# Looking for an open source image-to-video to test with Intel ARC GPU

**URL:** <https://discuss.huggingface.co/t/looking-for-an-open-source-image-to-video-to-test-with-intel-arc-gpu/141336>\
**Category:** Beginners\
**Created:** [February 17, 2025, 3:37pm UTC](https://discuss.huggingface.co/t/looking-for-an-open-source-image-to-video-to-test-with-intel-arc-gpu/141336 "2025-02-17T15:37:36Z")\
**Posts on this page:** 14\
**Page:** 1

<div class="post-metadata">

**Author:** ![Cedric1000](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/cedric1000/32/40916_2.png) [@Cedric1000](https://discuss.huggingface.co/u/Cedric1000)\
**Post date:** [February 17, 2025, 3:37pm UTC](https://discuss.huggingface.co/t/looking-for-an-open-source-image-to-video-to-test-with-intel-arc-gpu/141336/1 "2025-02-17T15:37:36Z")

</div>

Hi,

I have A770 INTEL ARC card and I’m looking an open source AI API to generate some videos from an image.  
A lot of thing I’ve found over the web is complicated (for me) to make it working with Intel ARC GPU. (ComfyUI works fine for me but just for generating images)

Could you give me some guidelines or AI open source solution or tools, to try please ?

I’ve read that INTEL AI Playground is great, but I don’t see any txt-to-video or img-to-video integrated tools

Best regards

PS : I have asked to INTEL support but they have suggested me to post my question here.

---

<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:** [February 17, 2025, 4:54pm UTC](https://discuss.huggingface.co/t/looking-for-an-open-source-image-to-video-to-test-with-intel-arc-gpu/141336/2 "2025-02-17T16:54:33Z")

</div>

After installing PyTorch for XPU, you should be able to generate it using Diffusers. It will probably take a long time…

.to(“cuda”) is for nVidia, so if you have an Intel GPU, replace it with .to(“xpu”).

> **[Welcome to Intel® Extension for PyTorch\* Documentation!](https://intel.github.io/intel-extension-for-pytorch/index.html#introduction)**
>
> This website introduces Intel® Extension for PyTorch\*

> **[State of open video generation models in Diffusers](https://huggingface.co/blog/video_gen)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.

```py
#.to("cuda")
.to("xpu")

```

---

<div class="post-metadata">

**Author:** ![Cedric1000](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/cedric1000/32/40916_2.png) [@Cedric1000](https://discuss.huggingface.co/u/Cedric1000)\
**Post date:** [February 18, 2025, 10:16am UTC](https://discuss.huggingface.co/t/looking-for-an-open-source-image-to-video-to-test-with-intel-arc-gpu/141336/3 "2025-02-18T10:16:22Z")

</div>

Thank you for your reply, I will look at it.

Meanwhile, I 've began to try Atomatic1111. could you tell me where we can I verify that the to(XPU) is well set please ?  
(I have launched a working process but I can see my Intel GPU is not used)

---

<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:** [February 18, 2025, 12:57pm UTC](https://discuss.huggingface.co/t/looking-for-an-open-source-image-to-video-to-test-with-intel-arc-gpu/141336/4 "2025-02-18T12:57:49Z")

</div>

Try IPEX.

> **[Three Ways to Generate AI Art Using Intel® Arc™ GPUs – Intel Gaming Access](https://game.intel.com/gb/stories/intel-arc-graphics-generative-ai-art/)**

---

<div class="post-metadata">

**Author:** ![Cedric1000](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/cedric1000/32/40916_2.png) [@Cedric1000](https://discuss.huggingface.co/u/Cedric1000)\
**Post date:** [February 18, 2025, 1:14pm UTC](https://discuss.huggingface.co/t/looking-for-an-open-source-image-to-video-to-test-with-intel-arc-gpu/141336/5 "2025-02-18T13:14:41Z")

</div>

Sorry I’m a Beginner, I’m sure to understand what you mean by IPEX.

I’m using Automatic1111 with the InfiniteZoom, but the process it is very long : I think my Intel GPU is not used.

you meant using IPEX within my Automatic1111 configuration ?

---

<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:** [February 18, 2025, 2:26pm UTC](https://discuss.huggingface.co/t/looking-for-an-open-source-image-to-video-to-test-with-intel-arc-gpu/141336/6 "2025-02-18T14:26:41Z")

</div>

That’s about it.

I think even advanced users would have a hard time using A1111 WebUI with a GPU other than nVidia…  
Intel ARC and RADEON themselves are for advanced users.  
Also, if you use Extensions such as InfiniteZoom, it may be a little pointless if they are not compatible with Intel GPUs.

In addition to IPEX, there is also a method for accelerating Intel chips called OpenVINO, but this is difficult in its own way. Probably IPEX or DirectML would be better this time.

