━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⚠️ Using v2? Open the "About this version" box of v2 and follow its Quick start: you type your own folder paths in the workflow (Image Iterator → folder_path, Processed Image Check → output_root). The "How to Use" steps further down (images in ./input, v1.1 file, output by date) are for v1.1 only.🔼 SeedVR2 Batch Upscaler — Sleep On It, Wake Up 4KDrop a folder, come back to 4K━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ComfyUI batch image upscaler powered by SeedVR2, the SOTA diffusion-based restoration model from ByteDance. Load an entire folder of QC-approved images, set the batch number, click Run once, and watch them upscale to 4K in a single session. No per-image re-queuing, no repetition—sequential images feed through the same upscaler instance to your output folder, all with automatic date-stamped organization. Built for production stock photography, concept art detail recovery, and QC'd generation batches.━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━✨ Features✅ Batch Folder Iterator — Place 10–100 images in input folder, set the batch number to match, all process sequentially without re-loading model✅ Whole-Folder Workflow — ImageIterator node handles file discovery, sorting, and index auto-increment✅ SeedVR2 7B fp16 (default) — Diffusion-based upscaler, SOTA quality; fp8 and 3B variants available for speed/VRAM trade-off✅ 4K Short-Edge Target — short edge upscaled to 4096, long edge capped at 4096 (1024×1024 → 4096×4096; 1280×1600 → 3276×4096). The effective upscale factor depends on the input's aspect ratio.✅ Block-Swap Ready — Pre-configured with blocks_to_swap=36 + CPU offload + SDPA attention for 16GB VRAM fit (requires ~33GB system RAM)✅ Automated Output Organization — Results saved to output/ folder with automatic date stamp [YYYY-MM-DD]✅ Torch.compile Optional — Node included but disabled by default; enable if you have triton-windows for inference speedup✅ Metadata-Safe Export — PNG output; embedded workflow metadata has no machine paths or language-specific notes━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━📦 Required Models (3 files, ~7-16 GB depending on variant)Primary (default — recommended)• seedvr2_ema_7b_fp16.safetensors — Main diffusion upscaler (highest quality, fits 16GB with block-swap)• ema_vae_fp16.safetensors — VAE codec for image reconstructionAlternative Variants (choose one — do NOT mix in same batch)• seedvr2_ema_7b_fp8_e4m3fn.safetensors + ema_vae_fp16.safetensors — Faster, near-identical quality, lower VRAM• seedvr2_ema_3b_fp16.safetensors + ema_vae_fp16.safetensors — Fastest option, fits 16GB without block-swap━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⬇️ Download Links (verified HuggingFace repositories)7B fp16 (default — recommended for quality)• seedvr2_ema_7b_fp16.safetensors — <a target="_blank" rel="ugc" href="https://huggingface.co/numz/SeedVR2_comfyUI/blob/main/seedvr2_ema_7b_fp16.safetensors">https://huggingface.co/numz/SeedVR2_comfyUI/blob/main/seedvr2_ema_7b_fp16.safetensors</a>• ema_vae_fp16.safetensors — <a target="_blank" rel="ugc" href="https://huggingface.co/numz/SeedVR2_comfyUI/blob/main/ema_vae_fp16.safetensors">https://huggingface.co/numz/SeedVR2_comfyUI/blob/main/ema_vae_fp16.safetensors</a>7B fp8 (faster, lower VRAM)• seedvr2_ema_7b_fp8_e4m3fn.safetensors — <a target="_blank" rel="ugc" href="https://huggingface.co/numz/SeedVR2_comfyUI/blob/main/seedvr2_ema_7b_fp8_e4m3fn.safetensors">https://huggingface.co/numz/SeedVR2_comfyUI/blob/main/seedvr2_ema_7b_fp8_e4m3fn.safetensors</a>• ema_vae_fp16.safetensors — <a target="_blank" rel="ugc" href="https://huggingface.co/numz/SeedVR2_comfyUI/blob/main/ema_vae_fp16.safetensors">https://huggingface.co/numz/SeedVR2_comfyUI/blob/main/ema_vae_fp16.safetensors</a>3B (fastest, native 16GB fit)• seedvr2_ema_3b_fp16.safetensors — <a