Model reference · open weights

SeedVR2_comfyUI

SeedVR2_comfyUI is an open-weight video model from AInVFX, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Video AInVFX 1 variants 73k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What SeedVR2_comfyUI is

SeedVR2 Additional Upscale Models This repository contains additional upscale models for SeedVR2 video upscaling, complementing the main numz/SeedVR2comfyUI repository. 📋 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/MBtWYXqr60) [](https://youtu.be/I0sl45GMqNg) 🎯 GGUF Models The GGUF format models in this repository are sourced from 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. 📄 License The code and model weights are released under the Apache 2.0 License. 🙏 Credits - Original SeedVR2: ByteDance-Seed/SeedVR by ByteDance Seed - ComfyUI original integration: numz/ComfyUI-SeedVR2VideoUpscaler by numz - Further integration: Additional code by Adrien Toupet from AInVFX - Official HuggingFace Models: numz/SeedVR2comfyUI - GGUF conversions: cmeka/SeedVR2-GGUF by cmeka - Tutorial: SeedVR2 Deep Dive by AInVFX 🛠️ 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 📞 Support For questions and support: - Use the main repository issues - Check the comprehensive tutorial by AInVFX

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

MakerAInVFX
TypeVideo models
Variants1
Runs withdiffusers
Based onByteDance-Seed/SeedVR2-7B, ByteDance-Seed/SeedVR2-3B
Released2025-07-18
Popularity73k downloads / month
Likes75
LicenceOpen weights

How it works

How video models work

Prompt / imagestart pointTemporal diffusionframes over timeVideoMP4 clipA video model generates a sequence of coherent frames from your prompt or a starting image.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
SeedVR2_comfyUIBF16Weights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys ainvfx-seedvr2-comfyui for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (ainvfx-seedvr2-comfyui below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/videos/generations \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"ainvfx-seedvr2-comfyui","prompt":"a drone shot over a forest"}'

Details

Languages, data & research

Tags

diffusers gguf art video-to-video

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want SeedVR2_comfyUI on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More video models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms