June 10, Update: stmfnet
Just to save folks a headache the file is available for download as a model now.
June 06, Update: V4.0
Just a minor improvement, using a double interpolation of SFTMVFI results in higher fidelity of dynamic or fast motion scenes. Video is manually loaded to reduce time when generating high quantities of test runs. Now you can select which videos you want to upscale, will copy the name of the original input video.
Included the context framing node from Kijai's wrapper. Usually leave this off will exponentially increase generation times if on; however, can let you generate much longer videos beyond what your vram will allow you.
Interpolation requires higher VRAM if scaling if greater than 1.0. Changed the scaling factor to float for more control.
Updated nodes if there is any issues feel free to let me know.
https://drive.google.com/file/d/1s5JJdt5X69AO2E2uuaes17aPwlWIQagG/view
Place it in the folder: Custom_nodes\ComfyUI-Frame-Interpolation\ckpts\stmfnet
April 14, Update: V3.3
Updated Nodes.
March 27, Update: V3.2
Small changes to the Torch Compile and Tea Cache for more dynamic outputs using my Lora's.
Workflow is suitable for a 24GB card using the 14B models and a 12GB card using the 1.3B model.
Updates:
***Error within the naming of outputs corrected.
Uploaded a very simple and straightforward Wan I2V workflow. The workflow includes an upscaler with frame interpolation to bring your videos to a cool and smooth 60FPS. No BS just a simple addition. Original WanI2V is based on the workflow example of the amazing work from Kijai linked here: https://github.com/kijai/ComfyUI-WanVideoWrapper/tree/main/example_workflows.
Additionally, I've left the annotations within.
Prev Updates:
Compatible with 12GB memory cards. Tested using a 3060 RTX 12GB using this workflow can comfortably go up to 85 frames. 97 Frames is pushing the absolute limits will take about an hour to generate.
Due to demand this workflow is a small improvement to the Super Simple HV2V for those who don't do postprocessing outside of Comfyui.
Designed for use with Hunyuan Video and trained Lora models, it can upscale videos to true 60 FPS. It combines detailed notes on denoising strength, step optimization, aspect ratio adjustments, frame interpolation, and upscaling to create high-quality, smooth videos.
Order matters:
Generate → Upscale → Interpolate. Upscaling first preserves detail for interpolation.
Adjust parameters based on your Lora’s behavior and hardware limits.
Description
Small modifications to the teacache and torch compile for more dynamic shifts between frames
FAQ
Comments (22)
Just a heads-up that the WanVideo ImageClip Encode node has been deprecated. Seems like you need to use the WanVideo ImageToVideo Encode node now.
Thank you, Ah I gotta update my system every other day if seems
@SingularUnity haha I know, updates are coming crazy fast.
GGUf Workflows multgpu are the top notch for RTX 4070 12GB. This wf sadly stucks at ptxas info : Compiling entry function 'triton_red_fused__to_copy_add_mul_native_layer_norm_7' for 'sm_89'
ptxas info : Function properties for triton_red_fused__to_copy_add_mul_native_layer_norm_7
0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads
ptxas info : Used 40 registers, used 1 barriers, 432 bytes cmem[0]
I'll update it later today. Thank you
WanVideoSampler
backend='inductor' raised: RuntimeError: Cannot find a working triton installation. More information on installing Triton can be found at https://github.com/openai/triton Set TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information You can suppress this exception and fall back to eager by setting: import torch._dynamo torch._dynamo.config.suppress_errors = True
You will need to have Triton installed and working if your using the Torch cache. Also keep in mind that only the e5m2 wan models work with the inductor.
You can simply remove that node and it should work too, but it will be slower to generate videos.
@SingularUnity I take it it’s not as simple as removing the node and then hitting “run”?
@User5000f24 that's an option but you're better off installing triton. It's pretty easily done now.
Hi! Thanks fo your Workflow (Super Simple Workflows - v2.0)!
Is is possible to have prompt/workflow for this video: https://civitai.com/images/60394981
I try to do the same video, but in your workflow v2.0, its upscale of an existing video...
So I don't have the prompt or the workflow for the first video
PS: I start using Comfy and Hunyuan, sorry for noobs questions...
PS2: is it possible to leave the metadata in your videos so we can try generation too?
Thanks! :)
i cant find this lora，where can download：wan\Orbit\EP20.safetensors
That's the one you download Epoch20
@SingularUnity What does that mean? Is that a specific Lora called "Epoch20"?
I hope you continue to update your workflow. I've updated my extensions and ComfyUI, and your workflow is no longer working for me.
在哪儿修改时长，跑出来的视频非常短
Yeah, dont work ^^
Failed to find the following ComfyRegistry list. The cache may be outdated, or the nodes may have been removed from ComfyRegistry.
comfyui-wanvideowrapper
jameswalker-nodes
jameswalker-nodes
image-saver
comfyui-wanvideowrapper
comfyui-wanvideowrapper
comfyui-wanvideowrapper
comfyui-wanvideowrapper
comfyui-wanvideowrapper
comfyui-wanvideowrapper
comfyui-wanvideowrapper
comfyui-wanvideowrapper
comfyui-wanvideowrapper
comfyui-wanvideowrapper
comfyui-wanvideowrapper
comfyui-wanvideowrapper
comfyui-wanvideowrapper
comfyui-wanvideowrapper
It's been a while since I updated it, try it now.
@SingularUnity thx ^^