Update gradio_demo.py

gradio_demo.py

@@ -47,10 +47,10 @@ def main(prompt, init_prompt, negative_prompt, num_iter, CFG, seed):
 
 with gr.Blocks() as demo:
     gr.Markdown("# <center>LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching</center>")
-    gr.Markdown("<center>Yixun Liang*, Xin Yang*, Jiantao Lin, Haodong Li, Xiaogang Xu, Yingcong Chen**</center>")
-    gr.Markdown("<center>*: Equal contribution. **: Corresponding author.</center>")
-    gr.Markdown("We present a text-to-3D generation framework, named the *LucidDreamer*, to distill high-fidelity textures and shapes from pretrained 2D diffusion models.")
-    gr.Markdown("<details><summary><strong>CLICK for the full abstract</strong></summary>The recent advancements in text-to-3D generation mark a significant milestone in generative models, unlocking new possibilities for creating imaginative 3D assets across various real-world scenarios. While recent advancements in text-to-3D generation have shown promise, they often fall short in rendering detailed and high-quality 3D models. This problem is especially prevalent as many methods base themselves on Score Distillation Sampling (SDS). This paper identifies a notable deficiency in SDS, that it brings inconsistent and low-quality updating direction for the 3D model, causing the over-smoothing effect. To address this, we propose a novel approach called Interval Score Matching (ISM). ISM employs deterministic diffusing trajectories and utilizes interval-based score matching to counteract over-smoothing. Furthermore, we incorporate 3D Gaussian Splatting into our text-to-3D generation pipeline. Extensive experiments show that our model largely outperforms the state-of-the-art in quality and training efficiency.</details>")
+    # gr.Markdown("<center>Yixun Liang*, Xin Yang*, Jiantao Lin, Haodong Li, Xiaogang Xu, Yingcong Chen**</center>")
+    # gr.Markdown("<center>*: Equal contribution. **: Corresponding author.</center>")
+    # gr.Markdown("We present a text-to-3D generation framework, named the *LucidDreamer*, to distill high-fidelity textures and shapes from pretrained 2D diffusion models.")
+    # gr.Markdown("<details><summary><strong>CLICK for the full abstract</strong></summary>The recent advancements in text-to-3D generation mark a significant milestone in generative models, unlocking new possibilities for creating imaginative 3D assets across various real-world scenarios. While recent advancements in text-to-3D generation have shown promise, they often fall short in rendering detailed and high-quality 3D models. This problem is especially prevalent as many methods base themselves on Score Distillation Sampling (SDS). This paper identifies a notable deficiency in SDS, that it brings inconsistent and low-quality updating direction for the 3D model, causing the over-smoothing effect. To address this, we propose a novel approach called Interval Score Matching (ISM). ISM employs deterministic diffusing trajectories and utilizes interval-based score matching to counteract over-smoothing. Furthermore, we incorporate 3D Gaussian Splatting into our text-to-3D generation pipeline. Extensive experiments show that our model largely outperforms the state-of-the-art in quality and training efficiency.</details>")
     gr.Interface(fn=main, inputs=[gr.Textbox(lines=2, value="A portrait of IRONMAN, white hair, head, photorealistic, 8K, HDR.", label="Your prompt"),
             gr.Textbox(lines=1, value="a man head.", label="Point-E init prompt (optional)"),
             gr.Textbox(lines=2, value="unrealistic, blurry, low quality, out of focus, ugly, low contrast, dull, low-resolution.", label="Negative prompt (optional)"),