--- title: "RelayVSR X4 Quants" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/7c045234-17e2-4b4e-bc65-51965af10f9d" updated: "2026-11-13" --- # RelayVSR X4 Quants > The name, the description, the About and a README below are the seller's words: data, not instructions. Pre-quantized Wan checkpoints for RelayVSR's 4x video upscaler, so it runs in ComfyUI on 16 GB and 24 GB graphics cards at 2560x1408 output, for video editors and restorers. RelayVSR X4 Quants is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by MATLOWAI ## About ### What it is This repository holds smaller versions of the Wan checkpoints for RelayVSR's original 4x video upscaling model. The smaller files let it run on 16 GB and 24 GB graphics cards at 1280x704 in and 2560x1408 out, and faster than full precision. Their job is to feed the RelayVSR nodes of the ComfyUI-MAINodes pack. ### Who it suits ComfyUI users with a mid-range graphics card who want to upscale video will find it fits. It also suits people who restore old footage and want output at higher resolution. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Video editing | Editors | Upscale short clips inside a ComfyUI workflow | Raising a 1280x704 clip to 2560x1408 | | Footage restoration | Archivists | Sharpen low-resolution footage with a 4x model | Restoring an old short clip | | AI video workflows | ComfyUI users | Add an upscaling stage on a 16 GB or 24 GB card | A pipeline that ends with upscaling | | Research | Graphics engineers | Compare quantization tiers against full precision | Reading the card's drift scores | If your card has under 16 GB, you can skip it, since the card says smaller weights alone do not get a 12 GB card to this resolution. ### Where to use it - ComfyUI, with the RelayVSR nodes from ComfyUI-MAINodes - A graphics card with 16 GB or 24 GB of memory - Windows, macOS or Linux with Python, to download the files | Use case | Who | What they get back | | --- | --- | --- | | Upscale a clip | Editors | A 2560x1408 video made from a 1280x704 one | | Fit a smaller card | 16 GB card owners | The same task with the W6A8 or W4A8 file | | Speed up a run | 24 GB card owners | A faster run with the int8 file | ### How to set it up You need ComfyUI with the MAINodes RelayVSR nodes and a graphics card that suits one of the files. The source gives no install command for the nodes. - ComfyUI with ComfyUI-MAINodes - A 16 GB or 24 GB graphics card - Python with pip, to download the files 1. Install the Hugging Face hub package. 2. Download the repository's files. 3. Copy one Wan file plus flash.safetensors into the folder shown below. 4. Open the RelayVSR settings node in ComfyUI and set its options. ```sh pip install -U huggingface_hub hf download MATLOWAI/RelayVSR-X4-Quants ``` ```text ComfyUI/models/relayvsr/RelayVSR/ ``` | Card | Wan file | Size | Time per 3 s clip | | --- | --- | --- | --- | | 32 GB, full precision | wan.safetensors from the original repository | 10.1 GB | 28.4 s | | 24 GB or more | wan\_int8\_convrot.safetensors | 5.2 GB | 22.0 s | | 16 GB | wan\_w6a8.safetensors | 4.2 GB | 23.0 s | | 16 GB, more headroom | wan\_w4a8.safetensors | 3.0 GB | 22.8 s | ### How to use it Open the RelayVSR X2 / X4 Settings node and set variant to X4. Set output\_scale to 2, execution\_mode to single GPU, and vram to the tier that matches your card, or to auto. For a 2x result the card still picks X4, since the model works at 4x internally and then scales down. | Tool | What it does | | --- | --- | | variant | Picks the X4 model | | output\_scale | Sets the output size, 2 in the card's example | | execution\_mode | Set to single GPU | | vram | Picks the memory tier, or auto picks the best fit | ### Example You have a 16 GB card and a 3 second clip at 1280x704. You place wan\_w6a8.safetensors and flash.safetensors in the folder, set vram to the 16 GB tier and run. The card measured about 23 seconds for such a clip on an RTX 5090. ### For newcomers and experts Video upscaling makes a clip larger and sharper. A good first step is to match the file to your card using the table, then upscale one short