# A program to use all modules

**URL:** <https://discuss.huggingface.co/t/a-program-to-use-all-modules/169015>\
**Category:** Beginners\
**Created:** [October 8, 2025, 6:55am UTC](https://discuss.huggingface.co/t/a-program-to-use-all-modules/169015 "2025-10-08T06:55:19Z")\
**Posts on this page:** 15\
**Page:** 1

<div class="post-metadata">

**Author:** ![Vihaananand](https://avatars.discourse-cdn.com/v4/letter/v/47e85d/32.png) [@Vihaananand](https://discuss.huggingface.co/u/Vihaananand)\
**Post date:** [October 8, 2025, 6:55am UTC](https://discuss.huggingface.co/t/a-program-to-use-all-modules/169015/1 "2025-10-08T06:55:19Z")

</div>

Hello,

I use Linux and I want to have an integrated environment where I can use all the modules. For example, Fooocus is only for producing photos, and if I want to produce videos, I have to install ComfyUI separately. Is there an environment where I can have all these features in one place?

Thank you.

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\
**Post date:** [October 8, 2025, 8:20am UTC](https://discuss.huggingface.co/t/a-program-to-use-all-modules/169015/2 "2025-10-08T08:20:41Z")

</div>

While it’s not impossible to link multiple workflows together, why not just use [software that supports both T2V and I2V](https://github.com/vladmandic/sdnext)?

---

<div class="post-metadata">

**Author:** ![Vihaananand](https://avatars.discourse-cdn.com/v4/letter/v/47e85d/32.png) [@Vihaananand](https://discuss.huggingface.co/u/Vihaananand)\
**Post date:** [October 8, 2025, 9:32am UTC](https://discuss.huggingface.co/t/a-program-to-use-all-modules/169015/3 "2025-10-08T09:32:40Z")

</div>

Hello,

Thank you so much for your reply.

Do I need a desktop environment to run this program? My Linux server does not have a graphical environment.

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\
**Post date:** [October 8, 2025, 9:35am UTC](https://discuss.huggingface.co/t/a-program-to-use-all-modules/169015/4 "2025-10-08T09:35:05Z")

</div>

(post deleted by author)

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\
**Post date:** [October 8, 2025, 9:37am UTC](https://discuss.huggingface.co/t/a-program-to-use-all-modules/169015/5 "2025-10-08T09:37:09Z")

</div>

If a GUI isn’t necessary, I think [using Diffusers for both T2V/I2V](https://huggingface.co/collections/Wan-AI/wan22-diffusers-68ac4d984d6db6f641a8aaf1) is the simplest approach.

---

<div class="post-metadata">

**Author:** ![Vihaananand](https://avatars.discourse-cdn.com/v4/letter/v/47e85d/32.png) [@Vihaananand](https://discuss.huggingface.co/u/Vihaananand)\
**Post date:** [October 8, 2025, 9:46am UTC](https://discuss.huggingface.co/t/a-program-to-use-all-modules/169015/6 "2025-10-08T09:46:26Z")

</div>

Sorry, what I meant was, does the program itself require a graphical desktop environment to run?

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\
**Post date:** [October 8, 2025, 9:49am UTC](https://discuss.huggingface.co/t/a-program-to-use-all-modules/169015/7 "2025-10-08T09:49:18Z")

</div>

> does the program itself require a graphical desktop environment to run?

I think so. From the names of the software mentioned, I thought it was about GUIs…

---

<div class="post-metadata">

**Author:** ![Vihaananand](https://avatars.discourse-cdn.com/v4/letter/v/47e85d/32.png) [@Vihaananand](https://discuss.huggingface.co/u/Vihaananand)\
**Post date:** [October 8, 2025, 9:51am UTC](https://discuss.huggingface.co/t/a-program-to-use-all-modules/169015/8 "2025-10-08T09:51:47Z")

</div>

Sure, but does it just run as a service? If yes, then there is no need for a graphical environment and it can be connected remotely.

