LTX-2.5 First Frame + Last Frame to Video (FLF2V)

A ComfyUI workflow for LTX-2.5 that adds first-frame/last-frame keyframe conditioning to the stock image-to-video template. The official 2.5 I2V workflow only conditions on a starting image and lets the model improvise where the clip ends up; this version also locks in an ending image, so the generated motion travels from your chosen start frame to your chosen end frame instead of drifting freely.

Built on top of Comfy's own LTX-2.5 template nodes — no custom node packs required.

What it does

- Takes a starting image and an ending image, plus a text prompt, and outputs a video that transitions between them.

- Uses LTXVAddGuide to inject both keyframes into the latent as fixed conditioning — first frame at frame_idx: 0, last frame at frame_idx: -1 — updating the positive/negative conditioning as well as the latent itself, rather than just pasting the image into the latent with no attention hint.

- The two guides are chained (first → last) and reapplied on both the base pass and the refine/upscale pass, so the end-frame identity survives the upscale instead of getting diluted.

- Audio generation is untouched — this only changes video conditioning.

Requirements

- ComfyUI with the LTX-2.5 nodes comfy-core, no extra custom nodes)

- LTX-2.5 checkpoint/model files as used by the stock LTX-2.5 template

Usage

1. Load the workflow into ComfyUI.

2. In Load First Frame, upload your starting image.

3. In Load Last Frame, upload your ending image.

4. Write your prompt describing the motion/transition between the two, and set duration/resolution as usual.

5. Queue the prompt.

Credit

Adapted from Comfy's stock LTX-2.5 image-to-video template.