Instructions to use AInVFX/SeedVR2_comfyUI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use AInVFX/SeedVR2_comfyUI with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("AInVFX/SeedVR2_comfyUI", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
| license: apache-2.0 | |
| pipeline_tag: video-to-video | |
| library_name: diffusers | |
| tags: | |
| - art | |
| base_model: | |
| - ByteDance-Seed/SeedVR2-7B | |
| - ByteDance-Seed/SeedVR2-3B | |
| # SeedVR2 Additional Upscale Models | |
| This repository contains additional upscale models for SeedVR2 video upscaling, complementing the main [numz/SeedVR2_comfyUI](https://huggingface.co/numz/SeedVR2_comfyUI) repository. | |
| ## π About SeedVR2 | |
| SeedVR2 is a high-quality video upscaling model that uses diffusion techniques to enhance video resolution while maintaining temporal consistency. This implementation is optimized for ComfyUI and supports both standalone and multi-GPU operation. | |
| [](https://youtu.be/MBtWYXq_r60) | |
| [](https://youtu.be/I0sl45GMqNg) | |
| ## π― GGUF Models | |
| The GGUF format models in this repository are sourced from [cmeka/SeedVR2-GGUF](https://huggingface.co/cmeka/SeedVR2-GGUF), where additional GGUF versions and quantizations are available. We acknowledge and appreciate cmeka's work in converting these models to GGUF format. | |
| ## π License | |
| The code and model weights are released under the Apache 2.0 License. | |
| ## π Credits | |
| - **Original SeedVR2**: [ByteDance-Seed/SeedVR](https://github.com/ByteDance-Seed/SeedVR) by ByteDance Seed | |
| - **ComfyUI original integration**: [numz/ComfyUI-SeedVR2_VideoUpscaler](https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler) by [numz](https://github.com/numz) | |
| - **Further integration**: Additional code by [Adrien Toupet](https://github.com/adrientoupet) from [AInVFX](https://www.youtube.com/@AInVFX) | |
| - **Official HuggingFace Models**: [numz/SeedVR2_comfyUI](https://huggingface.co/numz/SeedVR2_comfyUI) | |
| - **GGUF conversions**: [cmeka/SeedVR2-GGUF](https://huggingface.co/cmeka/SeedVR2-GGUF) by [cmeka](https://huggingface.co/cmeka) | |
| - **Tutorial**: [SeedVR2 Deep Dive](https://youtu.be/I0sl45GMqNg) by AInVFX | |
| ## π οΈ Usage Guidelines | |
| When using these additional models: | |
| 1. Compare output quality against official models | |
| 2. Monitor VRAM usage and performance | |
| 3. Test various input resolutions and batch sizes | |
| 4. Report issues on the [main repository](https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler/issues) | |
| ## π Support | |
| For questions and support: | |
| - Use the [main repository issues](https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler/issues) | |
| - Check the [comprehensive tutorial](https://youtu.be/I0sl45GMqNg) by AInVFX | |