remove

README.md

@@ -1,5 +1,5 @@
 ---
-title: Noisy-Style
+title: Inversion-InstantStyle
 emoji: 🎨
 colorFrom: blue
 colorTo: pink

app.py

@@ -1,6 +1,5 @@
 import os
 import random
-from typing import Optional
 
 import gradio as gr
 import numpy as np
@@ -9,16 +8,16 @@ import spaces
 import torch
 from diffusers import (AutoencoderKL, DDIMInverseScheduler, DDIMScheduler,
                        StableDiffusionXLPipeline)
-from torchvision.transforms import ToTensor 
+from torchvision.transforms import ToTensor
 
 # pyright: reportPrivateImportUsage=false
 
 
 DESCRIPTION = f"""
-    # 🎨 Noisy-Style 🎨  
+    # 🎨 Inversion-InstantStyle 🎨  
     This is an interactive demo of noisy DDIM inversion capabilities on top of Instant-Style styling method 
     
-    This method proposed in [Controllability of diffusion models]() *by Eyal Benaroche, Clément Chadebec, Onur Tasar, and Benjamin Aubin* from Jasper Research in the context of Eyal's internship with Ecole Polytechnique.
+    This method is proposed by *Eyal Benaroche, Clément Chadebec, Onur Tasar, and Benjamin Aubin* from Jasper Research in the context of Eyal's internship with Ecole Polytechnique.
 
     A style benchmark : [style-bench](https://gojasper.github.io/style-bench) was also provided to facilitate evaluation of diffusion models for styling purposes.
     """
@@ -54,7 +53,7 @@ if gr.NO_RELOAD:
         pipe.load_ip_adapter(
             "h94/IP-Adapter",
             subfolder="sdxl_models",
-            weight_name="ip-adapter_sdxl.safetensors"
+            weight_name="ip-adapter_sdxl.safetensors",
         )
         pipe.to(device)
 
@@ -88,7 +87,7 @@ def img_to_latents(x: torch.Tensor, vae: AutoencoderKL):
     return latents
 
 
-def invert_image(model, image: np.ndarray, n_steps: int, width:int, height:int):
+def invert_image(model, image: np.ndarray, n_steps: int, width: int, height: int):
 
     model.scheduler = invert_scheduler
 
@@ -128,7 +127,7 @@ def generate(
     height: int = 1024,
     guidance_scale_base: float = 5.0,
     num_inference_steps_base: int = 25,
-    style_image_value = None,
+    style_image_value=None,
     noise_scale: float = 1.5,
 ) -> PIL.Image.Image:
     torch.manual_seed(seed)
@@ -146,18 +145,15 @@ def generate(
     # Invert the image and get the latent
     if style_image_value is not None:
         latent = invert_image(pipe, style_image_value, 30, width, height)
-        print("Image was inverted")
-        print(latent)
 
         latent = latent + noise_scale * noise
-        latent = latent / torch.sqrt(torch.tensor(1 + noise_scale**2).to(device, dtype=torch.float16))
+        latent = latent / torch.sqrt(
+            torch.tensor(1 + noise_scale**2).to(device, dtype=torch.float16)
+        )
 
     else:
         latent = noise
 
-    print("Noise added")
-    print(latent)
-
     scale = {
         "up": {"block_0": [0.0, 1.0, 0.0]},
     }