Total runs:
77.9K
Run Growth:
23.9K
Growth Rate:
31.04%
Sponsored by
ThumbnailCreator.com
vantagewithai / Capybara-GGUF
Model's Last Updated: February 28 2026
any-to-any
Introduction of Capybara-GGUF
Model Details of Capybara-GGUF
Quantized GGUF Versions of Capybara-1.0
Original model Link: https://huggingface.co/xgen-universe/Capybara
Watch us at Youtube: @VantageWithAI
CAPYBARA: A Unified Visual Creation Model
🎉 Welcome to visit our Project Page | 💻 Visit our Demo Website to try our model!
Capybara is a unified visual creation model, i.e., a powerful visual generation and editing framework designed for high-quality visual synthesis and manipulation tasks.
The framework leverages advanced diffusion models and transformer architectures to support versatile visual generation and editing capabilities with precise control over content, motion, and camera movements.
|
Speech-driven base clips generated by Seedance 2.0. All editing powered by CAPYBARA |
Key Features:
- 🎬 Multi-Task Support : Supports Text-to-Video (T2V), Text-to-Image (T2I), Instruction-based Video-to-Video (TV2V), Instruction-based Image-to-Image (TI2I), and various editing tasks
- 🚀 High Performance : Built with distributed inference support for efficient multi-GPU processing
🔥 News
- [2026.02.20] 🎨 Added ComfyUI support with custom nodes for all task types (T2I, T2V, TI2I, TV2V), together with FP8 quantization support for the inference script and ComfyUI custom node.
- [2026.02.17] 🚀 Initial release v0.1 of the Capybara inference framework supporting generation and instruction-based editing tasks (T2I, T2V, TI2I, TV2V).
📝 TODO List
- Add support for ComfyUI.
- Release our unified creation model.
- Release training code.
🏞️ Show Cases
Results of generation tasks. We show two generation tasks under our unified model. The top section presents text-to-image results, illustrating high-fidelity synthesis across diverse styles. The bottom rows show text-to-video results, demonstrating temporally coherent generation with natural motion for both realistic and stylized content.
Results of image editing tasks. We show the results of both instruction-based image editing and in-context image editing. The examples cover local and global edits (e.g., time-of-day and style changes), background replacement, and expression control. We further demonstrate multi-turn editing, where edits are applied sequentially. We also show in-context editing guided by a refenece image.
Results of instruction-based video editing task. We showcase instruction-based editing (TV2V) under our unified creation interface, covering local edits, global edits, dense prediction, and dynamic edits. Each example presents input frames and the edited outputs, highlighting temporally coherent transformations that preserve identity and overall structure.
Results of in-context visual creation. We show in-context generation and in-context editing results, including subject-conditioned generation (S2V/S2I), conditional generation (C2V), image-to-video (I2V), reference-driven editing (II2I/IV2V).
Recommended Settings
For optimal quality and performance, we recommend the following settings:
| Task Type | Recommended Resolution | Recommended Steps | Note |
|---|---|---|---|
| Video (T2V, TV2V) |
480p
|
50
|
Balanced quality and generation speed |
| Image (T2I, TI2I) |
720p
|
50
|
Higher quality for static images |
Notes:
-
Resolution
: You can experiment with higher resolutions (
1024or1080p). - Inference Steps : 50 steps provide a good balance between quality and speed. You can use 30-40 steps for faster generation.
📄 License
This project is released under the MIT License.
🙏 Acknowledgments
This project is built upon:
- HunyuanVideo-1.5 - Base Video Generation Model
- Diffusers - Diffusion pipeline infrastructure
- Accelerate - Distributed training/inference
- SageAttention - Efficient attention mechanism
📝 Citation
If you find Capybara useful for your research, please consider citing:
@misc{capybara2026rao,
title={Capybara: A Unified Visual Creation Model},
author={Rao, Zhefan and Che, Haoxuan and Hu, Ziwen and Zou, Bin and Liu, Yaofang and He, Xuanhua and Choi, Chong-Hou and He, Yuyang and Chen, Haoyu and Su, Jingran and Li, Yanheng and Chu, Meng and Lei, Chenyang and Zhao, Guanhua and Li, Zhaoqing and Zhang, Xichen and Li, Anping and Liu, Lin and Tu, Dandan and Liu, Rui},
year={2026}
}
📧 Contact
For questions and feedback, please open an issue on GitHub.
