LTX 2.5 GGUF Image-to-Video
LTX-2.5 GGUF turns images into cinematic videos with synced audio.
AI model workflow
LTX ComfyUI Workflows
Create video with synchronized audio from text or images using LTX in ComfyUI. Choose LTX 2.5 for generation, or explore dedicated workflows for dialogue, multi-shot timing, and video editing. Run them on RunComfy Cloud, download workflow JSON, or deploy supported workflows as APIs.
36 workflows
Featured workflow
LTX 2.5 ComfyUI Image to Video | Realistic Motion & Native Audio
The workflows
36 LTX ComfyUI Workflows
Compare LTX ComfyUI examples by starting input, audio support, and shot control. Open a detail page for its exact LTX version, sample video, and instructions. Run it on RunComfy Cloud, download the workflow JSON, or deploy supported workflows as APIs.
LTX 2.5 First-Last Frame to Video
First-to-last frame animation delivers controlled cinematic motion with synced audio.
LTX 2.3 Director 2.0
LTX-2.3 Director delivers longer, sharper videos with total timeline control.
LTX 2.5 Text-to-Video (Multishot & 4K HDR)
LTX-2.5 turns prompts into sharp cinematic videos with synced audio.
LTX 2.5 Image-to-Video (Native Audio)
LTX-2.5 turns one frame into sharp video with synced audio.
LTX 2.3 Talking & Singing Lip Sync
Turn faces into singing, talking videos with perfect lip sync magic.
LTX 2.3 Video Face Swap
Swap faces in video with natural results and zero flicker.
LTX 2.3 Image-to-Video
Turn images into realistic, cinematic videos with smooth, consistent motion.
LTX 2.3 Close-Up Shots
Turn portraits into sharp, cinematic close-up videos with native audio.
LTX 2.3 Inpaint LoRA
Edit video areas fast with ultra-precise control and flawless continuity.
LTX 2.3 Sulphur Image-to-Video
Turns still images into cinematic motion scenes fast and smooth.
LTX 2.3 Sulphur 2 Text-to-Video
Turn text into cinematic character videos with synced motion fast.
LTX 2.3 Movie Builder
Turn prompts into full cinematic stories with total creative control.
LTX 2.3 Video Outpainting
Expand video scenes smoothly with consistent motion and perspective.
LTX 2.3 Multi-View Videos
Turns single video into consistent multi-camera scene shots fast.
LTX 2.3 IC-LoRA Motion Tracking
V2V Motion-guided video tool for ultra-precise, style-free AI creation
LTX 2.3 IC-LoRA Camera Control
Recreates cinematic camera motion with smooth, controllable precision.
LTX 2.3 Edit Anything
Edit videos fast. Keep motion clear. Total visual control.
LTX 2.3 Director
Turn prompts into full cinematic videos with timeline control.
LTX Video Image & Text-to-Video
Generates videos from image+text prompts.
LTX 2.3 MSR Multi-Subject Video
Keeps every character consistent across complex video scenes.
LTX 2.3 Sulphur 2 Prompt Relay
Turns still images into cinematic motion-controlled videos instantly.
LTX 2.3 ID-LoRA Talking Avatars
Creates true-to-life talking avatars with synced voice and visuals.
LTX 2.3 First-Last Frame to Video
Transforms keyframes into ultra-smooth, realistic video transitions fast.
LTX 2.3 IC-LoRA LipDub
Turn any video into a perfect lip-synced talking masterpiece.
LTX-2 Video Generation
Create real-time videos instantly, faster than any other generator.
LTX 2.3 Dual-Character Lip Sync LoRA
Build lifelike dual-character conversations with synced speech and expressions.
Krea 2 + LTX 2.3 Video Ads
Krea 2 and LTX 2.3 turn products into cinematic ads fast.
LTX-2 First-Last Frame to Video
Turn still frames into seamless video and sound transitions fast.
LTX 2.3 Sulphur Text-to-Video
Turns your text into cinematic, expressive story-driven video scenes instantly.
LTX-2 ControlNet
Sharp control, perfect sync, super clear AI video creation.
LTX 2.3 Text-to-Video
Turn text prompts into cinematic AI videos fast and beautifully.
32 of 36 workflows shown
About LTX
What can LTX do in ComfyUI?
LTX in ComfyUI supports text-to-video and image-to-video generation with synchronized audio in supported workflows. Reference frames and shot controls help guide a scene, while dedicated dialogue, timeline, and editing workflows provide more control over the result.
LTX 2.5 examples cover prompt-based video, image animation, and first-and-last-frame transitions. LTX 2.3 examples add established choices for dialogue, timelines, camera guidance, and video editing. Choose the model version used by the example rather than treating every LTX setup as interchangeable.
Dialogue, face replacement, and frame expansion need more than a basic video prompt. These examples may add audio inputs, LoRAs, or editing stages. Product-ad pipelines can also use Krea 2 to create the source image before LTX animates it.