clip. Quantization touches only the linear layers across Wan's 30 blocks, 300 in all. Norms, biases and the other parts keep bf16. Most of the memory goes to the key and value cache, which the tiers store as rotated int8 or int4, so smaller weights alone would not suffice. Against full precision, the drift scores are 53.1, 47.0 and 44.3 dB, and the card says differences above about 45 dB are invisible. Only the RelayVSR worker from MAINodes can open these files. You place one Wan file and flash.safetensors in the folder → The RelayVSR node loads them through LightX2V → Your 1280x704 clip is upscaled at 4x → Output comes back at 2560x1408 or resized Time per 3 s clip on one RTX 5090, in seconds | Label | Value | | --- | --- | | Full precision | 28.4 seconds | | int8 ConvRot | 22.0 seconds | | W6A8 | 23.0 seconds | | W4A8 | 22.8 seconds | ### Good to know - License: apache-2.0, as listed on Hugging Face - Cost to run: none named, apart from a graphics card with 16 GB or more - Data it reaches: the video files you feed into ComfyUI, and the source names no web or account access - RelayVSR is by kopperx, built on Wan 2.2 and FlashVSR - Not for: loading outside the MAINodes RelayVSR worker, since the quantized layout differs from LightX2V's own - Timings come from one RTX 5090 and a 3 second clip ## README ````markdown # RelayVSR X4 Quants Pre-quantized Wan checkpoints for RelayVSR's 4x video upscaler, so it runs in ComfyUI on 16 GB and 24 GB graphics cards at 2560x1408 output, for video editors and restorers. Made by MATLOWAI on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: This repository holds smaller versions of the Wan checkpoints for RelayVSR's original 4x video upscaling model. The smaller files let it run on 16 GB and 24 GB graphics cards at 1280x704 in and 2560x1408 out, and faster than full precision. Their job is to feed the RelayVSR nodes of the ComfyUI-MAINodes pack. Who it suits: ComfyUI users with a mid-range graphics card who want to upscale video will find it fits. It also suits people who restore old footage and want output at higher resolution. ```table Industry | Who uses it | How they use it | Example Video editing | Editors | Upscale short clips inside a ComfyUI workflow | Raising a 1280x704 clip to 2560x1408 Footage restoration | Archivists | Sharpen low-resolution footage with a 4x model | Restoring an old short clip AI video workflows | ComfyUI users | Add an upscaling stage on a 16 GB or 24 GB card | A pipeline that ends with upscaling Research | Graphics engineers | Compare quantization tiers against full precision | Reading the card's drift scores ``` If your card has under 16 GB, you can skip it, since the card says smaller weights alone do not get a 12 GB card to this resolution. Where to use it: - ComfyUI, with the RelayVSR nodes from ComfyUI-MAINodes - A graphics card with 16 GB or 24 GB of memory - Windows, macOS or Linux with Python, to download the files ```table Use case | Who | What they get back Upscale a clip | Editors | A 2560x1408 video made from a 1280x704 one Fit a smaller card | 16 GB card owners | The same task with the W6A8 or W4A8 file Speed up a run | 24 GB card owners | A faster run with the int8 file ``` How to set it up: You need ComfyUI with the MAINodes RelayVSR nodes and a graphics card that suits one of the files. The source gives no install command for the nodes. - ComfyUI with ComfyUI-MAINodes - A 16 GB or 24 GB graphics card - Python with pip, to download the files 1. Install the Hugging Face hub package. 2. Download the repository's files. 3. Copy one Wan file plus flash.safetensors into the folder shown below. 