This GGUF file is a direct conversion of Wan-AI/Wan2.2-T2V-A14B Since this is a quantized model, all original licensing terms and usage restrictions remain in effect. Usage The model can be used with the ComfyUI custom node ComfyUI-GGUF by city96 Place model files in ComfyUI/models/unet see the GitHub readme for further installation instructions.
drag gguf to >./ComfyUI/models/diffusionmodels - drag t5xxl-um to >./ComfyUI/models/textencoders - drag vae to >./ComfyUI/models/vae - for i2v model, drag clip-vision-h to >./ComfyUI/models/clipvision - run the.bat file in the main directory (assume you are…
Parameters—
Context—
Weights1.2 TB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads26.8k
Model Card
By Cαlcμ, published under apache-2.0, revision a06b67e9de7a.
drag gguf to >./ComfyUI/models/diffusionmodels - drag t5xxl-um to >./ComfyUI/models/textencoders - drag vae to >./ComfyUI/models/vae - for i2v model, drag clip-vision-h to >./ComfyUI/models/clipvision - run the.bat file in the main directory (assume you are using gguf pack below) - if you opt to use fp8 scaled umt5xxl encoder (if applies to any fp8 scale t5 actually), please use cpu offload (switch from default to cpu under device in gguf clip loader; won't affect speed); btw, it works fine for both gguf umt5xxl and gguf vae - drag any demo video (below) to > your browser for workflow - pig is a lazy architecture for gguf node; it applies to all model, encoder and vae gguf file(s); if you…
Read Cαlcμ's full model card
gguf quantized version of wan video
- drag gguf to >
./ComfyUI/models/diffusion_models - drag t5xxl-um to >
./ComfyUI/models/text_encoders - drag vae to >
./ComfyUI/models/vae
workflow
- for i2v model, drag clip-vision-h to >
./ComfyUI/models/clip_vision - run the .bat file in the main directory (assume you are using gguf pack below)
- if you opt to use fp8 scaled umt5xxl encoder (if applies to any fp8 scale t5 actually), please use cpu offload (switch from default to cpu under device in gguf clip loader; won't affect speed); btw, it works fine for both gguf umt5xxl and gguf vae
- drag any demo video (below) to > your browser for workflow
review
pigis a lazy architecture for gguf node; it applies to all model, encoder and vae gguf file(s); if you try to run it in comfyui-gguf node, you might need to manually addpigin it's IMG_ARCH_LIST (under loader.py); easier than you edit the gguf file itself; btw, model architecture which compatible with comfyui-gguf, includingwan, should work in gguf node- 1.3b model: t2v, vace gguf is working fine; good for old or low end machine
run it with diffusers (alternative 1)
import torch
from transformers import UMT5EncoderModel
from diffusers import AutoencoderKLWan, WanVACEPipeline, WanVACETransformer3DModel, GGUFQuantizationConfig
from diffusers.schedulers.scheduling_unipc_multistep import UniPCMultistepScheduler
from diffusers.utils import export_to_video
model_path = "https://huggingface.co/calcuis/wan-gguf/blob/main/wan2.1-v5-vace-1.3b-q4_0.gguf"
transformer = WanVACETransformer3DModel.from_single_file(
model_path,
quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
torch_dtype=torch.bfloat16,
)
text_encoder = UMT5EncoderModel.from_pretrained(
"chatpig/umt5xxl-encoder-gguf",
gguf_file="umt5xxl-encoder-q4_0.gguf",
torch_dtype=torch.bfloat16,
)
vae = AutoencoderKLWan.from_pretrained(
"callgg/wan-decoder",
subfolder="vae",
torch_dtype=torch.float32
)
pipe = WanVACEPipeline.from_pretrained(
"callgg/wan-decoder",
transformer=transformer,
text_encoder=text_encoder,
vae=vae,
torch_dtype=torch.bfloat16
)
flow_shift = 3.0
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=flow_shift)
pipe.enable_model_cpu_offload()
pipe.vae.enable_tiling()
prompt = "a pig moving quickly in a beautiful winter scenery nature trees sunset tracking camera"
negative_prompt = "blurry ugly bad"
output = pipe(
prompt=prompt,
negative_prompt=negative_prompt,
width=720,
height=480,
num_frames=57,
num_inference_steps=24,
guidance_scale=2.5,
conditioning_scale=0.0,
generator=torch.Generator().manual_seed(0),
).frames[0]
export_to_video(output, "output.mp4", fps=16)
run it with gguf-connector (alternative 2)
ggc v2
update
- wan2.1-v5-vace-1.3b: except block weights, all in
f32status (avoid triggering time/text embedding key error for inference usage)
reference
Identity and Version
- Repository
- calcuis/wan-gguf
- Publisher
- Cαlcμ
- Task
- Text to video
- Modality
- Video
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- en
- Revision
- a06b67e9de7a93117b8734c24bcae740dfd2cdad
- First published
- 2025-02-26
- Last updated
- 2025-07-08
Files and Weights
133 files, 1.2 TB in total. The weights are 110 files totalling 1.2 TB in gguf, safetensors.
