Acknowledgements
I have addressed all known bugs within this workflow (excluding those inherent to ComfyUI or specific custom nodes). As such, I am concluding regular updates for this project.
I might still push occasional updates if the mood strikes me, but for now, consider this the final version. Thank you so much for the downloads and support. I hope this workflow helps your creative process - happy generating!
Overview
A simple LTX-2.3 workflow. It uses the Distilled GGUF model for fast generation.
Core Features
Single / Extend Generation Mode
You can choose whether to generate the video once or extend it afterward.
Three prompt input modes
Prompt enhancement using Ollama
Native LTX prompt enhancement
Plain (no enhancement)
If Ollama is not needed, you can disconnect it from the Ollama SubGraph node or simply delete the node.
Optional Features
Preview Switch: Displays a preview during sampling.
Audio-driven: Generates a video that matches an existing audio file.
T2V Switch: Ignores the start image and generates the video using text-to-video.
Full Mode: Generated using Steps 15 and CFG 3.0. This takes a very long time. While the camera work and motion may be slightly improved, the generation time is not practical.
Double-Frame Mode: For use with intense motion. By rendering at twice the frame rate, facial distortion is less likely to occur.
Note
If you encounter the error, please update ComfyUI-KJNodes to the latest version.
If you apply the Sulphur LoRA, a strength of 0.5 is likely the best choice. At 1.0, it tends to introduce noise into the audio, and basic motions such as walking or running are more likely to appear in slow motion.
Description
Sampler and scheduler optimization
Ollama persona settings optimization
Full mode added
FAQ
Comments (3)
I'm at a loss - how in the world do I disable Ollama? I just want to use my prompts. Do I delete the whole subgraph, or what do I disconnect?
When I delete the whole subgraph, I get:
Model LTXAVTEModel_ prepared for dynamic VRAM loading. 14789MB Staged. 0 patches attached. Force pre-loaded 290 weights: 1497 KB.
Generating tokens: 21%|█████████████ | 54/256 [00:12<00:45, 4.42it/s]
And then in stops and won't re-launch, if I try to run it again I get:
Failed to validate prompt for output 1316:
* easy int 167:1310:1512:
- Required input is missing: value
Many of the errors are caused by bugs in the ComfyUI Frontend, but updates have been made to address them. Operation has been confirmed on the latest version of ComfyUI.
If you want to disable Ollama, connect the line currently attached to the text input field in the LTX-2.3 / LTX-2.3 Extend Subgraph to the small connector at the bottom-right of the green text input node. When using the LTX enhance feature, set “enable enhance” in the LTX-2.3 / LTX-2.3 Extend Subgraph to true. If set to false, you can input a plain prompt.
If you want to completely remove Ollama, delete both the Ollama and Generate Prompt subgraphs.
Bro is trying to trick us into updating Comfyui O.o;;;;;;
j/k lol, maybe I try this wf...
for disable ollama stuff I'd just control+b to disable the selected nodes, in case you need them later or whatever, plus don't need reconnect anything.