FilmLune · AI generator and gallery
Curated prompts | Create AI images & videos with ease
Understand FilmLune
FilmLune combines an AI image generator with a gallery of image and video examples. Each detail shows the result, available prompt, declared model, and a method you can adapt.
Explore all promptsA readable method
Two ways in
Start with an image example for a still composition, or a video example to study motion, inputs, and duration. Both libraries lead to the same canonical case details.
Useful boundaries
Models and settings describe the visible revision: FilmLune does not silently replace a model during handoff. External work keeps its attribution and source link on the detail page.
Only when that revision’s rights permit it. The detail then preserves the prompt and its provenance; an unavailable action is never replaced with invented content.
No. Model versions, inputs, and settings can change the output. Use the method as a starting point and check the parameters before generating.
SpringWangSeedance 2.0 · MiniPROMPT
A single cobalt-blue ceramic mug on a light oak desk, soft morning window light, photorealistic product photography, no people, no text, no logos. Wide horizontal 16:9 composition.Use @Image 1 as the exact first frame. A single cobalt-blue ceramic mug on the same light oak desk, fixed horizontal camera, gentle steam rising for 4 seconds. An off-screen adult narrator clearly says in English: "Good morning, this is a peaceful cup of tea." No people visible, no other voices, no text or logos. Keep the image composition and 16:9 framing.A two-step workflow: a photorealistic product photograph of a cobalt-blue ceramic mug on a light oak desk, then a short animated clip built from that image, with rising steam and a single spoken line.
Video prompts and examplesProduce a calm, softly lit product visual and extend it into a minimal four-second video for uses such as a website hero moment, a quiet social post, or a morning greeting. The generation text intends a single still-life scene with no people, no text and no logos, lit by soft morning window light.
Step 1 — Generate the image with GPT Image 2.5 in a wide horizontal 16:9 composition. Describe one cobalt-blue ceramic mug on a light oak desk, soft morning window light, photorealistic product photography, with no people, no text and no logos. Step 2 — Use that image as the exact first frame (referenced as @Image 1) in Seedance 2.0 · Mini. Keep the same desk, a fixed horizontal camera and the same framing. Request gentle steam rising for 4 seconds. Add an off-screen adult narrator clearly saying in English: "Good morning, this is a peaceful cup of tea." No people visible, no other voices, no text or logos.
The generated video runs 4 seconds and its output aspect ratio is 54:31, slightly different from the 16:9 source image, which can cause a minor crop. The narration is in English only, with no guarantee of perfect pronunciation and no subtitles. Steam and voice are generated automatically, so results can vary between runs, and the mug itself stays static.