What do you want to make?

Animate any image with MiniMax H3 while AI writes the prompt. Photo-to-video with sound for AI influencers, characters and cartoons.

Turn a photo into an AI video with sound using MiniMax H3 in ComfyUI. Animate your AI influencer, AI character or cartoon image.

Consistent AI characters in video: give MiniMax H3 image, video or audio references and let AI write the prompt. Sound included.

Skip LoRA training: load saved RefMods of your character, video or voice into MiniMax H3 and make consistent AI video with sound.

Text-to-video with MiniMax H3 where AI writes the prompt for you. Give a simple idea and get an AI video with sound in ComfyUI.

Free ComfyUI workflow for MiniMax H3 text-to-video with built-in audio. Type a prompt and get AI video of your AI influencer, character or cartoon scene.

Save a sound or voice clip as a MiniMax H3 RefMod and reuse it in your AI videos. Audio references, no training needed.

Save your AI character as a MiniMax H3 RefMod from a few photos. No LoRA training: a fast way to keep AI influencers consistent.

Save a video clip as a MiniMax H3 RefMod and reuse its look and motion in new AI videos. A free alternative to LoRA training.

One-click MiniMax H3 image-to-video: AI writes the prompt, then a 2x upscale sharpens it. Great for AI influencers and cartoons.

MiniMax H3 image-to-video with sound and a 2x latent upscale. Animate your AI influencer or cartoon character in sharper quality.

MiniMax H3 reference-to-video with auto prompting and a 2x upscale. Keep your AI character consistent in sharp AI video with sound.

The easiest MiniMax H3 text-to-video: AI writes your prompt, then a 2x upscale sharpens the AI video. Audio included.

MiniMax H3 text-to-video with sound, plus a 2x latent upscale for sharper AI video. Built for AI influencer, character and cartoon content.

Free Boogu Base text-to-image ComfyUI workflow. Create AI character art, cartoon images and AI influencer photos from a prompt.

Edit images with text using Boogu Edit. Change outfits, styles and scenes for your AI character or cartoon art in ComfyUI.

Boogu Turbo text-to-image in 4 steps: fast AI images for characters, cartoons and AI influencers. Free ComfyUI workflow.

Krea 2 Turbo plus the PiD upscaler: realistic AI influencer photos at 4K. Free ComfyUI workflow for sharp, natural-looking images.

Free Krea 2 Turbo ComfyUI workflow for natural, photorealistic AI images. Make AI influencer photos that look like real phone pictures.

Edit images with text using Qwen Image Edit 2511. Change outfits, poses and backgrounds of your AI influencer or character in ComfyUI.

Build a LoRA training dataset from one image: Qwen Image Edit makes a batch of outfits and poses of your AI character, with realistic skin.

Generate dozens of camera angles of your AI character from one image with Qwen Image Edit. Perfect for AI influencer photo sets.

Qwen Image 2512 with a detail pass and upscale for ultra-realistic AI influencer photos. Free ComfyUI text-to-image workflow.

Qwen Image 2512 text-to-image with easy prompt boxes and a resolution multiplier. Make AI influencer photos and characters in ComfyUI.

Make 4K AI images with Qwen Image and the PiD upscaler. Fast Lightning generation for sharp AI influencer and character portraits.

Free Qwen Image 2512 text-to-image ComfyUI workflow. Create realistic AI influencer photos, AI characters and cartoon art from a prompt.

Z Image Turbo with a 1.5x upscale for sharper realistic AI images. Free ComfyUI workflow for AI influencer and character photos.

Free Z Image Turbo ComfyUI workflow: fast, realistic AI images from text. Great for AI influencer photos and character art.

Z Image Turbo plus the PiD upscaler for 4K AI images. Fast, realistic AI influencer and character portraits in ComfyUI.

SCAIL 2 motion transfer in ComfyUI: animate your AI character with the moves from any video. Free workflow for AI influencer and cartoon videos.

Animate an image with Wan 2.1 image-to-video and get smooth 60 fps AI video. Free ComfyUI workflow for AI influencers and cartoons.

Free Wan 2.1 text-to-video ComfyUI workflow with smooth 60 fps interpolation. Create AI character and cartoon videos from a prompt.

Use the Wan 2.2 video model to make photorealistic AI images from text. A free ComfyUI workflow for AI influencer and character photos.

Make AI videos up to 20 seconds long with Wan 2.2 SVI. Chain four scenes, each with its own prompt and LoRAs, into one smooth clip.

Animate any image with Wan 2.2 image-to-video in ComfyUI, with 60 fps frame interpolation. Bring AI influencers and cartoon characters to life.

Free Wan 2.2 text-to-video ComfyUI workflow with smooth 60 fps output. Make AI influencer, AI character and cartoon videos from a prompt.

Free Wan Animate motion transfer workflow: put your AI character or AI influencer into any video. Character image plus driving video equals AI video.

Keep a real face consistent in AI video with LTX 2.3 Face ID. Upload a face and make AI influencer videos with the same identity, plus audio.

Draw the motion yourself: LTX 2.3 motion tracking turns an image into AI video that follows your paths. Free ComfyUI workflow with audio.

Direct your AI video like a film: LTX Director lets you set keyframes, timed prompts and audio on a timeline. Free LTX 2.3 ComfyUI workflow.

LTX 2.3 text-to-video and image-to-video in one free ComfyUI workflow. Fast AI video with audio for AI influencers, characters and cartoons.

Animate any image with LTX 2.5 image-to-video and get AI video with sound. Free ComfyUI workflow for AI influencers, characters and cartoons.

Free LTX 2.5 text-to-video ComfyUI workflow: generate sharp AI video with sound from a prompt. Great for AI influencer and cartoon content.

Free Qwen Image 2.1 text-to-image ComfyUI workflow. Generate high-resolution AI influencer photos, AI characters and cartoon art.

Keep your AI character consistent with Qwen Image 2.1: add up to 10 reference images and a prompt. Free ComfyUI reference editing workflow.

Generate video with native audio from a written scene, a starting image or reference media. MiniMax H3's reference mode accepts images, video and audio to guide the result.

Create video and synchronized audio from text or a starting frame. Use LTX 2.3 with motion-tracking and director graphs, or opt into LTX 2.5's updated prompt understanding and distilled model.

Generate and edit images, explore camera angles and upscale your results. Choose the models you need before deploying.

Direct a scene's lighting, colour and motion from text, or animate a still with Wan 2.2. The template adds a still-image graph and SVI video extension alongside its text-to-video and image-to-video setups.