skip the inference on the first step

README.md

@@ -8,7 +8,7 @@
 SVDQuant is a post-training quantization technique for 4-bit weights and activations that well maintains visual fidelity. On 12B FLUX.1-dev, it achieves 3.6× memory reduction compared to the BF16 model. By eliminating CPU offloading, it offers 8.7× speedup over the 16-bit model when on a 16GB laptop 4090 GPU, 3× faster than the NF4 W4A16 baseline. On PixArt-∑, it demonstrates significantly superior visual quality over other W4A4 or even W4A8 baselines. "E2E" means the end-to-end latency including the text encoder and VAE decoder.
 
 **SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models**<br>
-[Muyang Li](https://lmxyy.me), [Yujun Lin](https://yujunlin.com), [Zhekai Zhang](https://hanlab.mit.edu/team/zhekai-zhang), [Tianle Cai](https://www.tianle.website/#/), [Xiuyu Li](https://xiuyuli.com), [Junxian Guo](https://github.com/JerryGJX), [Enze Xie](https://xieenze.github.io), [Chenlin Meng](https://cs.stanford.edu/~chenlin/), [Jun-Yan Zhu](https://www.cs.cmu.edu/~junyanz/), and [Song Han](https://hanlab.mit.edu/songhan) <br>
+[Muyang Li](https://lmxyy.me)\*, [Yujun Lin](https://yujunlin.com)\*, [Zhekai Zhang](https://hanlab.mit.edu/team/zhekai-zhang)\*, [Tianle Cai](https://www.tianle.website/#/), [Xiuyu Li](https://xiuyuli.com), [Junxian Guo](https://github.com/JerryGJX), [Enze Xie](https://xieenze.github.io), [Chenlin Meng](https://cs.stanford.edu/~chenlin/), [Jun-Yan Zhu](https://www.cs.cmu.edu/~junyanz/), and [Song Han](https://hanlab.mit.edu/songhan) <br>
 *MIT, NVIDIA, CMU, Princeton, UC Berkeley, SJTU, and Pika Labs* <br>
 
 ![teaser](./assets/demo.gif)

app/i2i/run_gradio.py

@@ -13,6 +13,7 @@ from flux_pix2pix_pipeline import FluxPix2pixTurboPipeline
 from nunchaku.models.safety_checker import SafetyChecker
 from utils import get_args
 from vars import DEFAULT_SKETCH_GUIDANCE, DEFAULT_STYLE_NAME, MAX_SEED, STYLES, STYLE_NAMES
+import numpy as np
 
 blank_image = Image.new("RGB", (1024, 1024), (255, 255, 255))
 
@@ -51,6 +52,11 @@ def save_image(img):
 
 
 def run(image, prompt: str, prompt_template: str, sketch_guidance: float, seed: int) -> tuple[Image, str]:
+    image_numpy = np.array(image["composite"].convert("RGB"))
+
+    if prompt.strip() == "" and np.sum(image_numpy != 255) <= 100:
+        return image["composite"], "Please input the prompt or draw something."
+
     is_unsafe_prompt = False
     if not safety_checker(prompt):
         is_unsafe_prompt = True