Upscale videos fast, smooth, and super clear—no detail lost.Who it's for: creators who want this pipeline in ComfyUI without assembling nodes from scratch. Not for: one-click results with zero tuning — you still choose inputs, prompts, and settings.<h3 id="open-preloaded-workflow-on-runcomfy">Open preloaded workflow on RunComfy</h3><a target="_blank" rel="ugc" href="https://www.runcomfy.com/comfyui-workflows/flashvsr-in-comfyui-workflow-real-time-video-restoration?utm_source=civitai&amp;utm_medium=referral">Open preloaded workflow on RunComfy (browser)</a>Why RunComfy first - Fewer missing-node surprises — run the graph in a managed environment before you mirror it locally. - Quick GPU tryout — useful if your local VRAM or install time is the bottleneck. - Matches the published JSON — the zip follows the same runnable workflow you can open on RunComfy.When downloading for local ComfyUI makes sense — you want full control over models on disk, batch scripting, or offline runs.How to use (local ComfyUI) 1. Load inputs (images/video/audio) in the marked loader nodes. 2. Set prompts, resolution, and seeds; start with a short test run. 3. Export from the Save / Write nodes shown in the graph.Expectations — First run may pull large weights; cloud runs may require a free RunComfy account.<hr /><h3 id="overview">Overview</h3>This workflow helps you transform any low-resolution or AI-generated video into clear, high-definition footage. Using advanced diffusion and sparse attention mechanisms, it restores detail and sharpness while maintaining smooth motion. Perfect for visual creators, it streamlines post-production and video enhancement. You get control over fine textures and balance between speed and quality. Easily upscale your clips while preserving consistent results. Ideal for rapid, high-quality video restoration tasks.Important nodes:<h2 id="key-nodes-in-comfyui-flashvsr-workflow">Key nodes in Comfyui FlashVSR workflow</h2><code>FlashVSRNode</code> (#152, full) - Core ultra-fast upscaler in “full” mode. Adjust <code>scale</code> for 2x/4x work, enable <code>color_fix</code> to stabilize luminance, and use <code>tiled_vae</code> or <code>tiled_dit</code> when working at larger resolutions. Tune <code>sparse_ratio</code>, <code>kv_ratio</code>, and <code>local_range</code> only if you see motion softness or temporal drift. Implementation reference: <a target="_blank" rel="ugc" href="https://github.com/lihaoyun6/ComfyUI-FlashVSR_Ultra_Fast">ComfyUI-FlashVSR_Ultra_Fast</a>.<code>FlashVSRNode</code> (#143, tiny) - Ultra-fast “tiny” mode for maximum speed. Use it for previews or very long sequences. Same controls as the full node, but expect slightly softer micro-detail. Reference: <a target="_blank" rel="ugc" href="https://github.com/lihaoyun6/ComfyUI-FlashVSR_Ultra_Fast">ComfyUI-FlashVSR_Ultra_Fast</a>.<code>FlashVSR_SM_KSampler</code> (#146, Pass 1) - Streaming-quality sampler paired with a TCDecoder-enabled model (#158). Set <code>scale</code> first, then balance <code>cfg</code> and <code>steps</code> for detail vs speed. If VRAM is tight at high resolutions, enable <code>full_tiled</code> and reduce <code>split_num</code>. Implementation details and weights: <a target="_blank" rel="ugc" href="https://github.com/smthemex/ComfyUI_FlashVSR">ComfyUI_FlashVSR</a>.<code>FlashVSR_SM_KSampler</code> (#148, Pass 2) - Second streaming pass with a complementary model setup (#150). Use it to test alternative TCDecoder/embedding combos on the same frames. Keep <code>kv_ratio</code> and <code>local_range</code> consistent across passes when you want a controlled A/B.<code>WanVideoAddFlashVSRInput</code> (#114) - Bridges your preprocessed frames into the Wan sampler as FlashVSR conditioning. The <code>strength</code> control determines how assertively FlashVSR restoration is applied relative to any prompt influence. Increase strength when the source is very compressed or AI-generated.<code>WanVideoSampler</code> (#27) - One-step inference inside the Wan pipeline. If you use prompts, start neutral and avoid strong negative lists; let FlashVSR handle restoration while text slightly nudges tone or scene interpretation. Keep <code>steps</code> to one for true FlashVSR behavior in this route.<code>ColorMatch</code> (#142) - Harmonizes color back to the source after restoration. Use it to avoid unintended hue or gamma shifts, especially when exporting comparisons.<h3 id="notes">Notes</h3>FlashVSR in ComfyUI Workflow | Real-Time Video Restoration — see <a target="_blank" rel="ugc" href="https://www.runcomfy.com/comfyui-workflows/flashvsr-in-comfyui-workflow-real-time-video-restoration?utm_source=civitai&amp;utm_medium=referral">RunComfy page</a> for the latest node requirements.

Files with SHA256: 8f5e21bdac45d9d5431713bf3f3ea3d13729387f64654b922e881fe1ae4c26ec