Workflows/Generate videos locally with Wan2.1

Video / WORKFLOW

Generate videos locally with Wan2.1

Turn text prompts into local videos with the Wan2.1 T2V 1.3B model, complete pipeline files and a ready-to-load ComfyUI workflow.

Verified sourceSource checked 9/29/2026

LOCALRENTED GPU

Freshness 9 out of 100. Repository age: 621 days old, Feb 25, 2025. Measures age, not quality.

Popularity 68 out of 100. 90,282 downloads in 30 days; 667 lifetime likes. Checked Nov 7, 2026. Measures adoption, not quality.

What do these scores mean?

Two ways to compare models. Neither score measures answer quality, benchmark performance, or whether a model fits your machine.

Freshness · release age

A new release starts at 100. The score halves every 180 days: 100 × 2^(−age in days / 180). When the release date is unavailable, a repository date is a fallback—not proof of when the model was released. Missing dates stay unscored.

Check the date source

Popularity · adoption

Downloads over the past 30 days carry 80% of the score; lifetime likes carry 20%. Both use a logarithmic scale, capped at 10 million downloads and 100,000 likes. If likes are unavailable, downloads carry all the weight. Missing download statistics stay unscored.

round(80 × min(1, log10(1 + downloads) / 7) + 20 × min(1, log10(1 + likes) / 5))

Check the statistics source

Scores as of Nov 8, 2026. Statistics checked Nov 7, 2026. Statistics are marked for refresh after 72 hours.Full scoring method

Before you begin

Hardware

Estimated full-pipeline starting points: 1.3B T2V FP16, full-precision text encoder, VAE, batch 1, 832 × 480, 33 frames, 16 fps. CPU offload uses system RAM.

Machine	Wan2.1 T2V 1.3B · FP16
NVIDIA GPU · 8 GB + 32 GB RAM	Possible with CPU offload at 33 frames; reduce to 17 if memory is tight. Estimated.
NVIDIA GPU · 12–16 GB + 32 GB RAM	Practical short-clip starting point with automatic offload. Estimated.
NVIDIA GPU · 32 GB + 64 GB RAM	Ample starting capacity for this 1.3B pipeline and 33-frame preset. Estimated.
AMD GPU · 12–16 GB + 32 GB RAM	Supported ROCm card required; start at 33 frames with offload. Estimated.
Intel Arc GPU · 12–16 GB + 32 GB RAM	XPU backend required; 33 frames and automatic offload. Estimated.
Apple Silicon · 32 GB unified	Short-clip starting point using full-precision encoder and Metal. Estimated.
Apple Silicon · 64 GB unified	More memory headroom at 33 frames; not a render-time promise. Estimated.
CPU only · 32 GB RAM	Not recommended for video generation; use a GPU route or a rented 16 GB GPU.

Memory capacity is not a speed measurement. AMD/Intel require the correct supported GPU backend; Mac uses Apple Silicon Metal. These are source-informed estimates, not YouRunAI hardware benchmarks. Multi-GPU memory is not pooled by this graph.

LOCAL VIDEO GENERATIONSOURCE-LINKED SETUP

Generate videos locally with Wan2.1

Turn text prompts into local videos with the Wan2.1 T2V 1.3B model, complete pipeline files and a ready-to-load ComfyUI workflow. Choose your package and machine, then use Comfy Desktop to choose a built-in template or the supplied workflow JSON, download its models and save a result.

Choose a package Load the visual workflow Check the result

BEFORE YOU BEGIN

The documented package

This setup uses the package documented for this task. Review its source and supported platforms before starting.

Save your machine in My Hardware to get an automatic starting choice. You can always choose any package yourself.

CURRENT SETUP

Wan2.1 T2V 1.3B · FP16 · official

Estimated for 832 × 480, 33 frames, batch 1. Use 32 GB system RAM for automatic offload; 8 GB cards may need 17 frames. Close other GPU apps. Higher resolution, more frames and a second generation increase memory.

Freshness 9 out of 100. Repository age: 621 days old, Feb 25, 2025. Measures age, not quality.

Popularity 88 out of 100. 4,360,858 downloads in 30 days; 1,018 lifetime likes. Checked Oct 22, 2026. Statistics need refreshing. Measures adoption, not quality.

What do these scores mean?

Two ways to compare models. Neither score measures answer quality, benchmark performance, or whether a model fits your machine.

Freshness · release age

Check the date source

Popularity · adoption

round(80 × min(1, log10(1 + downloads) / 7) + 20 × min(1, log10(1 + likes) / 5))

Check the statistics source

Scores as of Nov 8, 2026. Statistics checked Oct 22, 2026. Statistics are marked for refresh after 72 hours. These statistics are due for a refresh.Full scoring method

View weight source

THE WORKFLOW

Set up Wan2.1 T2V 1.3B · FP16 on your machine

Choose your computer first, then its GPU path. Follow the visual setup and import the linked workflow.

