kling-2-6/pro/text-to-video
Create lifelike 1080p clips from text with synced audio and flexible ratios.
LTX 2 Retake Video is a video-to-video refinement engine. Unlike text-to-video generation which starts from scratch, LTX 2 Retake Video takes an existing video file and re-processes it based on your instructions. It is designed to fix artifacts, improve temporal consistency, and apply stylistic adjustments while preserving the scene's geometry and camera movement.
video_url (required): The source video to be retaken.prompt (required): Instructions for the refinement.start_time & duration: Select a specific segment to process if needed.retake_mode: Choose between modifying video, audio, or both.Create lifelike 1080p clips from text with synced audio and flexible ratios.
Cinematic motion model for fluid scene creation and adaptive visual editing.
Animate a single image into a smooth video with Kling 2.1 Standard.
Convert visuals to cinematic videos quickly with Veo 3.1 Fast image-to-video for seamless creative control.
Generate premium videos with synced audio from text using OpenAI Sora 2 Pro.
Convert photos into expressive talking avatars with precise motion and HD detail
LTX 2 Retake Video is a refinement tool. Unlike generation models that create from scratch, it modifies an existing video to fix errors, improve quality, or adjust the style while keeping the original motion and composition intact.
Yes. One of the primary uses of LTX 2 Retake Video is to repair specific artifacts. You can prompt the model to "fix hands" or "stabilize face," and it will regenerate those details with higher fidelity.
No. The output video retains the exact duration and frame rate of the input clip, ensuring it fits perfectly back into your timeline or project.
Typically, yes. Because the model has a strong visual reference (the input video) to guide it, LTX 2 Retake Video often converges on a high-quality result faster than trying to generate a perfect clip from scratch with a text prompt.
Absolutely. You can use prompts like "sunset lighting," "black and white film," or "neon atmosphere" to completely change the mood of the scene while preserving the original subject action and camera movement.
RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.
