JonXL Multi Wan 2.1 + 2.2 Advanced V5 AIO Workflow - T2I T2V I2V FLF2V (Trim, Extend, Upscale, Interpolate)

*V5g released! Now also added backwards compatible support for Wan 2.1 with a simple switch of a toggle!

*Consider upgrading to my latest (advanced) workflow, which now also includes Wan 2.1 VACE + Stand in
https://civitai.com/models/1889006?modelVersionId=2138145*

*Consider using my earlier workflow if you don't feel Comfy using more advanced ComfyUI workflows

https://civitai.com/models/1864291/jonxls-multi-wan22-t2i-t2v-i2v-clip-extender-workflow-upscaling-and-interpolation

*Downgrade node 'rgthree-comfy' to a lower version like 1.0.25052900, since their new bug prevents groups showing up in the control (bypass) panel*

A multipurpose workflow for generating text to image, text to video, (infinite) image to video, and first-last-frame to video, using a single switch, with a useful trimming feature.

Configure all models once (download links and folder paths provided in notes) and then switch between generation modes.

Zip Archive also includes JonXL's Top 10 Video Joiner Workflow (to join up to 10 videos, and upscale and interpolate optionally)

https://civitai.com/models/1872188/jonxl-top-10-video-joiner-interpolate-upscale

Stay tuned, Wan 2.1 VACE + Stand In integration coming soon (!)

Features:

• Allows for Wan 2.1 and Wan 2.2 Generation inside the same workflow, just change 1 switch! (Preset to Wan 2.2)

• Allows for T2V, T2I, I2V and First-Last-Frame 2V generation. Easily switch between T2V, I2V and FLF2V per toggle.

• Supports simple resize and rescaling of input images instead of cropping (using a single toggle)

• Allows for infinite video generation, when loading the last generated input image manually (auto saved in a separate folder).

• Includes a subprocess of clip trimming, choosing the start and end frame of a generated video before saving the video.

• Includes optional post processing upscaling and frame interpolation of the generated clip. (easy enable / disable through control panel)

• Multi Lora loading

• Sage Attention for performance (easy enable / disable through control panel) - recommended, but maybe hard to install.

• Notes explaining most important steps of the workflow

• Bonus (inside the workflow): Separately load a video for upscaling or frame interpolation

• Bonus (inside the workflow): Join two videos together into a single video

• Zip Archive also includes JonXL's Top 10 Video Joiner Workflow (to join up to 10 videos, and upscale and interpolate optionally.. very useful to join, upscale and interpolate clips all at once after generating the base trimmed clips)

By manually loading the last saved images, saved in a separate folder for ease of use, infinite video generation can be achieved.

Due to being able to trim the video before saving (and therefore also by choosing the last frame), more frames and clips can be salvaged.

Make sure to change the prompt (add a space for example) or manually select another seed in the KSampler if you want another clip generation based on the same frame.

When loading this workflow, make sure to load a random image in both 'Load Image' nodes. (perhaps the one that came with this workflow zip archive) to avoid the initial error for the "Load image" node.

(while the image is not needed, ComfyUI likes to complains about it)

The example Lora used in this model can be found here: https://civitai.com/models/1862320/wan22-t2v-lora-cartoon-style

For T2I it is recommend to install the following custom_node to use "res_2s" + "bong tangent" sampler: 

https://github.com/ClownsharkBatwing/RES4LYF

Control panel can be found at the top of the workflow.

Recommended usage:

(Initial setup)

0. Determine if you have Sage Attention installed, or try installing it following the notes.

1. Download and configure the necessary models (I2V, T2V, clip, vae) etc, use the download links and put in the right folder as mentioned in the notes if necessary.

(Normal use)

2. Configure whether to use Wan 2.2 or Wan 2.1, add a prompt, choose T2V, I2V, FLF2V and set video parameters (see note)

You can also change the sampler steps globally if needed.

Finally, press "Run" to generate the video.

The first and last frame will be previewed once generation is complete.

3. Trim the video optionally, by selecting first and last frame, through using a starting frame index and amount of frames to add from that point.

Press "Run" (or CTRL+ENTER) in ComfyUI to generate a preview of the trimmed clip.

Optionally use the "Dump frames" option in the Control Panel, to dump all frames to make it easier to find your start and end frame.

4. When you are happy with the trimmed video, save it by putting "SAVE TRIMMED CLIP" to 'true' and then "Run" ComfyUI once more.

Now, optionally choose to enable Step 4 "Upscale and Interpolate" to also save the video but upscaled and interpolated.

(You can also do this later, if you joined all your clips together in a final pass I guess)

5. Set "SAVE TRIMMED CLIP" to 'false' and either:

• Change the seed in the KSampler of step 2 for a new generation on same prompt

• Change the prompt in step 2 (different prompt) for a new generation on another prompt

• Change the image (if in Image to Video mode) in "Load image" and optionally change the prompt to generate from another frame.

• Load the last frame from the ComfyUI\output\JXL\LastFrames\ folder to continue generating from the last frame of the clip you just generated.

Folder structure:

• Output\JXL\Clips\ - All initial generated clips, untrimmed

• Output\JXL\FirstFrames\ - First Frames (useful for backtracking)

• Output\JXL\LastFrames\ - Last Frames (useful for the Load Image node to continuing clip generation)

• Output\JXL\Trimmed\ - Trimmed videos, when saved

• Output\JXL\Processed\ - Processed videos (based on the trimmed videos), upscaled and interpolated

• All files are prefixed with 'w22'.

Thank you for reading this wall of text!

Please leave a like, comment and feel free to upload any SFW content you made using this workflow on the workflow's CivitAI page.