Step 1: Start with the story you want to tell. If you don’t have an idea yet, ask ChatGPT for memorable historical events that can be told in 1 minute. Then use ChatGPT to turn it into a 1-minute voiceover script.
Step 2: Head to ElevenLabs.io, select the “Text to Speech” feature, and paste in your script. Choose the voice "Ryan - Deep and Meditative". Then click “Generate Speech.”
Step 3: Next, create your source image in Midjourney. Make sure it’s visually rich and detailed so Seedance (2.0 or 2.5) can pick up the style accurately.
Step 4: Then head to Seedance (2.0 or 2.5), upload your source image, and use the following prompt to create your first 15-second clip: "Nazi soldiers marching through a city street. [cut] Low-angle shot of a WWII bomber flying overhead. [cut] Close-up of a burning battlefield with flames and smoke. [cut] Wide front shot of artillery cannons firing at sunrise. [cut] Tracking shot from behind soldiers running across the battlefield. [cut] Side shot of a bomber flying low as explosions erupt below. [cut] Close shot of a soldier thrown back by a large explosion. [cut] Wide low-angle shot of the Eiffel Tower with a Nazi flag. [cut] Close-up profile of a serious military officer looking down. [cut] Medium shot of two intelligence officers studying maps in a war room. [cut] Close-up of the officers discussing the plan. [cut] Top-down close-up of hands marking a route on a map. [cut] Close-up top-down shot of a folder on the table labeled “OPERATION MINCEMEAT,” lit by a narrow beam of light. No music."
Step 5: Keep generating 15-second clips until all your shots are ready. Edit them into your final 1-minute animation. Add the voiceover and match it to the shots. Done
You can repurpose your horizontal videos into vertical IG Reels, YouTube Shorts, or TikToks and use the same content across multiple platforms. Convert the 16:9 video to 9:16 in Seedance 2.0/2.5 with a single prompt: "Convert the original 16:9 horizontal video @(TAG THE VIDEO) into a native 9:16 vertical video. Do NOT simply crop the original video. Intelligently reframe and extend/reconstruct the scene so the vertical composition feels like it was originally created in 9:16. Preserve all important visual information, characters, actions, objects, background details, and story beats from the original horizontal video. Reposition elements naturally within the vertical frame when necessary so nothing important is cut off. Keep the exact same characters, animation, actions, timing, camera movement, environment, lighting, colors, saturation, and visual style as the original video. Maintain correct anatomy, object geometry, perspective, spatial relationships, and continuity. Newly generated areas outside the original frame must seamlessly match the existing environment. Final result: 9:16 vertical, full-frame, naturally composed, no black bars, no stretched image, no important details cropped, and visually consistent with the original 16:9 video."
Step 7: Cross-post the same video across all platforms and track how it performs on each one. (screenshot shared by Cartoon Hero community member
)
https://x.com/Framer_X/status/2095151929743868370?s=20
No comments:
Post a Comment