Workflow highlights:

Audio Generation - via MMaudio - Render Audio with your videos

FAST preview generation with optional pausing
- Preview your videos in seconds before proceeding with the full length render
Multiple Upscale Methods -
- Standard Upscale
- Interpolation (double frame-rate)
- V2V method
Multiple Lora Options
- Traditional Lora using standard weights
- Double-Block (works better for multiple combined loras without worrying about weights)
Multiple Resolutions
- Created 5 common resolutions - select them with a switch - no need to remember all the optins
Prompting with Wildcard Capabilities
All Options are toggles and switches no need to connect any nodes
Detailed Notes on how to set things up.

This is my first workflow. I personally wanted options for video creations so here is my humble attempt.

Additional Details:

I am new to AI and comfy, this is my first workflow I loved the "Hunyuan 2step t2v and upscale" workflow - https://civitai.com/models/1092466/hunyuan-2step-t2v-and-upscale and it was highly used as the base. So should work on the same set-ups as the original.

By Default- everything has been setup according to the Hunyuan 2step t2v and upscale workflow. But with all the new toggles you have more options. Any Nodes marked in Green are the only ones you should need to touch.

All toggles and switches:

Lora Options:

Traditional Lora and Double Block can be used, Double-Block is default.

Double-block seems to do better with multiple lora's without having to worry about adjusting weights.

You can select which type of lora to use in the option.

Input 1 - To bypass loras completely

Input 2 - Traditional Loras - with multiple loras you will need to play with the weights

Input 3 - Double Block (Default) don't need to mess with weights, multi-loras work better with this.

This workflow has be setup to use up to 3 loras. If you only need 1 or 2 lora's, please right click on the unused lora selector and choose "Bypass". Make sure you do this from top to bottom, always leave the bottom most lora enabled if you only have 1 lora needed.

Resolution Options:

Select from common resolutions - or edit the 5 to make them your own. Change resolution with the "Resolution Selector" By Default the fastest smallest resolution is selected intended to go to the next V2V portion of the workflow. As you increase to the larger resolutions your render times will take much longer.

Pause after Preview - can be toggled on and off (On by default)

Video generation takes too long, experimenting with multiple loras or getting your prompt right takes so long when video render-times are slow. Use this to quickly preview your videos before going through the additional time to upscale process. By Default this is Enabled. After your start the workflow, it will quickly render the fast preview, then you will here a chime. Make sure you scroll down below the video preview for next steps.

Upscale the previews you like, or cancel and try again!

To disable this feature, toggle it off under "Options Selector"

MMaudio - Add audio automatically to your video

By Default it will only add audio to upscaled videos. However there is a switch to enable it for all parts of the render process. Be sure to add any audio details to your prompt for better generation.

Interpolation after Upscaling

This option lets you double the frame-rate of your rendered video, by default "enabled"

you an disable it from the "Options Selector". This can slow down your render if you don't need it.

Tips for how to use the workflow

Fast, V2V method,Double Lora (Default) - this follows the original work flow.

Quick Preview using a fast low res video: Use
- (Resolution 1 - 368x208) for landscape video
- (Resolution 3 - 320x416) for portrait video
Pause to decide if you want to do the full render
Full render includes audio, upscaling and interpolation

T2V straight to upscale method

Render at medium or high res, then use the upscaler, audio
Use Resolution 2, 4, 5 options for higher res - slower render. I personally use resolution 4 for most.
Will Upscale and add audio

Setup

Disable "Intermediate V2V" from Options menu

Select input 2 on Upscaler Select

Wildcards/Seeds and keeping consistentcy between preview and higher res renders (Non V2V)

Often i want to generate many quick previews to find the right video. V2V is good, but i do find it can change the video somewhat and may lose a bit of detail due to the original first render.

1) Setup using the "T2V straight to upscale method" from above.

2) Create previews using one of the FAST Resolutions (Resolution 1 or 3).

3) Once i find the right preview. I go to RandomNoise - set that value to fixed - so it will stay the same as my last preview. 4) If I used wildcards, I copy and paste the actual prompt from the "Show Text" field into the prompt field.

5) Change my resolution to one of the Large higher res. ie Resolution 2 or 4. Then Queue. For the most part, I get the same video only in a higher res. Please note that by default the Large resolutions are double the res of the small counterpart this helps maintain consistency when using this method. Please always use the same aspect ratios ie. 1--> 2, 3--> 4

That's all folks. all credits to all of the original authors of all of this.

Hope you enjoy. Great to be part of such an open and sharing community!

Search AI Models & Addons

very few results