What do you want to make?

Animate a starting image with an OpenRouter-assisted prompt and generated audio.

Animate a starting image using your own scene prompt, with generated audio.

Guide a video with reference media and an OpenRouter-assisted scene prompt.

Use reference conditioning to guide a MiniMax H3 video and its audio.

Expand a scene idea with OpenRouter, then generate video with audio.

Generate a video and audio from your own written scene.

Encode and save an audio reference pack for a compatible MiniMax H3 workflow.

Encode and save image references for a compatible MiniMax H3 workflow.

Encode and save a video reference pack for a compatible MiniMax H3 workflow.

Animate an image with an assisted prompt, then upscale the video in latent space.

Animate a starting image with your own prompt and add latent video upscaling.

Generate from reference media with an assisted prompt and latent video upscaling.

Turn a scene idea into video with assisted prompting and latent upscaling.

Generate video from your own scene prompt, then upscale before decoding.

Use reference media and a written prompt to guide video generation with audio.

Generate images from a text prompt with Boogu Base.

Transform a reference image with written editing instructions.

Generate images from a text prompt with the Boogu Turbo model.

Generate with Krea 2 RAW and its Turbo LoRA, then upscale through PiD.

Generate images with Krea 2 RAW and its Turbo LoRA.

Edit a reference image with text instructions using Qwen Image Edit 2511.

Turn a character reference into a batch of images for dataset review.

Generate a batch of camera angles and framings from one reference image.

Generate with Qwen Image 2512 and continue through an image detail and upscaling pass.

Create images with Qwen Image 2512 and configurable sampling and LoRA controls.

Generate an image with Qwen Image 2512, then upscale it through PiD.

Generate images from a written prompt using Qwen Image 2512.

Generate with Z Image Turbo and add a tiled image-upscaling pass.

Generate images from a written prompt using Z Image Turbo.

Generate with Z Image Turbo, then enlarge the image through PiD.

Animate a character reference using motion from a driving video.

Drive character animation with a reference image and extracted video poses.

Animate an image with Wan 2.1, then interpolate the output to 60 FPS.

Generate a video with Wan 2.1, then interpolate the output to 60 FPS.

Use Wan 2.2 high- and low-noise models to generate a still image.

Build an image-to-video sequence across four passes with separate LoRA controls.

Animate a starting image with Wan 2.2 and frame interpolation.

Generate video from a written prompt with Wan 2.2 and frame interpolation.

Transfer movement from a driving video to a reference character.

Guide video generation with Face ID conditioning and a reference image.

Guide motion with track controls and the LTX 2.3 motion-tracking LoRA.

Use Director controls and reference guides to shape an LTX 2.3 video.

Generate a video from text or a starting image, with a latent-upscaling stage.

Animate a starting image with LTX 2.5, generated audio and latent upscaling.

Generate video and audio from a scene prompt with LTX 2.5 and latent upscaling.

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.

Use Qwen Image 2512 for detailed portraits and text layouts, or Edit 2511 for identity-preserving edits. Add Krea 2 for visual concepts and Z-Image Turbo for photoreal images with English or Chinese text.

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.