target="_blank" rel="ugc" href="https://huggingface.co/numz/SeedVR2_comfyUI/blob/main/seedvr2_ema_3b_fp16.safetensors">https://huggingface.co/numz/SeedVR2_comfyUI/blob/main/seedvr2_ema_3b_fp16.safetensors</a>• ema_vae_fp16.safetensors — <a target="_blank" rel="ugc" href="https://huggingface.co/numz/SeedVR2_comfyUI/blob/main/ema_vae_fp16.safetensors">https://huggingface.co/numz/SeedVR2_comfyUI/blob/main/ema_vae_fp16.safetensors</a>Installation Path:• Diffusion models: ComfyUI/models/diffusion_models/• VAE files: ComfyUI/models/vae/━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━🧩 Required Custom Nodes⚠️ Manual Install Step (do this first — it's the only one not in ComfyUI Manager):Image_Anything (Batch Folder Iterator) — NOT in ComfyUI Manager registry1. Open terminal/PowerShell in your ComfyUI root directory2. Navigate to custom_nodes: <code>cd custom_nodes</code>3. Clone the repo: <code>git clone https://github.com/ComfyUI-Kelin/ComfyUI_Image_Anything.git</code>4. Restart ComfyUIThen install these via ComfyUI Manager (search → install):• ComfyUI-SeedVR2_VideoUpscaler (numz) — canonical SeedVR2 node pack, in Manager registry, searchable by name- Install via Manager: Manager → Install Custom Nodes → search "SeedVR2" → select numz's ComfyUI-SeedVR2_VideoUpscaler → Install• was-node-suite-comfyui (ltdrdata) — Image Save node (PNG/WebP export); MIT license, in Manager registry- Install via Manager: search "was-node-suite" → installVerify Installation: After restart, load this workflow in ComfyUI. If nodes resolve (no red outlines), you're good to go.━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━🚀 How to Use1. Prepare Images — Place your QC-approved images (PNG/JPG, any resolution 256–4096px) in ComfyUI's <code>./input</code> folder2. Load This Workflow — Open SeedVR2_Batch_Upscale_v1.1.json in ComfyUI3. Run It — Set the batch number next to Run to the number of images you want, then click Run once (older ComfyUI builds label this button Queue)- Each execution advances the ImageIterator by one file, so a batch of 10 walks 10 images. Clicking Run repeatedly does not stack on current frontends — it ignores presses until the current run finishes, so use the batch number.4. Monitor Progress — Watch the ImageIterator node report "current_index / total_count" as it walks the folder5. Collect Output — Check ComfyUI's <code>./output</code> folder for upscaled images, organized by date [YYYY-MM-DD]Example Workflow:- Input folder: <code>ComfyUI/input/</code> (contains 5 PNG files)- Set the batch number to 5 and click Run once- Wait ~1 minute per image on the default 7B fp16 config (measured — see the benchmark table below); slower if your system RAM is tight- Output appears in <code>ComfyUI/output/[YYYY-MM-DD]/</code>, named from the Image Save prefix (default <code>Up VR2 [time(...)]</code> plus a counter — edit the prefix widget on the Image Save node to change it)━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⚙️ Settings &amp; ParametersModel Loading• Model Path: Automatically detects from ComfyUI/models/diffusion_models/ (VAE loads from ComfyUI/models/vae/)• Device: CUDA (GPU); falls back to CPU if CUDA unavailable• Offload Device: CPU (system RAM) — keeps VRAM leanUpscale Output• Resolution: 4096 — target for the SHORT edge; aspect ratio is preserved• Max Resolution: 4096 — cap on the LONG edge; if an image exceeds it after the short-edge target is applied, both dimensions scale down proportionally. This keeps VRAM predictable on tall or wide images.