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\
**Post date:** [October 8, 2025, 9:58am UTC](https://discuss.huggingface.co/t/a-program-to-use-all-modules/169015/9 "2025-10-08T09:58:49Z")

</div>

Hmm… I don’t think SD.Next is suited for that kind of use. It’s maybe purely a desktop GUI. If you want to run T2V or I2V as a service, it’s probably easier to use [ComfyUI CLI](https://docs.comfy.org/comfy-cli/reference) or [Diffusers](https://huggingface.co/docs/diffusers/using-diffusers/create_a_server) with shell scripts or Python. [Using MCP](https://github.com/joenorton/comfyui-mcp-server) is an option, but it would be overkill.

---

<div class="post-metadata">

**Author:** ![Vihaananand](https://avatars.discourse-cdn.com/v4/letter/v/47e85d/32.png) [@Vihaananand](https://discuss.huggingface.co/u/Vihaananand)\
**Post date:** [October 8, 2025, 12:44pm UTC](https://discuss.huggingface.co/t/a-program-to-use-all-modules/169015/10 "2025-10-08T12:44:49Z")

</div>

I will test it.

---

<div class="post-metadata">

**Author:** ![Vihaananand](https://avatars.discourse-cdn.com/v4/letter/v/47e85d/32.png) [@Vihaananand](https://discuss.huggingface.co/u/Vihaananand)\
**Post date:** [October 11, 2025, 9:33am UTC](https://discuss.huggingface.co/t/a-program-to-use-all-modules/169015/11 "2025-10-11T09:33:53Z")

</div>

Hello,

Unfortunately, when downloading the WAN modules, I get the following error:

```auto
2025-10-11T09:25:10.187925Z WARN Reqwest(reqwest::Error { kind: Request, url: "https://transfer.xethub.hf.co/xorbs/default/8e191b93cc43f7a2c3ebcd8333d35cd90c140ef72cd8d564ae2dd5fe1e2c7894?X-Xet-Signed-Range=bytes%3D0-63159569&X-Xet-Session-Id=01K7997CS5PS8H1WXPQXVRRJAX&Expires=1760178120&Policy=eyJTdGF0ZW1lbnQiOlt7IlJlc291cmNlIjoiaHR0cHM6Ly90cmFuc2Zlci54ZXRodWIuaGYuY28veG9yYnMvZGVmYXVsdC84ZTE5MWI5M2NjNDNmN2EyYzNlYmNkODMzM2QzNWNkOTBjMTQwZWY3MmNkOGQ1NjRhZTJkZDVmZTFlMmM3ODk0P1gtWGV0LVNpZ25lZC1SYW5nZT1ieXRlcyUzRDAtNjMxNTk1NjkmWC1YZXQtU2Vzc2lvbi1JZD0wMUs3OTk3Q1M1UFM4SDFXWFBRWFZSUkpBWCIsIkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTc2MDE3ODEyMH19fV19&Signature=dLBAzRwV19fmL3K6AXTyosRpPWPVPV4BkGU3CDc4tIk-OqPWa1eCOXt8MOyEAChN0vU4S2Pb9w13C286scqR9Mg-38p13C~IeCtvCn8A~y1Y1YQn7iEYW~06RVpjZCwnOg7oEQsp9bynM8zqI~6skGUJ~4Z4XYDVR76UMQ2fYbS~4yNl2Vd~TMFCijFU2Km-8xV1r3Xs5l5LHqJwJ41UZSUzZcLagYz4bHAfxNRSpMElmkEFreSn8pUHBscRN9m8AOGNwHRpHKbNvTiVM5JSDDEaboLkBunw-VV9QSH~bFVIlLIMH1EcExpYwWT14q4bRP8FNoZTPK77~u9sUnBX0A__&Key-Pair-Id=K2L8F4GPSG1IFC", source: hyper_util::client::legacy::Error(SendRequest, hyper::Error(IncompleteMessage)) }). Retrying...

```

I have two questions:

1- Can I download the module manually?

2- What other module can do the WAN job?

Thank you.

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](https://discuss.huggingface.co/u/John6666)\
**Post date:** [October 11, 2025, 1:35pm UTC](https://discuss.huggingface.co/t/a-program-to-use-all-modules/169015/12 "2025-10-11T13:35:38Z")

</div>

Avoiding the issue itself is easy, but Rust is throwing errors…?  
I also encountered errors when using an old version of Candle before, so this might be a similar case. Just in case, I’ll ping @jsulz

* * *

Yes to both.

