SeedVR2
  • Preços
  • Orçamento em lote
  • Comparar
SeedVR2

Source-verified model guide

SeedVR2 Hugging Face: Official 3B/7B & ComfyUI Files

Use the right publisher, file, and folder before downloading. ByteDance publishes the official 3B and 7B checkpoints; Comfy-Org provides a ComfyUI repack; NumZ maintains a separate community node.

Who publishes what

These projects are related, but they are not interchangeable. The labels below prevent a community integration from being presented as an official ByteDance release.

Official ByteDance Seed

The upstream repository and the SeedVR2-3B / SeedVR2-7B Hugging Face repositories are the official model sources.

Hugging Face / GitHub

Comfy-Org repack

Comfy-Org republishes model files in the layout used by native ComfyUI integration. It does not replace ByteDance as the upstream model publisher.

Hugging Face / GitHub

NumZ community node

NumZ maintains a community custom node with additional workflow and memory options. Treat its claims and files as community-maintained.

Hugging Face / GitHub

Which SeedVR2 file should you download?

Download order matters more than names. The native ComfyUI template expects one 3B INT8 diffusion file plus the shared VAE; the official 7B checkpoint, FP8, and GGUF are heavier or community-only options. ByteDance documents H100 inference and the ComfyUI integration maintainer reports testing from roughly 18GB VRAM minimum, so no row below is an 8GB guarantee.

FilePublished byComfyUI folderWhere it fitsDownload it when
seedvr2_3b_int8_convrot.safetensorsComfy-Org repackComfyUI/models/diffusion_models/The 8GB and 12GB tiers start from 3BAlways first: this is the diffusion model the ComfyUI 0.28.0 template selects.
seedvr2_ema_vae_fp16.safetensorsComfy-Org repackComfyUI/models/vae/Shared by the image and video templatesTogether with the diffusion model, before the first sample run.
ByteDance-Seed/SeedVR2-3BByteDance Seed, Apache-2.0Upstream repository, not a ComfyUI folderThe official 3B sourceWhen you want the publisher original, or you are not running ComfyUI.
ByteDance-Seed/SeedVR2-7BByteDance Seed, Apache-2.0Upstream repository, not a ComfyUI folder12GB conservative test; 16GB or more with FP8/FP16Only after a 3B baseline passes and the source still needs more detail.
FP8 repackComfy-Org and integration repackComfyUI/models/diffusion_models/12GB and 16GBWhen 3B INT8 fits but you want a precision step before FP16.
GGUF Q4_K_M / Q8_0NumZ community nodeModels folder named by the community node8GB experimentsOnly after the native template fails: quantization is community work with no 8GB guarantee.

FP8 and GGUF are not ByteDance releases; they exist because Comfy-Org and the NumZ community node repack the model. A community file can load and still look worse than the official 3B INT8 baseline, so compare one 100 percent crop before committing a batch.

8GB card: read the low-memory order of operations first

Official snapshot_download method

from huggingface_hub import snapshot_download

snapshot_download(
    repo_id="ByteDance-Seed/SeedVR2-3B",
    local_dir="./SeedVR2-3B",
)

3B: ByteDance-Seed/SeedVR2-3B
7B: ByteDance-Seed/SeedVR2-7B

ComfyUI file directories

For the Comfy-Org package, put diffusion model files under ComfyUI/models/diffusion_models/ and the VAE under ComfyUI/models/vae/. Keep filenames unchanged, restart ComfyUI, then select the exact files in the workflow.

ComfyUI/models/diffusion_models/
ComfyUI/models/vae/

Hardware evidence—not an 8GB promise

ByteDance shows an H100 inference setup. The ComfyUI integration maintainer reports testing at roughly 18GB VRAM minimum. An 8GB run may be possible only through community quantization, tiling, offload, or BlockSwap experiments; neither source makes it an official guarantee.

