How to Build an LTX-Video ComfyUI Workflow for Consistent Clips
An LTX-Video ComfyUI workflow that locks seed, prompt, and sampler settings lets you render a batch of clips that look like they came from the same shoot, instead of 10 fragments that clash. You build it once, save the graph as a JSON template, and swap only the prompt text per clip.
The setup below targets ComfyUI on a 12GB GPU with the fp8 distilled checkpoint, and it covers the parts that trip people up: seed handling, image-to-video conditioning, and how to queue twenty variations without babysitting the machine.
Why lock the workflow instead of prompting fresh each time?
Video models are sensitive. Change the seed and the lighting flips. Change CFG and motion speed drifts. A fixed graph removes those variables so the only thing moving between renders is your subject.
That matters for LTX-Video specifically because the base and distilled checkpoints behave differently — a workflow tuned for one will look muddy on the other if you forget the step count.
What does the node graph look like?
Six core nodes carry the whole thing.
- Checkpoint Loader — points at the fp8 distilled file.
- CLIP Text Encode — positive prompt, and a separate negative you never blank out.
- Empty Latent Video — sets width, height, length (frames), and batch size.
- KSampler — 8 steps, CFG 3, euler sampler for the distilled build.
- VAE Decode — pipes latents to pixels.
- Video Combine — writes the MP4 and frame rate.
Wire them in that order and you have a working graph. The negative prompt is worth real effort here: “blurry, warped limbs, text overlay, flicker” removes a chunk of the artifacts people blame on the model.
How do you keep motion consistent across a batch?
Fixed seed plus one changed variable is the rule. Set batch size to 4 in Empty Latent Video, keep the seed static, and vary nothing but the prompt. You get four takes that share lighting and camera feel.
If you are turning a still into motion, feed it through an image-to-video conditioning node and keep the strength between 0.6 and 0.8. Below 0.6 the clip ignores your prompt; above 0.8 the source image barely moves.
How do you queue many clips unattended?
ComfyUI has a queue that keeps running after you close the browser tab, as long as the server process stays up. Load the API-format workflow, then script the prompt swaps with curl against the /prompt endpoint. Each job drops its MP4 into the output folder named by node and counter.
Watch VRAM. Four queued 121-frame jobs at 768×512 fit on 12GB; bumping to 1216×704 will push you into a card that has 24GB or into sequential offload that slows render times to minutes per clip.
Which mistakes waste the most time?
| Mistake | Fix |
|---|---|
| Using base model at 8 steps | Distilled needs 8, base needs 20-30 |
| Blank negative prompt | Always list flicker and text artifacts |
| Random seed per job | Lock it for style continuity |
| 60 fps output | LTX is trained near 24-30; higher looks interpolated |
Who should bother with the workflow route?
If you render one clip a month, the default example graph is fine. This pays off when you need 20 clips that match, or when you are handing the graph to an editor who should not be touching sampler settings. Skip it if your GPU has under 12GB and you refuse to use quantized weights — you will fight out-of-memory errors more than you create.
Quick Summary
- A fixed LTX-Video ComfyUI graph keeps lighting and camera stable across a batch of clips.
- Six nodes do the work: checkpoint, text encode, empty latent, KSampler, VAE decode, video combine.
- Use 8 steps and CFG 3 on distilled weights; 20-30 steps on the base model.
- Batch size 4 with a locked seed plus image-to-video strength of 0.6-0.8 gives consistent variations.