• Batch Size: 1 per queue (sequential processing)• Color Correction: "lab" (perceptually-aware color preservation)• Attention Mode: "sdpa" (scaled-dot-product attention — memory-efficient)Block-Swap (VRAM Management)• blocks_to_swap: 36 (default, pre-configured for 16GB VRAM)- Swaps 36 UNet blocks to system RAM to fit model on GPU- Requires ~33GB system RAM; 64GB recommended for smooth performance- If you have less RAM, switch to 7B fp8 or 3B variantTorch.compile (Optional Speedup)• Status: DISABLED by default (node present, not connected)• Reason: Requires triton-windows, which most Windows users lack → would error on first run• How to Enable (if you have triton): Reconnect the <code>SeedVR2TorchCompileSettings</code> node output → the <code>torch_compile_args</code> input on <code>SeedVR2LoadDiTModel</code>. The same input also exists on <code>SeedVR2LoadVAEModel</code> if you want to compile the VAE too. Can add ~20–30% speed boost, but only if dependencies are met.Seed &amp; Noise• Seed: 42, with control_after_generate set to "fixed" — every run is reproducible. Set the control to "randomize" if you want variation between runs.• Input Noise Scale: 0.05 · Latent Noise Scale: 0.0 — low values preserve detail and prevent hallucinationVAE Tiling (if image &gt;2048px)• Encode Tiled: Enabled (1024px tiles, 128px overlap)• Decode Tiled: Enabled (same tiling)→ Prevents OOM on large inputs━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━💡 Performance TipsVRAM &amp; System RAM Honesty• 7B fp16 + swap36 (default, shipped) — ~16GB VRAM, ~33GB offloaded to CPU. Highest quality. Requires 64GB system RAM for smooth batch processing; 32GB will thrash and be very slow. Measured: ~62s/image (steady-state, 17-image production batch, 1280×1600→3276×4096)*• 7B fp8_e4m3fn — ~9GB VRAM, ~18GB offloaded to CPU. Faster inference (~30% speedup estimated, not yet benchmarked). Quality near-identical to fp16. Fits 32GB system RAM comfortably.• 3B fp16 — ~16GB VRAM, no offload needed. Fastest option (not yet benchmarked). No block-swap overhead. Fits 16GB natively.*Measured on RTX 5080, 7B fp16 variant only, back-to-back queue (model already loaded). fp8/3B timings not yet benchmarked — estimates only.Practical Guidance• For highest quality + 64GB system RAM: Use 7B fp16 (default config)• For speed + 32GB RAM: Switch model to 7B fp8 (same setup, different checkpoint file)• For minimal VRAM/RAM: Use 3B variant (nearly as good, no block-swap delays)• Batch 10+ images together to amortize the one-time model load• Avoid running alongside heavy generation (e.g., Krea2 gen) — too much total VRAM pressure• Input image quality: Sharp, well-lit images upscale better than low-contrast originals (expected for all upscalers)━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━🔗 My Workflow SuiteI maintain a growing library of ComfyUI workflows. Check them out:• LTX-2.3 Image-to-Video — Lock-camera i2v with auto motion prompt (QwenVL)• Krea2 Turbo Dual-Mode — Fast diffusion gen (text or image-to-image)• Z-Image-Turbo — Another fast gen option with auto-prompt: <a target="_blank" rel="ugc" href="https://civarchive.com/models/2742740/z-image-turbo-qwenvl-dual-mode-auto-prompt">https://civarchive.com/models/2742740/z-image-turbo-qwenvl-dual-mode-auto-prompt</a>• SeedVR2 Batch Upscaler — This workflow (batch folder upscale to 4K)Find LTX-2.3 and Krea2 Turbo on my Civitai profile page. More coming soon — follow for updates!GitHub Mirror: <a target="_blank" rel="ugc" href="https://github.com/Thinni63/comfyui-workflows/tree/main/seedvr2-batch-upscale">https://github.com/Thinni63/comfyui-workflows/tree/main/seedvr2-batch-upscale</a>━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━🔄 Changelogv1.1 (2026-08-17)• Fixed: SeedVR2 was never actually connected. The Preview node carried a phantom output slot that ComfyUI drops when loading the file, which cut the link into SeedVR2, while a stale link ID made the Save node read the preview image instead. Net effect: saved files came out identical to the input. Thanks to daze45230 for the detailed report.• Changed: SeedVR2 is no longer hidden inside a subgraph. The model loaders, upscaler, and torch.compile node now sit directly on the canvas, so every setting is visible and editable without opening a container — and a subgraph-capable ComfyUI build is no longer required.• Improved: Node layout reorganized into labelled groups (start guide / run settings / model setup / pipeline).