Official limitations to check before a large run

  • Heavy degradation can exceed what the model can restore reliably.
  • Large motion can cause restoration failure or temporal inconsistency.
  • Lightly degraded sources can be over-sharpened.

License

The ByteDance SeedVR2 repository and official checkpoints are published under Apache-2.0. Review the repository license and any dependency or input-media rights before commercial use.

Primary sources

  • github.com/ByteDance-Seed/SeedVR
  • huggingface.co/ByteDance-Seed/SeedVR2-3B
  • huggingface.co/ByteDance-Seed/SeedVR2-7B
  • huggingface.co/Comfy-Org/SeedVR2
  • github.com/comfyorg/comfyui_seedvr2/blob/main/README.md
  • github.com/numz/ComfyUI-SeedVR2_VideoUpscaler

Frequently asked questions

Where is SeedVR2 on Hugging Face?
ByteDance publishes the official checkpoints at huggingface.co/ByteDance-Seed/SeedVR2-3B and huggingface.co/ByteDance-Seed/SeedVR2-7B, both under the Apache-2.0 license. Comfy-Org republishes ComfyUI-ready files and NumZ maintains a separate community node; neither replaces ByteDance as the model publisher.
Which SeedVR2 file should I download first?
For the native ComfyUI workflow, download seedvr2_3b_int8_convrot.safetensors into ComfyUI/models/diffusion_models/ and seedvr2_ema_vae_fp16.safetensors into ComfyUI/models/vae/. The 3B INT8 file is the diffusion model the ComfyUI 0.28.0 template selects.
Is SeedVR2 free and open source?
Yes. The SeedVR2 code and the official 3B/7B checkpoints are published under the Apache-2.0 license. Review the repository license and any dependency or input-media rights before commercial use.
How much VRAM does SeedVR2 need?
ByteDance documents H100 inference, and the ComfyUI integration maintainer reports testing from roughly 18GB VRAM minimum. 8GB is only possible through community quantization, tiling, offload or BlockSwap experiments; neither source makes it an official guarantee.
Can I use SeedVR2 without Hugging Face?
Yes. You can use the hosted upscaler on this site without downloading anything, or install the open-source model locally through ComfyUI. The Hugging Face checkpoints are the official source for the local route.
Open the complete ComfyUI installation guideUse the hosted upscaler
SeedVR2

SeedVR2 is an independent AI upscaling workspace for image and video upscaling, clear job tracking, and delivery workflows.

Launched on FazierLaunched on FazierFeatured on ToolPilot.ai
Empresa
  • Sobre
  • Blog
  • Tutorial
  • Suporte
Jurídico
  • Termos de Serviço
  • Política de Privacidade
  • Política de Reembolso
  • Política de Uso Aceitável
Recursos do SeedVR2
  • Orçamento de restauração de vídeo em lote (por projeto)
  • Download do modelo SeedVR2 (3B/7B)
  • Fluxo ComfyUI do SeedVR2
  • Modelos SeedVR2 no Hugging Face (3B/7B)
  • Repositórios SeedVR2 no GitHub
  • Download do upscaler SeedVR2 (sem instalar app)
  • Upscaler de imagem com IA online
  • Upscaler de vídeo com IA online
  • Comparativo de melhores upscalers de vídeo com IA
  • Restauração de vídeo para estúdios
  • Calculadora de custo de upscale de vídeo IA
  • Entrega profissional de vídeo
  • Ferramentas de IA para fantasias e vídeos de Halloween
  • Upscaler Flux 2 (rascunho para 2K)
  • Deixar texto nítido em imagem
  • Remover texto de vídeo

Receba novidades do produto

Enviaremos um e-mail apenas quando lançarmos um novo recurso ou modelo. Sem spam.

O SeedVR2 é um serviço independente que oferece acesso a modelos e fluxos de trabalho de IA de terceiros. Não somos afiliados, endossados nem patrocinados pelos provedores dos modelos.

© 2026 SeedVR2 Todos os Direitos Reservados.