2ImgPipeline
+)
+import spaces
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/stable-diffusion-3.5-large"
-
-if torch.cuda.is_available():
-    torch_dtype = torch.bfloat16
-else:
-    torch_dtype = torch.float32
-
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
-
+# Constants
 MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 1024
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+TORCH_DTYPE = torch.bfloat16 if torch.cuda.is_available() else torch.float32
+
+# Model configurations
+MODEL_CONFIGS = {
+    "Stable Diffusion 3.5": {
+        "repo_id": "stabilityai/stable-diffusion-3.5-large",
+        "pipeline_class": DiffusionPipeline
+    },
+    "FLUX": {
+        "repo_id": "black-forest-labs/FLUX.1-dev",
+        "pipeline_class": FluxPipeline
+    },
+    "PixArt": {
+        "repo_id": "PixArt-alpha/PixArt-Sigma-XL-2-1024-MS",
+        "pipeline_class": PixArtSigmaPipeline
+    },
+    "AuraFlow": {
+        "repo_id": "fal/AuraFlow",
+        "pipeline_class": AuraFlowPipeline
+    },
+    "Kandinsky": {
+        "repo_id": "kandinsky-community/kandinsky-3",
+        "pipeline_class": Kandinsky3Pipeline
+    },
+    "Hunyuan": {
+        "repo_id": "Tencent-Hunyuan/HunyuanDiT-Diffusers",
+        "pipeline_class": HunyuanDiTPipeline
+    },
+    "Lumina": {
+        "repo_id": "Alpha-VLLM/Lumina-Next-SFT-diffusers",
+        "pipeline_class": LuminaText2ImgPipeline
+    }
+}
 
-@spaces.GPU(duration=65)
-def infer(
+# Initialize model pipelines
+pipes = {}
+
+def load_pipeline(model_name):
+    config = MODEL_CONFIGS[model_name]
+    pipe = config["pipeline_class"].from_pretrained(
+        config["repo_id"],
+        torch_dtype=TORCH_DTYPE
+    )
+    pipe = pipe.to(DEVICE)
+    if hasattr(pipe, 'enable_model_cpu_offload'):
+        pipe.enable_model_cpu_offload()
+    return pipe
+
+@spaces.GPU(duration=180)
+def generate_image(
+    model_name,
     prompt,
     negative_prompt="",
     seed=42,
@@ -30,13 +72,23 @@ def infer(
     height=1024,
     guidance_scale=4.5,
     num_inference_steps=40,
-    progress=gr.Progress(track_tqdm=True),
+    progress=gr.Progress(track_tqdm=True)
 ):
+    progress(0, desc=f"Loading {model_name} model...")
+    
+    # Load model if not already loaded
+    if model_name not in pipes:
+        pipes[model_name] = load_pipeline(model_name)
+    
+    pipe = pipes[model_name]
+    
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
-
-    generator = torch.Generator().manual_seed(seed)
-
+    
+    generator = torch.Generator(DEVICE).manual_seed(seed)
+    
+    progress(0.3, desc=f"Generating image with {model_name}...")
+    
     image = pipe(
         prompt=prompt,
         negative_prompt=negative_prompt,
@@ -46,25 +98,22 @@ def infer(
         height=height,
         generator=generator,
     ).images[0]
-
+    
+    progress(1.0, desc=f"Generation complete with {model_name}")
     return image, seed
 
-
-examples = [
-        "A capybara wearing a suit holding a sign that reads Hello World",
-]
-
+# Gradio Interface
 css = """
 #col-container {
     margin: 0 auto;
-    max-width: 640px;
+    max-width: 1024px;
 }
 """
 
 with gr.Blocks(css=css) as demo:
     with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # [Stable Diffusion 3.5 Large (8B)](https://huggingface.co/stabilityai/stable-diffusion-3.5-large)")
-        gr.Markdown("[Learn more](https://stability.ai/news/introducing-stable-diffusion-3-5) about the Stable Diffusion 3.5 series. Try on [Stability AI API](https://platform.stability.ai/docs/api-reference#tag/Generate/paths/~1v2beta~1stable-image~1generate~1sd3/post), or [download model](https://huggingface.co/stabilityai/stable-diffusion-3.5-large) to run locally with ComfyUI or diffusers.")
+        gr.Markdown("# Multi-Model Image Generation")
+        
         with gr.Row():
             prompt = gr.Text(
                 label="Prompt",
@@ -73,19 +122,15 @@ with gr.Blocks(css=css) as demo:
                 placeholder="Enter your prompt",
                 container=False,
             )
-
-            run_button = gr.Button("Run", scale=0, variant="primary")
-
-        result = gr.Image(label="Result", show_label=False)
-
+            run_button = gr.Button("Generate", scale=0, variant="primary")
+        
         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,
@@ -93,18 +138,17 @@ with gr.Blocks(css=css) as demo:
                 step=1,
                 value=0,
             )
-
+            
             randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-
+            
             with gr.Row():
                 width = gr.Slider(
                     label="Width",
                     minimum=512,
                     maximum=MAX_IMAGE_SIZE,
                     step=32,
-                    value=1024, 
+                    value=1024,
                 )
-
                 height = gr.Slider(
                     label="Height",
                     minimum=512,
@@ -112,7 +156,7 @@ with gr.Blocks(css=css) as demo:
                     step=32,
                     value=1024,
                 )
-
+            
             with gr.Row():
                 guidance_scale = gr.Slider(
                     label="Guidance scale",
@@ -121,19 +165,52 @@ with gr.Blocks(css=css) as demo:
                     step=0.1,
                     value=4.5,
                 )
-
                 num_inference_steps = gr.Slider(
                     label="Number of inference steps",
                     minimum=1,
                     maximum=50,
                     step=1,
-                    value=40, 
+                    value=40,
                 )
-
-        gr.Examples(examples=examples, inputs=[prompt], outputs=[result, seed], fn=infer, cache_examples=True, cache_mode="lazy")
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
+        
+        # Create tabs for each model
+        with gr.Tabs() as tabs:
+            results = {}
+            seeds = {}
+            for model_name in MODEL_CONFIGS.keys():
+                with gr.Tab(model_name):
+                    results[model_name] = gr.Image(label=f"{model_name} Result")
+                    seeds[model_name] = gr.Number(label="Seed used", visible=False)
+        
+        examples = [
+            "A capybara wearing a suit holding a sign that reads Hello World",
+            "A serene landscape with mountains and a lake at sunset",
+        ]
+        gr.Examples(examples=examples, inputs=[prompt])
+
+    # Handle generation for each model
+    def generate_all(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, progress=gr.Progress()):
+        outputs = []
+        for model_name in MODEL_CONFIGS.keys():
+            try:
+                image, used_seed = generate_image(
+                    model_name, prompt, negative_prompt, seed,
+                    randomize_seed, width, height, guidance_scale,
+                    num_inference_steps, progress
+                )
+                outputs.extend([image, used_seed])
+            except Exception as e:
+                outputs.extend([None, None])
+                print(f"Error generating with {model_name}: {str(e)}")
+        return outputs
+
+    # Set up the generation trigger
+    output_components = []
+    for model_name in MODEL_CONFIGS.keys():
+        output_components.extend([results[model_name], seeds[model_name]])
+
+    run_button.click(
+        fn=generate_all,
         inputs=[
             prompt,
             negative_prompt,
@@ -144,8 +221,8 @@ with gr.Blocks(css=css) as demo:
             guidance_scale,
             num_inference_steps,
         ],
-        outputs=[result, seed],
+        outputs=output_components,
     )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()