Upload 2 files

app.py

@@ -0,0 +1,155 @@
+import gradio as gr
+import numpy as np
+import random
+import spaces
+import torch
+from diffusers.pipelines.prx import PRXPipeline
+
+dtype = torch.bfloat16
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+# Load the PRX pipeline with the distilled DC-AE model
+pipe = PRXPipeline.from_pretrained(
+    "Photoroom/prx-512-t2i-dc-ae-sft-distilled",
+    torch_dtype=dtype
+)
+pipe = pipe.to(device)
+
+MAX_SEED = np.iinfo(np.int32).max
+MAX_IMAGE_SIZE = 1024
+
+
+@spaces.GPU()
+def infer(
+    prompt,
+    seed=42,
+    randomize_seed=False,
+    width=512,
+    height=512,
+    num_inference_steps=8,
+    guidance_scale=1.0,
+    progress=gr.Progress(track_tqdm=True)
+):
+    if randomize_seed:
+        seed = random.randint(0, MAX_SEED)
+
+    generator = torch.Generator(device=device).manual_seed(seed)
+
+    image = pipe(
+        prompt=prompt,
+        width=width,
+        height=height,
+        num_inference_steps=num_inference_steps,
+        generator=generator,
+        guidance_scale=guidance_scale,
+    ).images[0]
+
+    return image, seed
+
+
+examples = [
+    "A front-facing portrait of a lion on the golden savanna at sunset.",
+    "A serene mountain landscape with a crystal clear lake reflecting snow-capped peaks.",
+    "A futuristic cityscape at night with neon lights and flying vehicles.",
+    "A whimsical illustration of a cat wearing a wizard hat and casting spells.",
+    "A cozy coffee shop interior with warm lighting and plants on the windowsill.",
+]
+
+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("# PRX Image Generator")
+        gr.Markdown(
+            "Generate high-quality images using the PRX distilled model with DC-AE compression. "
+            "This model uses 8-step distillation for fast inference with cfg=1.0. "
+            "Works best with less detailed prompts in natural language."
+        )
+
+        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):
+            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():
+                num_inference_steps = gr.Slider(
+                    label="Number of inference steps",
+                    minimum=1,
+                    maximum=28,
+                    step=1,
+                    value=8,
+                )
+
+                guidance_scale = gr.Slider(
+                    label="Guidance scale",
+                    minimum=0.0,
+                    maximum=5.0,
+                    step=0.1,
+                    value=1.0,
+                )
+
+        gr.Examples(
+            examples=examples,
+            fn=infer,
+            inputs=[prompt],
+            outputs=[result, seed],
+            cache_examples="lazy"
+        )
+
+    gr.on(
+        triggers=[run_button.click, prompt.submit],
+        fn=infer,
+        inputs=[
+            prompt,
+            seed,
+            randomize_seed,
+            width,
+            height,
+            num_inference_steps,
+            guidance_scale,
+        ],
+        outputs=[result, seed]
+    )
+
+demo.launch()

requirements.txt

@@ -0,0 +1,7 @@
+accelerate
+diffusers
+torch
+transformers
+sentencepiece
+spaces
+ftfy