## 1) Download WAN manually

Use the Hugging Face tools. Bypass the flaky Xet path if needed. As of 2025-10-11 these methods are current.

### A) CLI with file filters

```bash
pip install -U "huggingface_hub[cli]" hf_transfer
# Option 1: bypass Xet entirely
export HF_HUB_DISABLE_XET=1
# Option 2: try Rust downloader (faster on good links)
# export HF_HUB_ENABLE_HF_TRANSFER=1
# TI2V-5B (720p) essentials
hf download Wan-AI/Wan2.2-TI2V-5B-Diffusers \
  --include "diffusion_pytorch_model-*.safetensors" \
           "diffusion_pytorch_model.safetensors.index.json" \
           "Wan2.2_VAE.pth" "models_t5_umt5-xxl-enc-bf16.pth" \
           "config.json" "configuration.json" \
  --local-dir ./Wan2.2-TI2V-5B

```

CLI supports `--include/--exclude`, `--local-dir`, and works with the env vars above. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/guides/cli "Command Line Interface (CLI)"))

### B) Python API (`snapshot_download`) with patterns

```python
import os
os.environ["HF_HUB_DISABLE_XET"]="1" # or try HF_HUB_ENABLE_HF_TRANSFER=1
from huggingface_hub import snapshot_download
snapshot_download(
  repo_id="Wan-AI/Wan2.2-T2V-A14B-Diffusers",
  local_dir="./Wan2.2-T2V-A14B-Diffusers",
  allow_patterns=[
    "transformer/diffusion_pytorch_model-*.safetensors",
    "transformer/diffusion_pytorch_model.safetensors.index.json",
    "vae/*","text_encoder/*","tokenizer/*","scheduler/*","model_index.json",
  ],
)

```

`allow_patterns` avoids downloading the whole repo; env vars control the transport backend. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/guides/download "Download files from the Hub"))

### C) Pick the right WAN repo

- **A14B T2V Diffusers** (large, full Diffusers layout). Model card updated 2025-08-25. Use includes like in B. ([Hugging Face](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B-Diffusers "Wan-AI/Wan2.2-T2V-A14B-Diffusers"))
- **TI2V-5B Diffusers** (smaller, 720p on a 4090). Model card updated 2025-08-25. Includes ModelScope links. ([Hugging Face](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B-Diffusers "Wan-AI/Wan2.2-TI2V-5B-Diffusers"))

### D) If your network blocks HF

The TI2V-5B and A14B cards expose **ModelScope** mirrors; use their commands when HF is rate-limited or Xet is blocked. ([Hugging Face](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B-Diffusers "Wan-AI/Wan2.2-TI2V-5B-Diffusers"))

## 2) Modules that can “do the WAN job”

Pick by task first: text-to-video vs image-to-video. Then match VRAM and toolchain.

### Text-to-Video (open, maintained)

- **CogVideoX (2B/5B)**. Official Diffusers pipelines and training docs. Good prompt adherence. Active in 2024–2025. ([Hugging Face](https://huggingface.co/docs/diffusers/en/api/pipelines/cogvideox "CogVideoX"))
- **Mochi-1 preview**. Apache-2.0. Runs via Diffusers. Strong motion. Community shows 161-frame runs on 24 GB with recent Diffusers. ([Hugging Face](https://huggingface.co/genmo/mochi-1-preview "genmo/mochi-1-preview"))
- **Open-Sora v2**. Research-grade, heavier setup. Provides t2i2v pipeline examples. ([Hugging Face](https://huggingface.co/hpcai-tech/Open-Sora-v2 "hpcai-tech/Open-Sora-v2"))

### Image-to-Video (stable baseline)

- **Stable Video Diffusion (SVD, XT/XT-1.1)**. Solid i2v in Diffusers. Good swap-in for ComfyUI or Python workflows. ([Hugging Face](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid "stabilityai/stable-video-diffusion-img2vid"))

### Research directions

- **Pyramidal / temporal-pyramid flow models**. Useful if you need newer architectures or plan to finetune. ([arXiv](https://arxiv.org/abs/2410.05954 "Pyramidal Flow Matching for Efficient Video Generative Modeling"))