You can also contact us by email: [email protected] and [email protected]
⭐ If you find this project helpful, please consider giving it a star!
Runs of vantagewithai Capybara-GGUF on huggingface.co
151
Total runs
0
24-hour runs
-3
3-day runs
35
7-day runs
-44
30-day runs
More Information About Capybara-GGUF huggingface.co Model
Url of Capybara-GGUF
Capybara-GGUF huggingface.co Url
Provider of Capybara-GGUF huggingface.co
Other API from vantagewithai
Updated:June 24 2026
Total runs:
35.6K
Run Growth:
30.3K
Growth Rate:
85.23%
Total runs:
25.7K
Run Growth:
-1.2K
Growth Rate:
-4.72%
Total runs:
23.3K
Run Growth:
-5.6K
Growth Rate:
-23.95%
Total runs:
18.3K
Run Growth:
18.3K
Growth Rate:
100.00%
Total runs:
17.5K
Run Growth:
17.5K
Growth Rate:
100.00%
Total runs:
16.4K
Run Growth:
7.9K
Growth Rate:
47.32%
Total runs:
13.5K
Run Growth:
-32.7K
Growth Rate:
-242.03%
Total runs:
12.2K
Run Growth:
-2.4K
Growth Rate:
-19.66%
Total runs:
12.0K
Run Growth:
-3.1K
Growth Rate:
-25.96%
Total runs:
9.9K
Run Growth:
216
Growth Rate:
2.18%
Total runs:
9.1K
Run Growth:
99
Growth Rate:
1.10%
Total runs:
8.9K
Run Growth:
3.1K
Growth Rate:
35.45%
Total runs:
8.4K
Run Growth:
2.5K
Growth Rate:
29.87%
Total runs:
7.6K
Run Growth:
4.7K
Growth Rate:
60.10%
Total runs:
6.5K
Run Growth:
2.0K
Growth Rate:
30.49%
Total runs:
5.1K
Run Growth:
4.6K
Growth Rate:
90.15%
Total runs:
4.7K
Run Growth:
-1.4K
Growth Rate:
-30.23%
Total runs:
4.7K
Run Growth:
3.1K
Growth Rate:
66.12%
Total runs:
4.3K
Run Growth:
1.9K
Growth Rate:
43.35%
Total runs:
4.2K
Run Growth:
-423
Growth Rate:
-10.05%
Total runs:
4.0K
Run Growth:
904
Growth Rate:
22.40%
Total runs:
4.0K
Run Growth:
3.5K
Growth Rate:
86.42%
Total runs:
3.5K
Run Growth:
282
Growth Rate:
8.16%
Total runs:
2.1K
Run Growth:
1.5K
Growth Rate:
70.86%
Total runs:
1.2K
Run Growth:
597
Growth Rate:
48.34%
Total runs:
957
Run Growth:
-287
Growth Rate:
-29.99%
Total runs:
909
Run Growth:
-72
Growth Rate:
-7.92%
Total runs:
889
Run Growth:
706
Growth Rate:
79.42%
Total runs:
627
Run Growth:
138
Growth Rate:
22.01%
Total runs:
616
Run Growth:
139
Growth Rate:
22.56%
Total runs:
614
Run Growth:
52
Growth Rate:
8.47%
Total runs:
601
Run Growth:
-323
Growth Rate:
-53.74%
Total runs:
545
Run Growth:
474
Growth Rate:
86.97%
Total runs:
541
Run Growth:
-76
Growth Rate:
-14.05%
Total runs:
492
Run Growth:
327
Growth Rate:
66.46%
Total runs:
491
Run Growth:
-817
Growth Rate:
-166.40%
Total runs:
485
Run Growth:
210
Growth Rate:
43.30%
Total runs:
432
Run Growth:
46
Growth Rate:
10.65%
Total runs:
418
Run Growth:
227
Growth Rate:
54.31%
Total runs:
397
Run Growth:
139
Growth Rate:
35.01%
Total runs:
385
Run Growth:
-158
Growth Rate:
-41.04%
Total runs:
373
Run Growth:
79
Growth Rate:
21.18%
Total runs:
346
Run Growth:
150
Growth Rate:
43.35%
Total runs:
297
Run Growth:
-5
Growth Rate:
-1.68%
Total runs:
212
Run Growth:
13
Growth Rate:
6.13%
Total runs:
184
Run Growth:
-21
Growth Rate:
-11.41%
Total runs:
109
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%