Uploaded October 2025 | Updated November 2026, 2 days ago
When I first tested FlashVSR inside ComfyUI, I thought it was working fine.
But when I looked closely, the armor edge in my clip had split into two.
It looked like a ghost reflection, like the model could not decide which edge was real.
That’s when I started testing everything again.
I found out FlashVSR is not just an upscaler, it’s a video restoration model.
It rebuilds lost details frame by frame.
But the problem is most versions inside ComfyUI don’t have LCSA.
That’s why we get that reflection problem in some videos.
So in this video, I’ll show you the exact one step that fixes it.
Just divide your video resolution by 2, run it through FlashVSR, and then upscale it back to 4K using SeedVR2.
That’s it. The ghost reflection is gone and the result looks clean and stable.
I’ll go through everything step by step — how I built the workflow, what settings I used, and how you can get the same result even on a low VRAM GPU.
When you see the final clip, it looks naturally sharp and realistic, like it was actually shot in 4K.
If your video looks unclear, has ghost lines, or flicker between frames, this will fix it.
FlashVSR restores the detail, and SeedVR2 does the final upscale.
Together, they make your video look like new again.
Watch the full video till the end, I’ll show you side-by-side results and the full workflow you can try yourself.
Files You Need To Download:
Comfyui Workflow: aistudynow.com/flashvsr-in-comfyui-1-step-to-4k-upscale-video-no-ghost-lines
1️⃣ Wan2_1-T2V-1_3B_FlashVSR_fp32.safetensors
2️⃣ Wan2_1_FlashVSR_LQ_proj_model_bf16.safetensors
📂 Save both inside ComfyUI/models/diffusion_models/
3️⃣ Wan2_1_FlashVSR_TCDecoder_fp32.safetensors
📂 Save this one in ComfyUI/models/vae/
Then restart ComfyUI once all files are added.
If this video helped you or you learned something new, hit Like and Subscribe so you don’t miss the next tutorial.
When I first tested FlashVSR inside ComfyUI, I thought it was working fine.
But when I looked closely, the armor edge in my clip had split into two.
It looked like a ghost reflection, like the model could not decide which edge was real.
That’s when I started testing everything again.
I found out FlashVSR is not just an upscaler, it’s a video restoration model.
It rebuilds lost details frame by frame.
But the problem is most versions inside ComfyUI don’t have LCSA.
That’s why we get that reflection problem in some videos.
So in this video, I’ll show you the exact one step that fixes it.
Just divide your video resolution by 2, run it through FlashVSR, and then upscale it back to 4K using SeedVR2.
That’s it. The ghost reflection is gone and the result looks clean and stable.
I’ll go through everything step by step — how I built the workflow, what settings I used, and how you can get the same result even on a low VRAM GPU.
When you see the final clip, it looks naturally sharp and realistic, like it was actually shot in 4K.
If your video looks unclear, has ghost lines, or flicker between frames, this will fix it.
FlashVSR restores the detail, and SeedVR2 does the final upscale.
Together, they make your video look like new again.
Watch the full video till the end, I’ll show you side-by-side results and the full workflow you can try yourself.
Files You Need To Download:
Comfyui Workflow: aistudynow.com/flashvsr-in-comfyui-1-step-to-4k-upscale-video-no-ghost-lines
1️⃣ Wan2_1-T2V-1_3B_FlashVSR_fp32.safetensors
2️⃣ Wan2_1_FlashVSR_LQ_proj_model_bf16.safetensors
📂 Save both inside ComfyUI/models/diffusion_models/
3️⃣ Wan2_1_FlashVSR_TCDecoder_fp32.safetensors
📂 Save this one in ComfyUI/models/vae/
Then restart ComfyUI once all files are added.
If this video helped you or you learned something new, hit Like and Subscribe so you don’t miss the next tutorial.




![NEW! Wan 2.1 Fun ControlNet ComfyUI Workflow – Bye Bye Glitchy AI Videos
In this step-by-step tutorial, I’ll show you how to use Alibaba’s Wan 2.1 Fun Control Model to turn ordinary videos into eye-catching AI animations. Whether you want to make music videos, social media ads, or cinematic clips, this guide covers everything—from basic setup to advanced stylization tricks.
