Scenario 官方更新· 一手来源·· 3 天前AI 评分26
新模型：FLUX.3 Max 图生视频、关键帧生视频与文本
New Models: FLUX.3 Max Image to Video, Keyframes to Video & Text
正文 · 原文
Three Black Forest Labs FLUX.3 Max models generate up to 20 seconds of video with native audio from text prompts, stills or multiple keyframes.
Video
- FLUX.3 Max Image to Video: Animates a still image into video with native audio. You can optionally supply a last frame to set the final composition. Output runs up to 20 seconds at 720p or 1080p.
- FLUX.3 Max Keyframes to Video: Pins up to 10 images to specific frame positions to direct the motion. The model generates 5 to 20 seconds of 720p or 1080p video with native audio.
- FLUX.3 Max Text to Video: Generates video from a text prompt using prompt reasoning. Output runs up to 20 seconds at 720p or 1080p with native audio.
来源：Scenario 官方更新 · scenario.com