CHOOSE YOUR SETUPWindows

Hardware type

NVIDIA (CUDA) through Comfy Desktop. An existing working ComfyUI installation can use the same JSON and model files; a second installation is unnecessary.

Open Comfy Desktop — install only if needed

Already have a working, current ComfyUI? Skip installation and continue to the workflow choice below. Otherwise: Download the Windows installer, open the .exe and follow the setup screens. Launch Comfy Desktop from the Start menu. Choose New Instance → Standalone, the Stable channel and NVIDIA (CUDA) when the hardware options appear. Let the app install Python and dependencies for you; no separate Git or Python setup is needed. Use the current NVIDIA driver. For RTX 20-series and newer, including RTX 5090, select the recommended stable CUDA build; respect any driver or GPU-compatibility warning. When ready, click the instance card to open ComfyUI. In the card’s ⋮ → Manage → About, confirm the expected GPU and PyTorch backend rather than CPU before downloading large files.

Download Comfy Desktop Official Windows installation NVIDIA driver downloads

Choose Templates or the supplied workflow JSON

For the fewest setup changes, download this package’s JSON below (use Save link as if it opens as text), then drag it onto the ComfyUI canvas. It already contains the exact model selections, preset and output path used in this guide; no custom-node packs are needed. Or use ComfyUI Templates: click Templates in the sidebar (also Workflow → Browse Workflow Templates), search for “Wan 2.1 Text to Video” and open that exact template. It uses the matching 1.3B text-to-video model. Its default text encoder is FP8: to match this package, select umt5_xxl_fp16.safetensors in Load CLIP from the downloads below. Apply the 832 × 480, 33-frame, 16-fps preset and fixed seed below; set SaveVideo format to mp4 and codec to h264 instead of auto. Set SaveVideo filename_prefix to YouRunAI/wan-text-video so the save-location instructions match. If the exact template is absent, use the JSON or update ComfyUI and its template package. Use one route per run. The supplied JSON remains available if you prefer the expanded graph or want this guide’s exact setup.

Download this exact ComfyUI workflow JSON How to open ComfyUI Templates Official Wan 2.1 Text to Video template Original official graph and explanation

Download the matching model files

If you chose Templates, skip its FP8 text-encoder suggestion; use the FP16 encoder listed here. In Desktop’s missing-model dialog, click Download for each required file and wait for completion. Models already present can be reused. If the prompt is unavailable, use the exact links below: open ☰ → Desktop Settings → Storage → Shared Models, then click the folder icon beside Primary. The tree starts INSIDE that primary model folder; do not add another models folder. Older manual/portable installations use their existing ComfyUI/models folder instead. Confirm Load Diffusion Model selects wan2.1_t2v_1.3B_fp16.safetensors, Load CLIP selects umt5_xxl_fp16.safetensors with type wan, and Load VAE selects wan_2.1_vae.safetensors. After downloads finish, reload the workflow and reselect a file if a loader still shows it missing.

Put these files in Your primary model folder/3 required files

diffusion_models/

wan2.1_t2v_1.3B_fp16.safetensorsText-to-video checkpoint; does not accept a start imageGet file

text_encoders/

umt5_xxl_fp16.safetensorsFull-precision text encoder; avoids FP8-only backend assumptionsGet file

vae/

wan_2.1_vae.safetensorsDecodes the generated video framesGet file

Desktop model downloads Find your shared model folder

Describe the scene and set a short clip

In the positive CLIP Text Encode node enter: A small sailboat moving slowly across a calm lake, gentle camera pan, morning light, smooth natural motion. Keep the supplied negative prompt. This is text-to-video: it deliberately has no image-upload node. Set EmptyHunyuanLatentVideo to width 832, height 480, length 33 and batch_size 1. Set KSampler to 30 steps, CFG 6, uni_pc sampler, simple scheduler, denoise 1. Keep ModelSamplingSD3 shift at 8. Set seed to 20260928 and control_after_generate to fixed. CreateVideo must be 16 fps; SaveVideo is MP4/H.264. The result is 33 frames ÷ 16 fps ≈ 2.06 seconds, silent. Do not add interpolation or an upscaler for the first run.

Run and inspect the playable clip

Click Run once. Wait for the active queue item to finish; the queue shows progress. The first run can take longer while models load. Open the SaveVideo preview and play it. Verify motion, 832 × 480 dimensions, approximately 2.06 seconds at 16 fps and no audio. A completed render is the success check; importing a graph alone is not.

Save your result and return later

Use the SaveVideo preview menu to download your MP4. ComfyUI also saves it in the configured output folder’s YouRunAI subfolder. Find that folder in Desktop Settings → Storage → Shared Output; if shared output is disabled, use the instance’s Manage → Storage → Output Directory. Save/export the workflow JSON after editing settings so you can reopen the same setup. Change one prompt or seed and click Run for another result. To stop an unwanted render, use the queue’s Cancel/Interrupt control. To shut down, return to the instance card → ⋮ → Stop; tomorrow, open Comfy Desktop, click that card and load your saved JSON. No terminal launch commands are needed.