What You’ll Learn:
✔️ How to download & install Wan 2.1 Fun Control in ComfyUI
✔️ ControlNet techniques for smooth motion transfer (pose, depth & line art)
✔️ Fixing common issues like glitchy frames & style inconsistencies
Resources Mentioned:
• Download Wan 2.1 Fun Control: [Hugging Face Link]
• Free Workflow Templates:
• My Recommended GPU Settings for Lag-Free Rendering
https://comfyuiblog.com/wan-2-1-fun-controlnet-comfyui-workflow/
Join the Discussion!
Have questions about ComfyUI Wan 2.1 or ControlNet workflows? Drop them in the comments below!
👍 Enjoyed This Tutorial?
Please LIKE and SUBSCRIBE for more ComfyUI and AI content!
#ComfyUI #Wan2.1 #ControlNet #AIVideo #ComfyUIWorkflow NEW! Wan 2.1 Fun ControlNet ComfyUI Workflow – Bye Bye Glitchy AI Videos](https://i.ytimg.com/vi/AeaGmjYeMoY/mqdefault.jpg)


![MiniMax H3 Upscaler vs RelayVSR vs SeedVR2 — Which Looks Better?
I upscaled the same MiniMax H3 video with RelayVSR and SeedVR2 in ComfyUI. RelayVSR 2x finished in about 37 seconds. SeedVR2 took 4 minutes 54 seconds.
SeedVR2 gives the sharper result. To me, RelayVSR looks more natural, and it keeps the original face. In this video, I show both results side by side, one problem I found with RelayVSR in fast action scenes, and the settings I use now.
In this video:
- What RelayVSR is, and the 2x and 4x model files
- The two new nodes: RelayVSR Conditioning and VSR Decode
- Why RelayVSR is fast: the big model runs only on every 15th frame and on the last frame
- Test 1: RelayVSR, SeedVR2, and the MiniMax H3 upscaler on one 26.4 second video
- How long each upscaler took
- Test 2: blur and extra detail in a fast fight scene with the 2x model
- The fix: the 4x model with the 4x VAE
- Test 3: the detail slider at 1 and at 0.6
RelayVSR is built into ComfyUI, so you do not need a custom node. If you cannot find the nodes, update ComfyUI.
Settings from the video:
- KSampler: 1 step, CFG 1, no prompt
- Always use the model and the VAE as a pair: 2x model with 2x VAE, 4x model with 4x VAE
- Detail slider: 1 is the default. I keep it from 0.6 to 1, and I do not go below 0.5
- 2x model for normal scenes
- 4x model for fast action. It needs more time and more memory, so use it on small videos
- Detail at 0.6 when the skin looks too sharp
Time in my test (26.4 second video made with [Pika H3 Flex - CONFIRM] on MiniMax H3):
- RelayVSR 2x: about 37.2 seconds
- SeedVR2: about 4 minutes 54 seconds
- MiniMax H3 upscaler: [30 minutes 30 seconds - CONFIRM]
Tested on: [YOUR GPU]. Your times can be different.
Model files for ComfyUI:
https://huggingface.co/Comfy-Org/RelayVSR
ComfyUI/models/diffusion_models: relayvsr_x2_lightx2v_int8_convrot.safetensors, relayvsr_x4_int8_convrot.safetensors
ComfyUI/models/vae: relayvsr_flash_vae_x2_fp32.safetensors, relayvsr_flash_vae_x4_fp32.safetensors
Original model: https://huggingface.co/kopper/RelayVSR
Workflow: https://www.patreon.com/ComfyuiWorkflowBlog/posts/relayvsr-comfyui-175122349
Which result do you prefer: the sharper SeedVR2 or the more natural RelayVSR? Tell me in the comments.
#RelayVSR #ComfyUI #MiniMaxH3 MiniMax H3 Upscaler vs RelayVSR vs SeedVR2 — Which Looks Better?](https://i.ytimg.com/vi/BskTA7BoNsk/mqdefault.jpg)


