Update README.md

README.md

@@ -6,9 +6,9 @@ tags:
 - 3d-generation
 - rectified-flow
 ---
-# TripoSG - High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
+# TripoSG-scribble - Fast 3D Shape Prototyping with Scribble and Prompt
 
-TripoSG-scribble is a variant of TripoSG. TripoSG is a state-of-the-art image-to-3D generation foundation model that leverages large-scale rectified flow transformers to produce high-fidelity 3D shapes from single images.
+TripoSG-scribble converts a scribble image and a text prompt to a 3D shape. TripoSG-scribble is a variant of TripoSG. TripoSG is a state-of-the-art image-to-3D generation foundation model that leverages large-scale rectified flow transformers to produce high-fidelity 3D shapes from single images.
 
 ## Model Description
 
@@ -20,7 +20,7 @@ TripoSG utilizes a novel architecture combining:
 - Cross-attention mechanism for image feature condition
 - 1.5B parameters operating on 2048 latent tokens
 
-TripoSG-scribble accepts scribble image and text prompt condition. For inference efficiency, TripoSG-scribble is different from TripoSG in:
+For inference efficiency, TripoSG-scribble is different from TripoSG in:
 - TripoSG-scribble is a CFG-distilled model and should be used with CFG=0
 - TripoSG-scribble is trained with 512 latent tokens