Create app.py

app.py

@@ -0,0 +1,134 @@
+from __future__ import annotations
+import math
+import random
+import gradio as gr
+import numpy as np
+import torch
+from PIL import Image
+from diffusers import StableDiffusionXLImg2ImgPipeline, EDMEulerScheduler, AutoencoderKL, DPMSolverMultistepScheduler
+from huggingface_hub import hf_hub_download, InferenceClient
+
+vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
+pipe_edit = StableDiffusionXLImg2ImgPipeline.from_single_file(
+    hf_hub_download(repo_id="stabilityai/cosxl", filename="cosxl_edit.safetensors"),
+    num_in_channels=8,
+    is_cosxl_edit=True,
+    vae=vae,
+    torch_dtype=torch.float16,
+)
+pipe_edit.scheduler = EDMEulerScheduler(sigma_min=0.002, sigma_max=120.0, sigma_data=1.0, prediction_type="v_prediction")
+pipe_edit.to("cuda")
+
+refiner = StableDiffusionXLImg2ImgPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", vae=vae, torch_dtype=torch.float16, use_safetensors=True, variant="fp16")
+refiner.to("cuda")
+
+def set_timesteps_patched(self, num_inference_steps: int, device=None):
+    self.num_inference_steps = num_inference_steps
+    
+    ramp = np.linspace(0, 1, self.num_inference_steps)
+    sigmas = torch.linspace(math.log(self.config.sigma_min), math.log(self.config.sigma_max), len(ramp)).exp().flip(0)
+    
+    sigmas = (sigmas).to(dtype=torch.float32, device=device)
+    self.timesteps = self.precondition_noise(sigmas)
+    
+    self.sigmas = torch.cat([sigmas, torch.zeros(1, device=sigmas.device)])
+    self._step_index = None
+    self._begin_index = None
+    self.sigmas = self.sigmas.to("cpu")
+
+EDMEulerScheduler.set_timesteps = set_timesteps_patched
+
+def king(
+        input_image,
+        instruction: str,
+        negative_prompt: str = "",
+        steps: int = 25,
+        randomize_seed: bool = True,
+        seed: int = 2404,
+        guidance_scale: float = 6,
+        progress=gr.Progress(track_tqdm=True)
+    ):
+    input_image = Image.open(input_image).convert('RGB')
+    if randomize_seed:
+        seed = random.randint(0, 999999)
+    generator = torch.manual_seed(seed)
+    output_image = pipe_edit(
+        instruction,
+        negative_prompt=negative_prompt,
+        image=input_image,
+        guidance_scale=guidance_scale,
+        image_guidance_scale=1.5,
+        width=input_image.width,
+        height=input_image.height,
+        num_inference_steps=steps,
+        generator=generator,
+        output_type="latent",
+    ).images
+    refine = refiner(
+        prompt=f"{instruction}, 4k, hd, high quality, masterpiece",
+        negative_prompt=negative_prompt,
+        guidance_scale=7.5,
+        num_inference_steps=steps,
+        image=output_image,
+        generator=generator,
+    ).images[0]  
+    return seed, refine
+
+css = '''
+.gradio-container{max-width: 700px !important}
+h1{text-align:center}
+footer {
+    visibility: hidden
+}
+'''
+
+examples = [
+    [
+        "./supercar.png",
+        "make it red",
+    ],
+    [
+        "./red_car.png",
+        "add some snow",
+    ],
+]
+
+with gr.Blocks(css=css) as demo:
+    gr.Markdown("# Image Editing\n### Note: First image generation takes time")
+    with gr.Row():
+        instruction = gr.Textbox(lines=1, label="Instruction", interactive=True)
+        generate_button = gr.Button("Run", scale=0)
+        
+    with gr.Row():
+        input_image = gr.Image(label="Image", type='filepath', interactive=True)
+
+    with gr.Row():
+        guidance_scale = gr.Number(value=6.0, step=0.1, label="Guidance Scale", interactive=True)
+        steps = gr.Number(value=25, step=1, label="Steps", interactive=True)
+
+    with gr.Accordion("Advanced options", open=False):
+        with gr.Row():
+            negative_prompt = gr.Text(
+                label="Negative prompt",
+                max_lines=1,
+                value="(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, ugly, disgusting, blurry, amputation,(face asymmetry, eyes asymmetry, deformed eyes, open mouth)",
+                visible=True
+            )
+        with gr.Row():
+            randomize_seed = gr.Checkbox(label="Randomize Seed", value=True, interactive=True)
+            seed = gr.Number(value=2404, step=1, label="Seed", interactive=True)
+
+    gr.Examples(
+        examples=examples,
+        inputs=[input_image, instruction],
+        outputs=[input_image],
+        cache_examples=False,
+    )
+
+    generate_button.click(
+        king,
+        inputs=[input_image, instruction, negative_prompt, steps, randomize_seed, seed, guidance_scale],
+        outputs=[seed, input_image],
+    )
+
+demo.queue(max_size=500).launch()