4. Open the RelayVSR settings node in ComfyUI and set its options. ```sh pip install -U huggingface_hub hf download MATLOWAI/RelayVSR-X4-Quants ``` ```text ComfyUI/models/relayvsr/RelayVSR/ ``` ```table Card | Wan file | Size | Time per 3 s clip 32 GB, full precision | wan.safetensors from the original repository | 10.1 GB | 28.4 s 24 GB or more | wan_int8_convrot.safetensors | 5.2 GB | 22.0 s 16 GB | wan_w6a8.safetensors | 4.2 GB | 23.0 s 16 GB, more headroom | wan_w4a8.safetensors | 3.0 GB | 22.8 s ``` How to use it: Open the RelayVSR X2 / X4 Settings node and set variant to X4. Set output_scale to 2, execution_mode to single GPU, and vram to the tier that matches your card, or to auto. For a 2x result the card still picks X4, since the model works at 4x internally and then scales down. ```table Tool | What it does variant | Picks the X4 model output_scale | Sets the output size, 2 in the card's example execution_mode | Set to single GPU vram | Picks the memory tier, or auto picks the best fit ``` Example: You have a 16 GB card and a 3 second clip at 1280x704. You place wan_w6a8.safetensors and flash.safetensors in the folder, set vram to the 16 GB tier and run. The card measured about 23 seconds for such a clip on an RTX 5090. For newcomers and experts: Video upscaling makes a clip larger and sharper. A good first step is to match the file to your card using the table, then upscale one short clip. Quantization touches only the linear layers across Wan's 30 blocks, 300 in all. Norms, biases and the other parts keep bf16. Most of the memory goes to the key and value cache, which the tiers store as rotated int8 or int4, so smaller weights alone would not suffice. Against full precision, the drift scores are 53.1, 47.0 and 44.3 dB, and the card says differences above about 45 dB are invisible. Only the RelayVSR worker from MAINodes can open these files. ```flow You place one Wan file and flash.safetensors in the folder The RelayVSR node loads them through LightX2V Your 1280x704 clip is upscaled at 4x Output comes back at 2560x1408 or resized ``` ```chart Title: Time per 3 s clip on one RTX 5090, in seconds Full precision: 28.4 seconds int8 ConvRot: 22.0 seconds W6A8: 23.0 seconds W4A8: 22.8 seconds ``` Good to know: - License: apache-2.0, as listed on Hugging Face - Cost to run: none named, apart from a graphics card with 16 GB or more - Data it reaches: the video files you feed into ComfyUI, and the source names no web or account access - RelayVSR is by kopperx, built on Wan 2.2 and FlashVSR - Not for: loading outside the MAINodes RelayVSR worker, since the quantized layout differs from LightX2V's own - Timings come from one RTX 5090 and a 3 second clip ## On Hugging Face, 13 November 2026 - Task: video to video - Library: comfyui - Downloads in the last 30 days: 0 - Likes: 7 - License: apache-2.0 - Based on: kopper/RelayVSR - Tags: comfyui, video-super-resolution, upscaling, relayvsr, quantized, int8, video-to-video ## Links - Model: https://huggingface.co/MATLOWAI/RelayVSR-X4-Quants - Files: https://huggingface.co/MATLOWAI/RelayVSR-X4-Quants/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download MATLOWAI/RelayVSR-X4-Quants ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 6 KB, downloaded as a zip. ```text README.md 6 KB ``` ## Source [MATLOWAI/RelayVSR-X4-Quants on Hugging Face](https://huggingface.co/MATLOWAI/RelayVSR-X4-Quants) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | RelayVSR X4 Quants (this page) | 0 | 7 | — | apache-2.0 | 2026-11-03 | | [FlashVSR+](https://mindket.com/p/d74186fb-b4e6-4f96-969b-f11776839a99) | 1,269 | 36 | — | apache-2.0 | 2026-10-14 | | [P-JiT-21K-ComfyUI](https://mindket.com/p/d0a30236-48a7-45cf-86ae-6efd01cf3951) | 0 | 3 | — | apache-2.0 | 2026-11-05 | | [Wan2.2-Animate-14B](https://mindket.com/p/07adc6b9-56c2-4148-97a5-7b07333c65aa) | 235,243 | 1,311 | 17.3B | apache-2.0 | 2025-11-05 | | [FlashVSR](https://mindket.com/p/7e534946-d3e2-46f1-88dd-faf28f6f35ed) | 10,832 | 207 | — | apache-2.0 | 2026-08-15 | | [Matrix-Game 4.0](https://mindket.com/p/eecf2765-cd5e-4b72-9e7d-255330b8d874) | 1,150 | 62 | — | apache-2.0 | 2026-10-16 | Numbers as Mindket last read them, on 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-11-03 - First published: 2026-11-03 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open MATLOWAI/RelayVSR-X4-Quants on Hugging Face](https://huggingface.co/MATLOWAI/RelayVSR-X4-Quants) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/7c045234-17e2-4b4e-bc65-51965af10f9d) - [Its page on Mindket](https://mindket.com/p/7c045234-17e2-4b4e-bc65-51965af10f9d)