Weights110 files · 1.2 TB
Configuration6 files · 64.2 KB
Documentation1 file · 6.9 KB
Other15 files · 13.4 MB
Repository1 file · 10.1 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| clip_vision_h_fp16.safetensors | Weights | 1.3 GB | 64a7ef761bfc |
| clip_vision_h_fp8_e4m3fn.safetensors | Weights | 632.1 MB | 644857118a5e |
| t5xxl_um_fp16.safetensors | Weights | 11.4 GB | 7b8850f1961e |
| t5xxl_um_fp8_e4m3fn_scaled.safetensors | Weights | 6.7 GB | c3355d30191f |
| wan2.1-flf2v-720p-14b-f32-00001-of-00005.gguf | Weights | 14.2 GB | 549fe4c8f47b |
| wan2.1-flf2v-720p-14b-f32-00002-of-00005.gguf | Weights | 14.2 GB | 4dd9077285d4 |
| wan2.1-flf2v-720p-14b-f32-00003-of-00005.gguf | Weights | 14.2 GB | 2bc2f9b87041 |
| wan2.1-flf2v-720p-14b-f32-00004-of-00005.gguf | Weights | 14.2 GB | 925c094bf5fc |
| wan2.1-flf2v-720p-14b-f32-00005-of-00005.gguf | Weights | 9.0 GB | f52616eba493 |
| wan2.1-flf2v-720p-14b-q2_k.gguf | Weights | 7.9 GB | 9d290dd78d9f |
| wan2.1-flf2v-720p-14b-q3_k_m.gguf | Weights | 9.2 GB | c230874ee831 |
| wan2.1-flf2v-720p-14b-q3_k_s.gguf | Weights | 8.6 GB | 003780757c35 |
| wan2.1-flf2v-720p-14b-q4_0.gguf | Weights | 10.3 GB | f0d9d1db4a0d |
| wan2.1-flf2v-720p-14b-q4_1.gguf | Weights | 11.1 GB | fc5d5e911521 |
| wan2.1-flf2v-720p-14b-q4_k_m.gguf | Weights | 11.3 GB | 4da74fc03bfa |
| wan2.1-flf2v-720p-14b-q4_k_s.gguf | Weights | 10.4 GB | ef02b09d9972 |
| wan2.1-flf2v-720p-14b-q5_0.gguf | Weights | 12.3 GB | e7b4a379bdd8 |
| wan2.1-flf2v-720p-14b-q5_1.gguf | Weights | 13.1 GB | e80d0444232d |
| wan2.1-flf2v-720p-14b-q5_k_m.gguf | Weights | 12.7 GB | c3a13722c9ee |
| wan2.1-flf2v-720p-14b-q5_k_s.gguf | Weights | 12.1 GB | 747c0cbb14eb |
| wan2.1-flf2v-720p-14b-q6_k.gguf | Weights | 14.2 GB | f0c1ea9a94d1 |
| wan2.1-flf2v-720p-14b-q8_0.gguf | Weights | 18.1 GB | 99020aba9a52 |
| wan2.1-i2v-14b-480p-q2_k.gguf | Weights | 7.9 GB | 9bf0a9b8f599 |
| wan2.1-i2v-14b-480p-q3_k_m.gguf | Weights | 8.6 GB | a0cb40c39201 |
| wan2.1-i2v-14b-480p-q4_0.gguf | Weights | 10.2 GB | c04b220c1b8e |
| wan2.1-i2v-14b-480p-q4_1.gguf | Weights | 11.1 GB | 17d85e7bf7d4 |
| wan2.1-i2v-14b-480p-q4_k_m.gguf | Weights | 11.3 GB | f1aa553f85e3 |
| wan2.1-i2v-14b-480p-q5_0.gguf | Weights | 12.3 GB | 5090377bec1b |
| wan2.1-i2v-14b-480p-q5_1.gguf | Weights | 13.1 GB | bdbfeb40a473 |
| wan2.1-i2v-14b-480p-q5_k_m.gguf | Weights | 12.7 GB | 0827a2955040 |
