Hugging Face's logo

Video-Reason
/
VBVR-LTX2.3-diffsynth

Image-to-Video
Diffusers
Model card Files
xet
 Community
1
wruisi commited on
Commit
05d6c61
·
verified ·
1 Parent(s): fdbd5d3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -2
README.md CHANGED
@@ -4,6 +4,8 @@ base_model:
4
  library_name: diffusers
5
  license: apache-2.0
6
  pipeline_tag: image-to-video
 
 
7
  ---
8
  # VBVR: A Very Big Video Reasoning Suite
9
 
@@ -51,11 +53,11 @@ The model was presented in the paper [A Very Big Video Reasoning Suite](https://
51
 
52
  | Model | Base Architecture | Other Remarks |
53
  |-------|-------------------|---------------|
54
- | [**VBVR-Wan2.1**](https://huggingface.co/Video-Reason/VBVR-Wan2.1) | Wan2.1-I2V-14B-720P | Diffusers format |
55
  | [VBVR-Wan2.2](https://huggingface.co/Video-Reason/VBVR-Wan2.2) | Wan2.2-I2V-A14B | Diffusers format |
56
  | [VBVR-Wan2.1-diffsynth](https://huggingface.co/Video-Reason/VBVR-Wan2.1-diffsynth) | Wan2.1-I2V-14B-720P | DiffSynth LoRA format |
57
  | [VBVR-Wan2.2-diffsynth](https://huggingface.co/Video-Reason/VBVR-Wan2.2-diffsynth) | Wan2.2-I2V-A14B | DiffSynth LoRA format |
58
- | [VBVR-LTX2.3-diffsynth](https://huggingface.co/Video-Reason/VBVR-LTX2.3-diffsynth) | LTX-2.3 | DiffSynth LoRA format |
59
 
60
  ## Release Information
61
  VBVR-LTX2.3 is trained from LTX-2.3 without architectural modifications, as the goal of VBVR is to *investigate data scaling behavior* and provide *strong baseline models* for the video reasoning research community. Leveraging the VBVR-Dataset, which constitutes one of the largest video reasoning datasets to date, the VBVR model family achieved highest scores on VBVR-Bench.
 
4
  library_name: diffusers
5
  license: apache-2.0
6
  pipeline_tag: image-to-video
7
+ datasets:
8
+ - Video-Reason/VBVR-Dataset
9
  ---
10
  # VBVR: A Very Big Video Reasoning Suite
11
 
 
53
 
54
  | Model | Base Architecture | Other Remarks |
55
  |-------|-------------------|---------------|
56
+ | [VBVR-Wan2.1](https://huggingface.co/Video-Reason/VBVR-Wan2.1) | Wan2.1-I2V-14B-720P | Diffusers format |
57
  | [VBVR-Wan2.2](https://huggingface.co/Video-Reason/VBVR-Wan2.2) | Wan2.2-I2V-A14B | Diffusers format |
58
  | [VBVR-Wan2.1-diffsynth](https://huggingface.co/Video-Reason/VBVR-Wan2.1-diffsynth) | Wan2.1-I2V-14B-720P | DiffSynth LoRA format |
59
  | [VBVR-Wan2.2-diffsynth](https://huggingface.co/Video-Reason/VBVR-Wan2.2-diffsynth) | Wan2.2-I2V-A14B | DiffSynth LoRA format |
60
+ | [**VBVR-LTX2.3-diffsynth**](https://huggingface.co/Video-Reason/VBVR-LTX2.3-diffsynth) | LTX-2.3 | DiffSynth LoRA format |
61
 
62
  ## Release Information
63
  VBVR-LTX2.3 is trained from LTX-2.3 without architectural modifications, as the goal of VBVR is to *investigate data scaling behavior* and provide *strong baseline models* for the video reasoning research community. Leveraging the VBVR-Dataset, which constitutes one of the largest video reasoning datasets to date, the VBVR model family achieved highest scores on VBVR-Bench.