Video Upscale: RelayVSR 2x
Upscale a clip 2x with the workflow below. The upscaler runs inside a subgraph, so the canvas only shows the video going in and coming out.
Download Workflow
Download JSON or search “RelayVSR 2x” in Template Library
Diffusion Model (2x)
relayvsr_x2_lightx2v_int8_convrot.safetensors → ComfyUI/models/diffusion_models/
VAE (2x)
relayvsr_flash_vae_x2_fp32.safetensors → ComfyUI/models/vae/
utility_relayvsr_video_x2_upscale_input.mp4
LoadVideo · utility_relayvsr_video_x2_upscale_input.mp4- Load your clip in the
Load Videonode. The template trims it to the first 5 seconds with aTrim Videonode, so raise that duration for longer clips or upscale long footage in passes. - Run the workflow. The result is saved by
Save VideounderComfyUI/output/video/.
Video Upscale: RelayVSR 4x
The 4x template is the same graph with the original RelayVSR weights, so the picture comes out exactly four times the size of the input.
Download Workflow
Download JSON or search “RelayVSR 4x” in Template Library
Diffusion Model (4x)
relayvsr_x4_int8_convrot.safetensors → ComfyUI/models/diffusion_models/
VAE (4x)
relayvsr_flash_vae_x4_fp32.safetensors → ComfyUI/models/vae/
cyber_samurai_chainsaw_lunge_video.mp4
LoadVideo · cyber_samurai_chainsaw_lunge_video.mp4- Load your clip in the
Load Videonode. - Run the workflow.
Save Videowrites the result underComfyUI/output/video/.