| wan2.1-i2v-14b-480p-q6_k.gguf | Weights | 14.2 GB | fcd850a31604 |
| wan2.1-i2v-14b-480p-q8_0.gguf | Weights | 18.1 GB | 0398f93e53aa |
| wan2.1-i2v-14b-720p-q2_k.gguf | Weights | 7.9 GB | 32fb12286d1a |
| wan2.1-i2v-14b-720p-q3_k_m.gguf | Weights | 8.6 GB | bcd1fb05e702 |
| wan2.1-i2v-14b-720p-q4_0.gguf | Weights | 10.2 GB | 7cddb81cda11 |
| wan2.1-i2v-14b-720p-q4_1.gguf | Weights | 11.1 GB | 13575bb81fcf |
| wan2.1-i2v-14b-720p-q4_k_m.gguf | Weights | 11.3 GB | 65a3e0a8da61 |
| wan2.1-i2v-14b-720p-q5_0.gguf | Weights | 12.3 GB | fa56850aa912 |
| wan2.1-i2v-14b-720p-q5_1.gguf | Weights | 13.1 GB | 6a660eb81cf4 |
| wan2.1-i2v-14b-720p-q5_k_m.gguf | Weights | 12.7 GB | 05288c44806a |
| wan2.1-i2v-14b-720p-q6_k.gguf | Weights | 14.2 GB | 20f9fbbe0be1 |
| wan2.1-i2v-14b-720p-q8_0.gguf | Weights | 18.1 GB | f5898730c655 |
| wan2.1-i2v-480p-14b-f32-00001-of-00004.gguf | Weights | 17.2 GB | b6d6fffb2c63 |
| wan2.1-i2v-480p-14b-f32-00002-of-00004.gguf | Weights | 17.2 GB | 97e9f352bec0 |
| wan2.1-i2v-480p-14b-f32-00003-of-00004.gguf | Weights | 17.2 GB | f0b41c2b5f6f |
| wan2.1-i2v-480p-14b-f32-00004-of-00004.gguf | Weights | 14.0 GB | 17b5c085c6f5 |
| wan2.1-i2v-720p-14b-f32-00001-of-00004.gguf | Weights | 17.2 GB | 36ff8b813126 |
| wan2.1-i2v-720p-14b-f32-00002-of-00004.gguf | Weights | 17.2 GB | 4deb295536f1 |
| wan2.1-i2v-720p-14b-f32-00003-of-00004.gguf | Weights | 17.2 GB | 80e8fcd8e26b |
| wan2.1-i2v-720p-14b-f32-00004-of-00004.gguf | Weights | 14.0 GB | a858aae840e6 |
| wan2.1-t2v-14b-f32-00001-of-00002.gguf | Weights | 41.9 GB | 43d58a66c689 |
| wan2.1-t2v-14b-f32-00002-of-00002.gguf | Weights | 15.2 GB | 1356532e363b |
| wan2.1-t2v-14b-q2_k.gguf | Weights | 7.0 GB | 4f1be4d0cca0 |
| wan2.1-t2v-14b-q3_k_m.gguf | Weights | 7.6 GB | 5252437353cd |
| wan2.1-t2v-14b-q4_0.gguf | Weights | 9.0 GB | 3af9b947848d |
| wan2.1-t2v-14b-q4_1.gguf | Weights | 9.7 GB | 902d63e6950c |
| wan2.1-t2v-14b-q4_k_m.gguf | Weights | 10.1 GB | d96b55715ef5 |
| wan2.1-t2v-14b-q5_0.gguf | Weights | 10.8 GB | fcfcdc942181 |
| wan2.1-t2v-14b-q5_1.gguf | Weights | 11.5 GB | 4fdea22431a6 |
| wan2.1-t2v-14b-q5_k_m.gguf | Weights | 11.3 GB | 57e931cf7b1f |
| wan2.1-t2v-14b-q6_k.gguf | Weights | 12.5 GB | 048ac61a0be6 |
| wan2.1-t2v-14b-q8_0.gguf | Weights | 15.9 GB | b2db8395ab0b |
| wan2.1-v1-vace-1.3b-q4_0.gguf | Weights | 1.3 GB | bc5e1701d61c |
