Codex commited on
Commit
d53b4d8
ยท
1 Parent(s): 9e741c4

Update model card with paper links and citation

Browse files
Files changed (1) hide show
  1. README.md +42 -2
README.md CHANGED
@@ -5,7 +5,7 @@ language:
5
  library_name: diffusers
6
  base_model:
7
  - Lightricks/LTX-2.3
8
- pipeline_tag: video-to-video
9
  tags:
10
  - video-editing
11
  - video-restoration
@@ -44,7 +44,31 @@ This release focuses on four practical video editing directions:
44
 
45
  Unlike conventional frame-level enhancement pipelines, this model family operates as a **generative video restoration system** in latent video space. It is designed to preserve global structure, camera motion, object identity, and temporal consistency while reconstructing missing or degraded visual content.
46
 
47
- Project links: [GitHub project](https://github.com/Valiant-Cat/LTX2-ICEdit-Insight) | [JoyFox on Hugging Face](https://huggingface.co/joyfox)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
 
49
  ## ๐Ÿ“ฆ Model Files
50
 
@@ -263,6 +287,22 @@ This is especially helpful for recovering:
263
  - Frame count should follow the `8k + 1` rule.
264
  - Output height and width should be multiples of `32` in single-stage inference.
265
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
266
  ## ๐Ÿ—๏ธ Training
267
 
268
  This model family was trained and optimized by **JoyFox Lab** (**Chengdu Xuanhu Technology Co., Ltd.**).
 
5
  library_name: diffusers
6
  base_model:
7
  - Lightricks/LTX-2.3
8
+ pipeline_tag: image-to-video
9
  tags:
10
  - video-editing
11
  - video-restoration
 
44
 
45
  Unlike conventional frame-level enhancement pipelines, this model family operates as a **generative video restoration system** in latent video space. It is designed to preserve global structure, camera motion, object identity, and temporal consistency while reconstructing missing or degraded visual content.
46
 
47
+ Project links: [GitHub project](https://github.com/Valiant-Cat/LTX2-ICEdit-Insight) | [JoyFox on Hugging Face](https://huggingface.co/joyfox) | [Paper (Research Square)](https://www.researchsquare.com/article/rs-9775063/v1) | [DOI](https://doi.org/10.21203/rs.3.rs-9775063/v1)
48
+
49
+ ## ๐Ÿ“„ Paper
50
+
51
+ - **Title**: *LTX-Insight: Unified Video Restoration and Semantic Editing via Task-Aware Adaptation and Temporal Consistency*
52
+ - **Authors**: Fan Tang, Siyuan Li
53
+ - **Venue**: Research Square
54
+ - **Posted date**: May 25, 2026
55
+ - **DOI**: [`10.21203/rs.3.rs-9775063/v1`](https://doi.org/10.21203/rs.3.rs-9775063/v1)
56
+ - **Paper URL**: https://www.researchsquare.com/article/rs-9775063/v1
57
+
58
+ This model release corresponds to the paper's unified video post-processing framework built around three high-level settings: video super-resolution/enhancement, occlusion removal and repair, and instruction-driven semantic editing.
59
+
60
+ In the currently released inference package, those ideas are exposed through four practical routes:
61
+
62
+ - **Video Restoration**
63
+ - **Video HD Enhancement**
64
+ - **Watermark Removal**
65
+ - **Subtitle Removal**
66
+
67
+ The paper introduces three core components:
68
+
69
+ - **TADA (Task-Aware Decoupled Adapter)** for separating structure restoration from texture/semantic editing under a shared backbone.
70
+ - **FGLC (Flow-Guided Latent Consistency)** for explicit temporal consistency modeling in latent space using optical-flow alignment and cross-frame attention bias.
71
+ - **PMTR (Progressive Multi-Task Routing)** for more stable joint multi-task training through curriculum scheduling and collaborative routing.
72
 
73
  ## ๐Ÿ“ฆ Model Files
74
 
 
287
  - Frame count should follow the `8k + 1` rule.
288
  - Output height and width should be multiples of `32` in single-stage inference.
289
 
290
+ ## ๐Ÿ“š Citation
291
+
292
+ If this model family is useful in your research or application workflow, please cite:
293
+
294
+ ```bibtex
295
+ @article{tang2026ltxinsight,
296
+ title = {LTX-Insight: Unified Video Restoration and Semantic Editing via Task-Aware Adaptation and Temporal Consistency},
297
+ author = {Tang, Fan and Li, Siyuan},
298
+ journal = {Research Square},
299
+ year = {2026},
300
+ month = {05},
301
+ doi = {10.21203/rs.3.rs-9775063/v1},
302
+ url = {https://www.researchsquare.com/article/rs-9775063/v1}
303
+ }
304
+ ```
305
+
306
  ## ๐Ÿ—๏ธ Training
307
 
308
  This model family was trained and optimized by **JoyFox Lab** (**Chengdu Xuanhu Technology Co., Ltd.**).