### Intel® Extension for PyTorch (IPEX)

[https://github.com/intel/intel-extension-for-pytorch?tab=readme-ov-file](https://github.com/intel/intel-extension-for-pytorch?tab=readme-ov-file)

### Command Line Arguments and Settings

> **[Command Line Arguments and Settings](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Command-Line-Arguments-and-Settings)**
>
> Stable Diffusion web UI. Contribute to AUTOMATIC1111/stable-diffusion-webui development by creating an account on GitHub.

```auto
--use-ipex

```

### Any way to run this on Intel Arc? #455 (WebUI Forge)

> **[Any way to run this on Intel Arc? · lllyasviel stable-diffusion-webui-forge ·...](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/455)**
>
> Guess it doesn't support IPEX? Tried it and it gives TypeError: 'NoneType' object is not iterable Error

### sd-webui-ipex-enhancement

[https://github.com/Nuullll/sd-webui-ipex-enhancement?tab=readme-ov-file](https://github.com/Nuullll/sd-webui-ipex-enhancement?tab=readme-ov-file)

---

<div class="post-metadata">

**Author:** ![Cedric1000](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/cedric1000/32/40916_2.png) [@Cedric1000](https://discuss.huggingface.co/u/Cedric1000)\
**Post date:** [February 18, 2025, 4:43pm UTC](https://discuss.huggingface.co/t/looking-for-an-open-source-image-to-video-to-test-with-intel-arc-gpu/141336/7 "2025-02-18T16:43:23Z")

</div>

Thanks a lot for all your links.

If I really need to generate Infinite Zoom, which other framework (than A1111) would you recommend me fully compatible with Intel Arc ?

A1111+InfiniteZoom is the only easy way GUI I’ve found over the web…  
(unfortunately, I did not find any other simple resource to do it easily)

---

<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:** [February 18, 2025, 4:51pm UTC](https://discuss.huggingface.co/t/looking-for-an-open-source-image-to-video-to-test-with-intel-arc-gpu/141336/8 "2025-02-18T16:51:47Z")

</div>

It looks like ComfyUI also has a plugin, and it seems to be compatible with Intel GPUs.  
Also, although it’s not a GUI, I found something that looks like it’s for Intel’s OpenVINO.

However, basically, you should think that you will need a lot of extra effort and skill for anything you do other than CUDA…

> **[Intel Arc Graphics Thread · comfyanonymous/ComfyUI · Discussion #476](https://github.com/comfyanonymous/ComfyUI/discussions/476)**
>
> ComfyUI now supports Intel Arc Graphics. (#409) Since the installation tutorial for Intel Arc Graphics is quite long, I'll write it here first. Chinese version / 中文版: HERE Intel Extension for PyTor...

[https://docs.openvino.ai/2023.3/notebooks/236-stable-diffusion-v2-infinite-zoom-with-output.html](https://docs.openvino.ai/2023.3/notebooks/236-stable-diffusion-v2-infinite-zoom-with-output.html)

---

<div class="post-metadata">

**Author:** ![Cedric1000](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/cedric1000/32/40916_2.png) [@Cedric1000](https://discuss.huggingface.co/u/Cedric1000)\
**Post date:** [February 18, 2025, 5:12pm UTC](https://discuss.huggingface.co/t/looking-for-an-open-source-image-to-video-to-test-with-intel-arc-gpu/141336/9 "2025-02-18T17:12:36Z")

</div>

Really, ComfUI has a plugin for it ?  
that’s a good news … So I have to go back with ComfyUI,

Few weeks ago, I succeeded in generating images with it, and it was full working with Intel GPU. But I never succeeded in getting it to work with OpenVino so i’ve forgot it.

But ok, I will try again with this plugin, 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:** [February 18, 2025, 6:14pm UTC](https://discuss.huggingface.co/t/looking-for-an-open-source-image-to-video-to-test-with-intel-arc-gpu/141336/10 "2025-02-18T18:14:29Z")

</div>

Perhaps just similar one.  
[https://weirdwonderfulai.art/comfyui/infinite-zoom-loop-in-comfyui/](https://weirdwonderfulai.art/comfyui/infinite-zoom-loop-in-comfyui/)

---

<div class="post-metadata">

**Author:** ![Cedric1000](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/cedric1000/32/40916_2.png) [@Cedric1000](https://discuss.huggingface.co/u/Cedric1000)\
**Post date:** [February 23, 2025, 12:41pm UTC](https://discuss.huggingface.co/t/looking-for-an-open-source-image-to-video-to-test-with-intel-arc-gpu/141336/11 "2025-02-23T12:41:46Z")

</div>

Hi,

I’ve reinstalled first ComfyUI that works fine to generate an image.  
but when launching I can see some import errors:

> WARNING: some comfy\_extras/ nodes did not import correctly. This may be because they are missing some dependencies.  
> -IMPORT FAILED: nodes\_canny.py  
> -IMPORT FAILED: nodes\_morphology.py  
> -IMPORT FAILED: nodes\_audio.py  
> -IMPORT FAILED: nodes\_video.py  
> =\> This issue might be caused by new missing dependencies added the last time you updated ComfyUI.  
> Please do a: pip install -r **requirements.txt**

Could you tell me how to correct the issue ?