| wan2.1-v1-vace-1.3b-q5_0.gguf | Weights | 1.6 GB | fbffa52e5317 |
| wan2.1-v1-vace-1.3b-q8_0.gguf | Weights | 2.4 GB | 506eb52947f9 |
| wan2.1-v2-vace-1.3b-q4_0.gguf | Weights | 1.3 GB | c4fc8311e07c |
| wan2.1-v2-vace-1.3b-q5_0.gguf | Weights | 1.6 GB | 4524939e4c27 |
| wan2.1-v2-vace-1.3b-q8_0.gguf | Weights | 2.4 GB | b6b6081a7578 |
| wan2.1-v2-vace-14b-q2_k.gguf | Weights | 8.3 GB | 0c55f85de3d1 |
| wan2.1-v2-vace-14b-q3_k_m.gguf | Weights | 9.1 GB | 20c7d0308cc7 |
| wan2.1-v2-vace-14b-q4_0.gguf | Weights | 10.8 GB | 2505dd64c8f7 |
| wan2.1-v2-vace-14b-q4_1.gguf | Weights | 11.6 GB | ea5a42fc044d |
| wan2.1-v2-vace-14b-q4_k_m.gguf | Weights | 12.1 GB | 9e3206313cc6 |
| wan2.1-v2-vace-14b-q5_0.gguf | Weights | 12.9 GB | 8d27d094baa3 |
| wan2.1-v2-vace-14b-q5_1.gguf | Weights | 13.8 GB | 755026a2e6cc |
| wan2.1-v2-vace-14b-q5_k_m.gguf | Weights | 13.5 GB | a4419315733e |
| wan2.1-v2-vace-14b-q6_k.gguf | Weights | 15.0 GB | b5d019445b26 |
| wan2.1-v2-vace-14b-q8_0.gguf | Weights | 19.1 GB | 590aace3bee9 |
| wan2.1-v4-vace-1.3b-q4_0.gguf | Weights | 1.2 GB | dd87b3ad9c69 |
| wan2.1-v4-vace-1.3b-q5_0.gguf | Weights | 1.5 GB | 378ee83655f3 |
| wan2.1-v4-vace-1.3b-q8_0.gguf | Weights | 2.3 GB | 3f4f01cd03e1 |
| wan2.1-v5-vace-1.3b-q4_0.gguf | Weights | 1.3 GB | 44b969e51b4f |
| wan2.1-v5-vace-1.3b-q5_0.gguf | Weights | 1.6 GB | 904bfc64f684 |
| wan2.1-v5-vace-1.3b-q8_0.gguf | Weights | 2.4 GB | be7390dcf865 |
| wan2.1-vace-14b-f32-00001-of-00002.gguf | Weights | 36.7 GB | 8e7b2c29f413 |
| wan2.1-vace-14b-f32-00002-of-00002.gguf | Weights | 32.7 GB | 7ef151a551a1 |
| wan2.1-vace-14b-q2_k.gguf | Weights | 6.8 GB | 5570db7474e0 |
| wan2.1-vace-14b-q3_k_l.gguf | Weights | 9.8 GB | 4434ca76226d |
| wan2.1-vace-14b-q3_k_m.gguf | Weights | 9.1 GB | aa59323898c5 |
| wan2.1-vace-14b-q3_k_s.gguf | Weights | 8.3 GB | e0f337001ba8 |
| wan2.1-vace-14b-q4_0.gguf | Weights | 10.8 GB | 39f6af35f579 |
| wan2.1-vace-14b-q4_1.gguf | Weights | 11.6 GB | c7c8b927869a |
| wan2.1-vace-14b-q4_k_m.gguf | Weights | 12.1 GB | 308cfd41da74 |
| wan2.1-vace-14b-q4_k_s.gguf | Weights | 11.0 GB | fb0608c45771 |
| wan2.1-vace-14b-q5_0.gguf | Weights | 12.9 GB | d3310860a253 |
| wan2.1-vace-14b-q5_1.gguf | Weights | 13.8 GB | c5254918e80f |
| wan2.1-vace-14b-q5_k_m.gguf | Weights | 13.5 GB | 785d0435287f |
| wan2.1-vace-14b-q5_k_s.gguf | Weights | 12.7 GB | 844e29e96ff1 |
