ErenAta00
/

gargantua

video-inpainting

video-object-removal

video-generation

Model card Files Files and versions

ErenAta00 commited on Apr 24

Commit

2e96945

·

verified ·

1 Parent(s): c8b4db3

Update README.md

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -34,7 +34,6 @@ The result: a LoRA adapter that **removes an object and its physical aftermath**
 ## Benchmarks
-![BigBenHeykel](https://cdn-uploads.huggingface.co/production/uploads/672b6a9a5cf8fcb442436a7a/VsNxEK_0Httnyjy9GJrE6.gif)
 3-way evaluation on 3 diverse scenes — static urban (`hydrant`), moving pedestrian (`slow_walk`), reflective/transparent object (`sphere`). **Identical input video**, **identical SAM 2.1 per-frame masks**, same sampler, seed, steps, CFG.
@@ -101,7 +100,7 @@ Gargantua inherits the failure modes of its base model and adds a few of its own
 The Winston Churchill statue in Parliament Square is removed, but the stone pedestal and brick textures behind it are not fully regenerated. A soft residue remains in the inpainted region and the model does not reconstruct the distant crowd that was never directly visible in any frame of the clip.
-![churchill limitation](assets/churchill_limitation.gif)
 ### Known failure modes

 ## Benchmarks
 3-way evaluation on 3 diverse scenes — static urban (`hydrant`), moving pedestrian (`slow_walk`), reflective/transparent object (`sphere`). **Identical input video**, **identical SAM 2.1 per-frame masks**, same sampler, seed, steps, CFG.
 The Winston Churchill statue in Parliament Square is removed, but the stone pedestal and brick textures behind it are not fully regenerated. A soft residue remains in the inpainted region and the model does not reconstruct the distant crowd that was never directly visible in any frame of the clip.
+![BigBenHeykel](https://cdn-uploads.huggingface.co/production/uploads/672b6a9a5cf8fcb442436a7a/VsNxEK_0Httnyjy9GJrE6.gif)
 ### Known failure modes