Ever feel like creating videos takes forever? You're not alone! That's where LTX and ComfyUI come in, making video creation smoother and faster. LTX speeds up the video-making process so you can focus on what really matters — telling your story and connecting with your audience. In this guide, we'll focus on img2vid generation and we’ll explore all the features that make LTX a game-changer. Let’s jump in!
How to run LTX in ComfyUI
Installation guide
Custom Nodes
If there are red nodes in the workflow, it means that the workflow lacks the certain required nodes. Install the custom nodes in order for the workflow to work.
- Go to ComfyUI Manager > Click Install Missing Custom Nodes
- Check the list below if there's a list of custom nodes that needs to be installed and click the install.
Is your custom nodes list empty?
- If your list of missing custom nodes is empty, you might already have LTX installed but an older version. Go to Custom Nodes Manager.
- Search for LTX in the list and Update ComfyUI-LTXVideo. Click Restart and Click Refresh to refresh Node Definition in workspace. Open the workflow again and your issue should be resolved.
Models
For this guide you'll need 3 models. 1 will be auto-downloaded and 2 will have to be downloaded manually.
- Go to ComfyUI Manager > Click Model Manager
- When you find the exact model that you're looking for, click install and make sure to press refresh when you are finished.
Model Path Source
Use the model path source if you prefer to install the models using model's link address and paste into ThinkDiffusion MyFiles using upload URL.
| Model Name | Model Link Address | ThinkDiffusion Upload Directory |
|---|---|---|
| Florence 2 model | Auto Downloaded by Node |
Auto Uploaded by Node |
| ltx-video-2b-v0.9.1.safetensors | ...comfyui/models/checkpoint/ |
|
| t5xxl_fp8_e4m3fn.safetensors | ...comfyui/models/clip/ |
Step-by-step Workflow Guide
| Steps | Recommended Nodes |
|---|---|
| 1. Load an Image |  |
| 2. Set the Size Set the recommended size by 768x512 resolution. The model works best on resolutions under 720. |
 |
| 3. Set the Models |  |
| 4. Check the Caption and Prompt You don't need to write anything in the 3rd text box because it is already provided by Florence. Image captioning by Florence doesn't address the kind of motion that happens in the scenes. Consider adding this part manually by writing in 1st text box or 2nd text box. |
 |
| 5. Set the Generation Settings Follow the settings as seen on the image. |
 |
| 6. Check the Generated Video |  |
Examples
Man playing a guitar.
Illustration of running motorcycle.
Drone view from above.
Man relaxing at the port.
If you’re having issues with installation or slow hardware, you can try any of these workflows on a more powerful GPU in your browser with ThinkDiffusion.
If you enjoy ComfyUI and you want to test out creating awesome animations, then feel free to check out this AnimateDiff tutorial here. And have fun out there with your videos!
Member discussion