| wan2.1-vace-14b-q6_k.gguf | Weights | 15.0 GB | bdeda1d0c69e |
| wan2.1-vace-14b-q8_0.gguf | Weights | 19.1 GB | 1ec35c3de211 |
| wan2.1_t2v_1.3b-q4_0.gguf | Weights | 916.9 MB | aa35d5d114d7 |
| wan2.1_t2v_1.3b-q5_0.gguf | Weights | 1.1 GB | 9ffa82db5cf3 |
| wan2.1_t2v_1.3b-q8_0.gguf | Weights | 1.6 GB | 8f10260cc264 |
| wan2.1_t2v_1.3b_fp16.safetensors | Weights | 2.8 GB | 6f999b0d6cb9 |
| wan2.1_t2v_1.3b_fp32-f32.gguf | Weights | 5.7 GB | 0192b22aec6a |
| wan2.1_t2v_1.3b_fp32.safetensors | Weights | 5.7 GB | 3d6c7f5d31da |
| wan2.1_vace_1.3b_preview-f16.gguf | Weights | 4.3 GB | 41b78f8d6060 |
| wan2.1_vace_1.3b_preview-f32.gguf | Weights | 8.6 GB | 3f73c0016580 |
| wan_2.1_vae_fp32-f16.gguf | Weights | 253.9 MB | 290e463b9d66 |
| wan_2.1_vae_fp8_e4m3fn.safetensors | Weights | 126.9 MB | fe1c43442d6c |
| workflow-wan-flf2v.json | Configuration | 11.7 KB | — |
| workflow-wan-i2v.json | Configuration | 6.6 KB | — |
| workflow-wan-t2v.json | Configuration | 4.9 KB | — |
| workflow-wan-vace-i2v.json | Configuration | 13.8 KB | — |
| workflow-wan-vace-t2v.json | Configuration | 13.6 KB | — |
| workflow-wan-vace-v2v.json | Configuration | 13.7 KB | — |
| README.md | Documentation | 6.9 KB | — |
| samples\ComfyUI_00001_.webp | Other | 1.2 MB | e9d0f5b03cc5 |
| samples\ComfyUI_00002_.webp | Other | 685.7 KB | cc6d59c0ab8a |
| samples\ComfyUI_00003_.webp | Other | 1.5 MB | c9f77760a6a7 |
| samples\ComfyUI_00004_.webp | Other | 1.4 MB | ea1e4d4a86bc |
| samples\ComfyUI_00005_.webp | Other | 1.3 MB | 29e9928eae99 |
| samples\ComfyUI_00006_.webp | Other | 403.5 KB | 87a2c9216085 |
| samples\ComfyUI_00007_.webp | Other | 958.5 KB | bb62bcf5bcb6 |
| samples\ComfyUI_00008_.webp | Other | 1.2 MB | 485efe75dbe8 |
| samples\ComfyUI_00009_.webp | Other | 988.4 KB | 808d33e7b0ac |
| samples\ComfyUI_00010_.webp | Other | 1.3 MB | 9d585d2f9fb1 |
| samples\ComfyUI_00011_.mp4 | Other | 360.8 KB | 217518cba72b |
| samples\ComfyUI_00012_.mp4 | Other | 459.3 KB | c8ddeb16eede |
| samples\ComfyUI_00013_.mp4 | Other | 551.7 KB | b66a6b4cad6b |
| samples\first.png | Other | 464.7 KB | c88ea154ce45 |
| samples\last.png | Other | 700.1 KB | 87cce5c49699 |
| .gitattributes | Repository | 10.1 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 1.2 TB
Download from Cαlcμ
Released by Cαlcμ through its official repository on Hugging Face. Read the license.