• Settings and model requirements are unchanged — drop-in replacement for v1.v1 (2026-07-03)• Initial release.━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━📝 Notes &amp; AI Disclosure• AI-Generated Example Images — All provided examples are AI-generated via Krea2 + upscaled with this workflow• Hardware Tested — Verified on RTX 5080 16GB VRAM, Windows 11, CUDA 12.1+• ComfyUI Version — No subgraph support required as of v1.1 (the graph is flat). Any reasonably recent ComfyUI with the three custom node packs installed will load it.• Model Weights License — SeedVR2 weights are NOT distributed with the workflow; you download them separately from HuggingFace (see Download Links above)• Metadata Safety — This workflow JSON has no machine paths or language-specific notes; it's safe to share and distribute━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⭐ Found this useful?• Like if it saved you time• Comment your results — I read every one• Follow for new ComfyUI workflows, all tested on 16 GB VRAM━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━Roadmap TeaserA video-batch variant of this upscaler is coming soon. Stay tuned!━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━⚖️ Model Attribution &amp; LicensingSeedVR2 (ByteDance Seed Team)• License: Apache License 2.0 — <a target="_blank" rel="ugc" href="https://huggingface.co/ByteDance-Seed/SeedVR2-7B">https://huggingface.co/ByteDance-Seed/SeedVR2-7B</a>• Attribution Required: "SeedVR2 by ByteDance Seed Team, licensed under Apache License 2.0."• Safetensors Conversion: Hosted at <a target="_blank" rel="ugc" href="https://huggingface.co/numz/SeedVR2_comfyUI">https://huggingface.co/numz/SeedVR2_comfyUI</a> for ComfyUI-compatible format• Free for commercial and non-commercial use (see license for full terms)Custom Nodes• ComfyUI-SeedVR2_VideoUpscaler (numz) — Check repository for license• was-node-suite-comfyui (ltdrdata) — MIT License• ComfyUI_Image_Anything (ComfyUI-Kelin) — MIT LicenseThis Workflow (JSON Configuration)• Original work by TP_AI_63 (Civitai) / Thinni63 (GitHub)• Shared under MIT License; credit appreciated• Model weights must be downloaded separately (not included)All example outputs are AI-generated via Krea2 generation and SeedVR2 upscaling.

SeedVR2 Batch Upscaler — Sleep On It, Wake Up 4K

What's new in v2.1Two folder boxes at the front of the graph. "1. IMAGE FOLDER" and "2. OUTPUT FOLDER" are now plain text boxes (coloured, on the left) that feed the Image Iterator and the Processed Image Check. Paste your two folder paths there and press Run. In v2 these two fields sat inside the nodes, empty, and the workflow stopped at Run until they were filled - thanks to the reviewer who pointed this out.Troubleshooting is written into the note at the top of every file, with the exact error texts we saw (see below).Nothing else changed: same six files (16 / 12 / 8 GB x 2K / 4K), same models, same settings, same helper scripts as v2.If Run stops with a red error (texts seen in our tests, ComfyUI 0.41.1):<ul><li>save_spec.output_root cannot be empty. -&gt; box 2 is empty.</li><li>Invalid folder path: ... -&gt; box 1 is not an existing folder; check the spelling.</li><li>[WinError 123] The filename, directory name, or volume label syntax is incorrect -&gt; box 2 still holds the placeholder text. This one appears only after the first image was upscaled, so fill both boxes first.</li></ul>Checked: in ComfyUI 0.41.1 (frontend 1.52.7) on an RTX 5080 Laptop 16 GB, the 8GB_2K file and the 8GB_4K file were loaded from the .json, only the two boxes were filled, Run was pressed once - each produced its image (1932x2048 and 3864x4096 from a 1024 px source). The other four files differ only in model and block-swap numbers; they passed the same structure check but were not run again. Everything else in the v2 description (numbers, VRAM and RAM warnings) still applies.

Files with SHA256: d567aa98667229e26b5e096fb6bae50726f20062b0dedf376e0b13042bbdfb80