References and model resources: LTX-2 GitHub, ComfyUI-LTXVideo GitHub, LTX 2.5 documentation, Explore LTX models on Hugging Face, Explore LTX models on Civitai.
Capabilities
Explore LTX capabilities in ComfyUI
Start with a prompt, image, audio track, or existing clip. Choose generation, performance, or editing controls according to how much of the video you need to direct.
Video generation with audio
Turn a scene description into video with synchronized audio using a supported LTX setup.
Image and keyframe animation
Animate from image references, including a defined opening and ending frame.
Lip sync and audio-driven video
Use an audio-driven dialogue setup when a character's performance should follow speech.
Timeline and shot control
Arrange scene timing and guide shots with an LTX Director timeline setup.
Video editing
Use instructions to change existing footage with a dedicated LTX editing setup.
LTX models on RunComfy
Direct LTX video in a prepared cloud workspace
Use ComfyUI to adjust the prompts, images, audio, and shot settings exposed by an LTX example. RunComfy prepares its required dependencies and offers cloud GPU options for video workloads. For local use, download the JSON and install the files listed on the detail page.
Run an LTX workflow nowEditable shot inputs
Adjust the prompt, image, keyframes, or footage accepted by the selected LTX example.
Audio and control assets
Use the audio inputs and compatible control files required by your chosen video setup.
Prepared dependencies
Open the configured model and node environment for the example before customizing it.
Cloud GPU options
Match GPU memory to the model, clip length, resolution, and additional audio or enhancement stages.
Applications
What you can make with LTX
Explore LTX examples for short films, product ads, dialogue scenes, and reframed footage. Each opens a specific production setup with its own inputs.
Product Video Ads
Combine Krea 2 product imagery with LTX camera movement and video generation.
Talking and Singing Avatars
Animate a portrait or character using speech or vocals as a performance input.
Cinematic Camera Shots
Guide camera movement with a reference-motion and compatible LoRA setup.
Video Face Swap
Change a face in existing footage using a dedicated video identity-editing pipeline.
Wider Video Compositions
Extend a clip beyond its original frame with a video outpainting setup.
Frequently asked questions
LTX in ComfyUI: FAQ
Choose an LTX version, check audio and frame-control support, and understand cloud or local requirements before you start.
Which LTX setup should I start with?
Choose an LTX 2.5 text-to-video example if you have a written scene, or image-to-video if you already have a still image. If the opening and ending both need to follow supplied images, choose first-and-last-frame control. Start with the simplest setup that accepts your inputs.
Does LTX 2.5 create video with audio in ComfyUI?
Yes, in setups that include native audio generation, such as the LTX 2.5 text-to-video example. Audio support is not the same across all LTX versions and workflows. Check the example's listed output before assuming it includes sound.
Should I use LTX 2.5 or LTX 2.3?
Both have examples here. LTX 2.5 covers general generation and frame-guided video, while LTX 2.3 also has dedicated timeline, dialogue, and editing setups. Choose the demonstrated result you need, then use its listed version and compatible add-ons.
Can LTX do lip sync from an image and audio?
Choose a talking or singing portrait example when you want an image to perform supplied audio. For dialogue, use a dual-character lip-sync setup. These use additional performance guidance and should not be treated as the same task as generating ambient sound with a video.
How much VRAM do I need for LTX 2.5 in ComfyUI?
Memory use depends on the LTX model format, resolution, clip length, audio support, and any enhancement stages. Check the requirements of the selected example; a lower-memory setup may trade speed or resolution for a smaller footprint. You can use a suitable cloud GPU if the local requirements exceed your hardware.
Can I choose the first and last frame of an LTX video?
Yes. A first-and-last-frame example uses your opening and ending images to guide the clip. This is useful for planned reveals and transitions, but it does not guarantee every intermediate frame will follow an exact path.
Where can I download an LTX ComfyUI workflow JSON?
Use Download JSON on an LTX card or detail page and open the file in ComfyUI. Install the matching model files and any audio components or custom nodes listed for that example before running locally. Run now opens its prepared cloud setup.
Related resources
More ways to use LTX
Train an LTX LoRA with the supported LTX-2, LTX-2.3, or LTX-2.5 base, or use LTX 2.5 directly from RunComfy Models.
Train an LTX-2 LoRA
Train a custom visual or motion concept against the original supported LTX-2 base.
Open LTX-2 TrainerTrain an LTX-2.3 LoRA
Create an identity, style, or motion LoRA for the LTX-2.3 workflows on this page.
Open LTX-2.3 TrainerTrain an LTX-2.5 LoRA
Train against the newest supported LTX-2.5 base for compatible video generation workflows.
Open LTX-2.5 TrainerUse LTX 2.5 models directly
Open the LTX 2.5 Models page when you want direct video generation instead of starting from a workflow graph.
Browse LTX 2.5 Models