I’m not using “requirements.txt” but “ **requirements-ipex.txt** ”  
And when installing ComfyUI the first I’ve already launched this command line:

> pip install -r **requirements-ipex.txt**

But the issue is still there…

---

<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:** [February 23, 2025, 1:01pm UTC](https://discuss.huggingface.co/t/looking-for-an-open-source-image-to-video-to-test-with-intel-arc-gpu/141336/12 "2025-02-23T13:01:37Z")

</div>

I don’t know how to fix the error in ComfyUI…  
I think the situation is probably the same as the github issue below, so please try changing the file and folder names to match your environment.

To be more specific, you can have as many Python installations as you like on the same PC, so there’s no point in installing the library in a Python other than the target one, and you definitely need to install the library in the Python that ComfyUI is using. If it still doesn’t work, it’s probably not compatible and won’t work.

> <https://github.com/kijai/ComfyUI-CogVideoXWrapper/issues/5>
>
> Tried to use the example\_01.json but it didn't import correctly and is missing a… bunch of nodes. Here's the full console log:
> 
> \`\`\`
> Z:\\webui\\ComfyUI\_windows\_portable\>.\\python\_embeded\\python.exe -s ComfyUI\\main.py --windows-standalone-build --gpu-only
> \[START\] Security scan
> \[DONE\] Security scan
> \## ComfyUI-Manager: installing dependencies done.
> \*\* ComfyUI startup time: 2024-08-08 23:13:09.890191
> \*\* Platform: Windows
> \*\* Python version: 3.11.6 (tags/v3.11.6:8b6ee5b, Oct 2 2023, 14:57:12) \[MSC v.1935 64 bit (AMD64)\]
> \*\* Python executable: Z:\\webui\\ComfyUI\_windows\_portable\\python\_embeded\\python.exe
> \*\* ComfyUI Path: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI
> \*\* Log path: Z:\\webui\\ComfyUI\_windows\_portable\\comfyui.log
> 
> Prestartup times for custom nodes:
> 0.0 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\rgthree-comfy
> 1.5 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ComfyUI-Manager-main
> 
> Total VRAM 24576 MB, total RAM 32694 MB
> pytorch version: 2.4.0+cu121
> Set vram state to: HIGH\_VRAM
> Device: cuda:0 NVIDIA GeForce RTX 3090 : cudaMallocAsync
> Using pytorch cross attention
> \[Prompt Server\] web root: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\web
> Z:\\webui\\ComfyUI\_windows\_portable\\python\_embeded\\Lib\\site-packages\\kornia\\feature\\lightglue.py:44: FutureWarning: \`torch.cuda.amp.custom\_fwd(args...)\` is deprecated. Please use \`torch.amp.custom\_fwd(args..., device\_type='cuda')\` instead.
> @torch.cuda.amp.custom\_fwd(cast\_inputs=torch.float32)
> Traceback (most recent call last):
> File "Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\nodes.py", line 1941, in load\_custom\_node
> module\_spec.loader.exec\_module(module)
> File "\<frozen importlib.\_bootstrap\_external\>", line 940, in exec\_module
> File "\<frozen importlib.\_bootstrap\>", line 241, in \_call\_with\_frames\_removed
> File "Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ComfyUI-CogVideoXWrapper-main\\\_\_init\_\_.py", line 1, in \<module\>
> from .nodes import NODE\_CLASS\_MAPPINGS, NODE\_DISPLAY\_NAME\_MAPPINGS
> File "Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ComfyUI-CogVideoXWrapper-main\\nodes.py", line 6, in \<module\>
> from diffusers.schedulers import CogVideoXDDIMScheduler, CogVideoXDPMScheduler
> ImportError: cannot import name 'CogVideoXDDIMScheduler' from 'diffusers.schedulers' (Z:\\webui\\ComfyUI\_windows\_portable\\python\_embeded\\Lib\\site-packages\\diffusers\\schedulers\\\_\_init\_\_.py)
> 
> Cannot import Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ComfyUI-CogVideoXWrapper-main module for custom nodes: cannot import name 'CogVideoXDDIMScheduler' from 'diffusers.schedulers' (Z:\\webui\\ComfyUI\_windows\_portable\\python\_embeded\\Lib\\site-packages\\diffusers\\schedulers\\\_\_init\_\_.py)
> \### Loading: ComfyUI-Manager (V2.48.4)
> \### ComfyUI Revision: 2489 \[8115d8cc\] | Released on '2024-08-07'
> Failed to auto update \`Quality of Life Suit\`
> QualityOfLifeSuit\_Omar92\_DIR: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ComfyUI-QualityOfLifeSuit\_Omar92
> \[ComfyUI-Manager\] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json\[ComfyUI-Manager\] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json\[ComfyUI-Manager\] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
> \[ComfyUI-Manager\] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
> \[ComfyUI-Manager\] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
> 
> \[rgthree\] Loaded 20 exciting nodes.
> \[rgthree\] Optimizing ComfyUI recursive execution. If queueing and/or re-queueing seems broken, change "patch\_recursive\_execution" to false in rgthree\_config.json
> 
> 
> Import times for custom nodes:
> 0.0 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\websocket\_image\_save.py
> 0.0 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\prompt\_injection.py
> 0.0 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\sdxl\_prompt\_styler
> 0.0 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\prompt\_injection-main
> 0.0 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ELLA
> 0.0 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\StableZero123-comfyui
> 0.0 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ComfyMath
> 0.0 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ComfyUI-QualityOfLifeSuit\_Omar92
> 0.0 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ComfyUI-Frame-Interpolation
> 0.0 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ComfyUI-Shinsplat-main
> 0.0 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ComfyUI-DareMerge-master
> 0.0 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\rgthree-comfy
> 0.0 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ComfyUI\_essentials
> 0.0 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ComfyUI\_ExtraModels
> 0.0 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ComfyUI-Flowty-TripoSR
> 0.0 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\Derfuu\_ComfyUI\_ModdedNodes
> 0.0 seconds (IMPORT FAILED): Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ComfyUI-CogVideoXWrapper-main
> 0.0 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ComfyUI-VideoHelperSuite
> 0.2 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ComfyUI-ELLA-wrapper
> 0.3 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ComfyUI-Manager-main
> 0.4 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ComfyUI-DareMerge
> 0.4 seconds: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ComfyUI-Flowty-CRM
> 
> Starting server
> 
> To see the GUI go to: http://127.0.0.1:8188
> FETCH DATA from: Z:\\webui\\ComfyUI\_windows\_portable\\ComfyUI\\custom\_nodes\\ComfyUI-Manager-main\\extension-node-map.json \[DONE\]
> Error: OpenAI API key is invalid OpenAI features wont work for you
> QualityOfLifeSuit\_Omar92::NSP ready
> \`\`\`