### Minimal code examples

**CogVideoX (Diffusers)**

```python
# docs: https://huggingface.co/docs/diffusers/en/api/pipelines/cogvideox
from diffusers import CogVideoXPipeline
import torch
pipe = CogVideoXPipeline.from_pretrained("THUDM/CogVideoX-5b", torch_dtype=torch.bfloat16).to("cuda")
video = pipe("A tabby cat astronaut slowly walks on the moon, cinematic, 24 fps", num_frames=49, height=480, width=720).frames

```

([Hugging Face](https://huggingface.co/docs/diffusers/en/api/pipelines/cogvideox "CogVideoX"))

**Mochi-1 preview (Diffusers)**

```python
# docs: https://huggingface.co/docs/diffusers/en/api/pipelines/mochi
from diffusers import MochiPipeline
pipe = MochiPipeline.from_pretrained("genmo/mochi-1-preview", torch_dtype=torch.bfloat16).to("cuda")
out = pipe("Aerial drone shot over snowy mountains at golden hour", num_frames=49, height=480, width=832)

```

([Hugging Face](https://huggingface.co/docs/diffusers/en/api/pipelines/mochi "Mochi 1 Preview"))

**SVD i2v**

```python
# model card: https://huggingface.co/stabilityai/stable-video-diffusion-img2vid
from diffusers import StableVideoDiffusionPipeline
pipe = StableVideoDiffusionPipeline.from_pretrained(
    "stabilityai/stable-video-diffusion-img2vid", torch_dtype=torch.float16
).to("cuda")

```

([Hugging Face](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid "stabilityai/stable-video-diffusion-img2vid"))

* * *

### Quick selector

- Need **T2V** with open weights and Diffusers: start with **CogVideoX-5B** , then try **Mochi-1 preview** if you prefer Apache-2.0. ([Hugging Face](https://huggingface.co/docs/diffusers/en/api/pipelines/cogvideox "CogVideoX"))
- Need **I2V** fast and simple: **SVD**. ([Hugging Face](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid "stabilityai/stable-video-diffusion-img2vid"))
- Want **WAN-like** quality with open stack and can afford setup: **Open-Sora v2**. ([Hugging Face](https://huggingface.co/hpcai-tech/Open-Sora-v2 "hpcai-tech/Open-Sora-v2"))

---

<div class="post-metadata">

**Author:** ![Vihaananand](https://avatars.discourse-cdn.com/v4/letter/v/47e85d/32.png) [@Vihaananand](https://discuss.huggingface.co/u/Vihaananand)\
**Post date:** [October 13, 2025, 12:16pm UTC](https://discuss.huggingface.co/t/a-program-to-use-all-modules/169015/13 "2025-10-13T12:16:49Z")

</div>

Hello,

Thanks again.

I have a question about manual download. Let’s say I want to download [Wan-AI/Wan2.2-T2V-A14B-Diffusers](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B-Diffusers/tree/main). First, I create a directory in the **sdnext/models** directory. Now, do I need to download all the files and directories located at [https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B-Diffusers/tree/main](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B-Diffusers/tree/main)?

---

<div class="post-metadata">

**Author:** ![jsulz](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/jsulz/32/28279_2.png) [@jsulz](https://discuss.huggingface.co/u/jsulz)\
**Post date:** [October 13, 2025, 2:03pm UTC](https://discuss.huggingface.co/t/a-program-to-use-all-modules/169015/14 "2025-10-13T14:03:22Z")

</div>

Hey there!

These print statements are just warnings and shouldn’t impede your ability to finish a download. If you were unable to complete a download, was there an error statement or stack trace provided?

---

<div class="post-metadata">

**Author:** ![Vihaananand](https://avatars.discourse-cdn.com/v4/letter/v/47e85d/32.png) [@Vihaananand](https://discuss.huggingface.co/u/Vihaananand)\
**Post date:** [October 13, 2025, 7:09pm UTC](https://discuss.huggingface.co/t/a-program-to-use-all-modules/169015/15 "2025-10-13T19:09:59Z")

</div>

Hello,

Please forget that error. If I want to download the files manually, which files should I download?