Built From
- Derived from Comfy-Org/Wan_2.1_ComfyUI_repackaged
- Quantized from Comfy-Org/Wan_2.1_ComfyUI_repackaged
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.2 TB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About wan-gguf
Can I use wan-gguf commercially?
Yes. wan-gguf is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Similar Models
A LoRA for MiniMax-H3 that renders joint video + synchronized stereo audio in as few as 4 sampling steps instead of the usual ~20 — a ~5× sampling speedup — and keeps getting better as you add steps. For most work, use minimaxh3turbov4step600ema.safetensors. It's the markedly better micro-detail (faces, fingers, fine texture), and the over-sharpening / plastic look of the earlier v1 (~850) line is fully resolved. v4 introduced a static-frame enhancement — a big win for static and small-motion content. The one trade-off shows up only at 4 steps with large, fast motion, where v4 can produce motion-smear / trailing ghosting (we're actively fixing this). Two things address it: - Use 6–8 steps.…
This repository contains MiniMax-H3 Turbo LoRAs converted and optimized for ComfyUI: These LoRAs accelerate MiniMax-H3 video and synchronized-audio generation by reducing the required number of sampling steps. Newly added LoRA, located in the experimental/ folder: Manual recommended sigmas: 3-step 1.0, 0.961165, 0.853333, 0.0 4-step 1.0, 0.970874, 0.907249, 0.640000, 0.0 Three LoRAs extracted from VDN-H3 8 step: The main 8-step LoRA works on both FL2VA and Ref2VA. If you are running a pruned base, choose the pruned version that corresponds to your base — the pruned versions need their own matching pruned base. Three dynamically resized BF16 LoRAs are now included. Their source weights were…
Sulphur 2 An uncensored video generation model based on LTX 2.3 supporting both t2v and i2v natively, as well as all of the other ltx 2.3 formats. Follow us on X Join our Discord Support the next version of the project, even just a few dollars would go a long way: Kofi To get started with the model, I recommend downloading either of the dev versions, (fp8mixed or bf16) and downloading the distill lora provided. By the way, I'm aware the workflows contain sulphurfinal right now, just use the lora or use the full models, don't use both at the same time. This model contains a prompt enhancer. The easiest way to get started with the prompt enhancer is by using it on lmstudio. The way to…
Wan2.1 is an open-source suite of video foundation models, compatible with consumer-grade GPUs, that excels in various video generation tasks like text-to-video, image-to-video, and video editing, even supporting visual text generation. Download models using huggingface-cli: You can also download directly from this page. This model is a derivative work of the original model licensed under the Apache 2.0 License, and is therefore distributed under the terms of the same license. Thanks to Patrick Gillespie for creating the ASCII text art tool used in this project https://patorjk.com/software/taag/ Wan-AI for the Wan model https://huggingface.co/Wan-AI/Wan2.1-VACE-1.3B…
Wan2.1 is an open-source suite of video foundation models, compatible with consumer-grade GPUs, that excels in various video generation tasks like text-to-video, image-to-video, and video editing, even supporting visual text generation. Download models using huggingface-cli: You can also download directly from this page. This model is a derivative work of the original model licensed under the Apache 2.0 License, and is therefore distributed under the terms of the same license. Thanks to Patrick Gillespie for creating the ASCII text art tool used in this project https://patorjk.com/software/taag/ Wan-AI for the Wan model https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B…