SUCCESS CHECK · Wan2.1 T2V 1.3B · FP16

Your clip is playable and saved

The SaveVideo preview plays a silent 832 × 480 MP4 of about 2.06 seconds. Its file is in your configured output folder’s YouRunAI subfolder. You can reopen the saved workflow, keep the same files and change one prompt or seed to make another clip.

Verified refers to the linked model/runtime documentation and reviewed graph structure. Hardware advice is Estimated. No render-time or YouRunAI physical-execution claim is made. This focused setup uses publisher model packages; it does not bundle a speculative uncensored LoRA or claim that every third-party derivative works.

Back to setup steps

When it doesn’t go to plan

A loader says the model file is missing

Check the exact filename in this package’s file tree and finish the Desktop download. If downloading manually, put the file inside the Primary shared model folder’s indicated subfolder; for manual/portable ComfyUI use its models folder. Reload the workflow and reselect the file. If it remains missing, stop the instance from its card menu and click the card to relaunch. A .safetensors file must not be a partial download or an HTML error page.

The GPU check fails or generation falls back to the CPU

Open the instance card → ⋮ → Manage → About and inspect Hardware and PyTorch. Confirm NVIDIA/CUDA, AMD/ROCm, Intel/XPU or Apple/MPS for your route. Update the vendor driver if needed. Desktop can change the PyTorch stack from its Manage panel (About → Change PyTorch; some versions place the picker on Update). Use an offered stable stack compatible with your actual GPU and OS. On Linux AMD, resolve any missing /dev/kfd or GPU-access warning using the vendor instructions. More VRAM does not fix an unsupported backend.

A core node is missing when the JSON is loaded

Update the active ComfyUI instance through its card → Manage → Update → Check for update, using Stable, then stop and reopen it and reload the JSON. Updating only the Desktop launcher does not update an older instance. The supplied graphs use ComfyUI core nodes; do not install unrelated custom-node packs to replace them. If a node is still absent in the current stable release, compare the linked official template requirements before changing release channels.

Generation runs out of memory

Cancel the current job and close other GPU applications. Keep batch_size 1. Reduce length from 33 to 17 frames (about 1.06 seconds at 16 fps); use 4n+1 frame counts. Keep width and height divisible by 16. The text encoder can be offloaded; ensure at least 32 GB system RAM. If automatic offload is insufficient, add --lowvram in the instance’s Manage → Startup Args, then stop and reopen it. On Mac, reduce workload and close apps rather than disabling the system memory safety limit.

The clip duration or motion looks wrong

Confirm CreateVideo is 16 fps and the latent length is 33; changing FPS changes playback duration, not generated motion. Keep the fixed seed and try a simpler positive motion prompt. For image-to-video, confirm the uploaded image reaches both the vision encoder and WanImageToVideo. A T2V checkpoint cannot replace the I2V checkpoint.

REFERENCE LIBRARY

Sources and files

Original instructions, model files, and compatibility notes behind this setup.

11 SOURCES

01Official Wan ComfyUI examplescomfyanonymous.github.io 02Wan model publishergithub.com 03Official ComfyUI graph sourcegithub.com 04AMD GPU / OS compatibilityrocm.docs.amd.com 05Intel XPU setupdocs.pytorch.org 06Apple Metal setupdeveloper.apple.com 07Comfy Desktop installationdocs.comfy.org 08Comfy Desktop: manage GPU, updates and storagedocs.comfy.org 09Shared models and output foldersdocs.comfy.org 10Automatic model downloads from workflowsdocs.comfy.org 11Official built-in Wan 2.1 Text to Video templategithub.com

The model behind this workflow

Wan2.1 · 1.3B

Keep exploring

Text

SETUP GUIDE

Qwen3.5 · 9B private chat setup

Source-backed package and platform-route plan for private local chat with Qwen3.5 · 9B. Preserves the official Ollama 9B package, a smaller 4B family fallback, and a clearly labeled community uncensored GGUF option.

Freshness 38 out of 100. Release age: 254 days old, Feb 27, 2026. Measures age, not quality.

Build a private coding assistant with Qwen3.8 27B

Run Qwen3.8 27B with Ollama, connect it to Cline in VS Code, and make one reviewable code change in a tiny local project.

Freshness 69 out of 100. Repository age: 95 days old, Aug 5, 2026. Measures age, not quality.

Arena Open Source Web coding: rank 12 of 62. Ranked model: Qwen3.8-27B. Original model ranking, not a benchmark of this package. Export dated Nov 6, 2026. Source checked Nov 7, 2026. Human preference ranking, not hardware suitability.+3

SOFTWAREOllama + Visual Studio Code + Cline + Python

Create images locally with FLUX.2 Klein

Generate images from text prompts in ComfyUI with the fast distilled or more adjustable base 4B model. Save your results and reuse the visual workflow.

Freshness 32 out of 100. Release age: 297 days old, Jan 15, 2026. Measures age, not quality.

SOFTWAREComfyUI

LOCALRENTED GPU

Verified source