Image and video model guides

Choose the model for the input, control, and finish you need.

TongAI brings prompt-based, image-guided, frame-guided, character-reference, LoRA, and motion-transfer models into one creative workspace. These guides explain what each important model can do, which inputs it accepts, how character guidance works, the available resolutions, and how current credit pricing is applied.

Compare current prices

Creative freedom for your prompts and content.

TongAI has no prompt restrictions, including for adult creative themes. Choose the subject, tone, and visual style that fit your idea, and write the direction in your own words.

Use remains subject to our Acceptable Use Policy, consent and rights requirements, and model-provider policies. Generation depends on the selected model’s capabilities and availability.

Model directory

Eight ways to start creating.

Create anime artwork with Anime (WAI), shape recurring characters and visual styles with LoRA Models, or compare image and video models for prompt, reference, and frame-based workflows.

Start with the job, not the model name.

A model is useful only when its supported input matches what you have. If you have a prompt, choose a text-to-image or text-to-video route. If you have a designed frame, choose image-to-video. If identity or wardrobe must carry forward, use a compatible reference workflow and a saved character.

  1. 01Choose your input

    Prompt, source image, opening frame, multiple references, LoRA, or performance video.

  2. 02Compare controls

    Confirm reference support, duration, resolution, audio behavior, and model-specific limitations.

  3. 03Review the live rate

    TongAI shows the exact credit total before submission. There is no fixed daily generation cap while you have credits.

Need the same character across scenes?

Learn how saved characters, face and full-body references, image recreation, and reference video work together.

Explore consistent characters