LTX 2.5 — First/Last Frame to Video (FLF2V)
Quick answer: LTX 2.5 FLF2V generates a video that blends a first and last reference image into a single animated sequence, using Lightricks' LTX-2.5 model. It's built for transition shots, morphing between two subjects or scenes, and multi-shot narratives built from still reference frames.
What this template does
Generate a video from first and last frame reference images using LTX-2.5, blending both frames into a single animated sequence. Ideal for creating transition shots, morphing between two subjects or scenes, and building multi-shot narratives from still reference frames.
Before you run this
This needs a capable GPU. Requirements: CUDA GPU with 32GB+ VRAM, 32GB system RAM, ~100GB free disk space for model files (Lightricks' official minimum for LTX-2.5; 64GB+ RAM and 200GB+ SSD recommended). Windows desktop app or CosyCloud.
Frequently asked questions
How much VRAM do I need?
At least 32GB, per Lightricks' official LTX-2.5 requirements — plus 32GB system RAM and about 100GB free disk space for the model files. Below that, use CosyCloud instead of trying to force a local run.
Does this template generate audio too?
No — this workflow is video-only. If you want synchronized audio generated alongside the video, use the LTX-2.5 Text/Image to Video (Two-Stage Distilled) CosyFlow instead.
Open CosyTemplates and search "LTX-2.5" to find this workflow.
Reviews
What our community is saying about us
Jose Romero
Illustrator
Promptus Cosyflow interface works like magic - we didn’t even know we needed.
Dmitry Selivanov
Art director
We’ve been recommending Promptus to everyone we know who’s interested in starting in AI art design.
Sadiya Abdullah
Brand agency
Promptus saved me hours of fiddling with setup. It just works. I can create custom workflows and generate videos for my clients in seconds.
Lupe Rodriguez
Product designer
Promptus has transformed my product design process. The support, advanced in-design, in-painting features and immediate access to new models is a game changer. Highly recommend!
Dianne Russell
Graphic Designer
This isn’t just a tool; it’s a playground for your imagination.
Marie McKinney
Game designer
As a game design studio, Promptus has been invaluable. The GPU marketplace allowed us to test 3D and video workflows affordably, and the secure web hosting has allowed us to quickly share our designs with our clients and fans.
Share your compute
Join our distributed GPU compute network. Help us make AI accessible, scalable
and secure for designer, developers and start-ups.
FAQ Section
Frequently Asked Questions
What is Promptus?
Promptus enable users to generate customized, AI videos, high-resolution images, AI characters, music, audio, chat and more with ease using the latest's AI models.
Anyone can use Promptus AI—designers, marketers, hobbyists, or beginners—to generate AI art, photos, and videos quickly and easily.
What is an AI workflow?
An AI workflow is a structured process that turns inputs into repeatable outputs using models, prompts, and logic.
Can I create realistic photos with AI?
What is the GPU compute?
Does Promptus work with ComfyUI workflows?
Start running your first workflow
Go from idea to production-ready output in minutes.
Try Promptus for free ➜