Write and improve prompts for Kling AI video generation and pick the right Kling model. Covers Kling 4.0, Kling 4.0 Flash, VIDEO 3.0, VIDEO 3.0 Turbo, VIDEO 3.0 Omni (including video editing), Motion Control, Avatar 2.0 talking avatars, multi-shot storyboards, Element Reference, Voice Control, native audio, first/last frame control, credit and API costs.
1 skill
Write and improve prompts for Nano Banana - Google's Gemini image generation models. Covers Nano Banana 2 (gemini-3.1-flash-image), Nano Banana 2 Lite (gemini-3.1-flash-lite-image), Nano Banana Pro (gemini-3-pro-image) and the deprecated legacy gemini-2.5-flash-image, plus conversational editing, up to 14 reference images, video-to-image, in-image translation, search grounding, YouTube thumbnails and infographics.
1 skill
Write and improve prompts for ByteDance Seedance 2.0 video generation. Covers the four task types (multimodal reference, video editing, video extension, combined), the shot-by-shot storyboard format the model expects, subject definition and binding to reference assets, the official symbol conventions for dialogue, sound effects, music and subtitles, camera language, constraint words, and fixes for character ID drift, unwanted subtitles and style drift.
1 skill
Write and improve prompts for Z-Image, Alibaba Tongyi-MAI's open-weights 6B image model, and pick the right variant. Covers the Turbo vs. base fork that decides whether negative prompts work at all, the dense-clause prompt style the model was tuned on, photorealism vocabulary, bilingual English/Chinese text rendering, the prompt-enhancer workflow, and the correct inference settings per variant.
1 skill