---

<div class="post-metadata">

**Author:** ![Cedric1000](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/cedric1000/32/40916_2.png) [@Cedric1000](https://discuss.huggingface.co/u/Cedric1000)\
**Post date:** [February 26, 2025, 6:55pm UTC](https://discuss.huggingface.co/t/looking-for-an-open-source-image-to-video-to-test-with-intel-arc-gpu/141336/13 "2025-02-26T18:55:09Z")

</div>

Hi,  
Thank you. I think I’ve previously followed the bad tutorial to install ComfyUI.

So I’ve installed it again to the letter, with the Intel ARC instructions below:

> **[GitHub - comfyanonymous/ComfyUI: The most powerful and modular diffusion model GUI,...](https://github.com/comfyanonymous/ComfyUI)**
>
> The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

… and now all is fine. The Defaut worflow works fine and generate well images.

Now, I’m trying a simple thing but I have a very weird error :  
if I replace the “Empty latent image” node by these 3 nodes : LoadImage+PadImageForInpainting+VAEencode (OR same thing with: LoadImage+VAEencode),

I obtain the Error:  
`KSampler : XPU out of memory. Tried to allocate 128.00 GiB. GPU 0 has a total capacity of 15.56 GiB. Of the allocated memory 2.50 GiB is allocated by PyTorch, and 39.26 MiB is reserved by PyTorch but unallocated. Please use ` empty\_cache` to release all unoccupied cached memory.`

but if I let ComfyUI generates the image it works fine.

Would you have any idea of the cause ?

---

<div class="post-metadata">

**Author:** ![Cedric1000](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/cedric1000/32/40916_2.png) [@Cedric1000](https://discuss.huggingface.co/u/Cedric1000)\
**Post date:** [February 26, 2025, 7:38pm UTC](https://discuss.huggingface.co/t/looking-for-an-open-source-image-to-video-to-test-with-intel-arc-gpu/141336/14 "2025-02-26T19:38:52Z")

</div>

I’ve followed this tutorial and all works fine until 6’00" :  
[Outpainting](https://www.youtube.com/watch?v=c1BUAi_Obqg)

but after 6’00’', when I replace VAEdecode+SaveImage by LoadImage+PadImageForInpainting+VAEencode, I obtain that big error…

Any idea ?