Veo3.1 Fast Reference-to-Video
Google Veo 3.1 Fast Reference-to-Video generates 8-second videos from up to three reference images using the official Veo predictLongRunning endpoint with referenceImages assets.
作例
Use the first image as the main subject reference and the second image as the outfit reference. Preserve the same male model, pose, body proportions, camera angle, studio background, and lighting from the first image. Replace his current black leather outfit with the clothing from the second image: a clean white T-shirt, navy blue shorts, white sneakers, and a beige straw hat. Make the outfit fit naturally on his body while keeping the dynamic fashion pose. Maintain realistic fabric texture, natural folds, accurate shadows, and commercial fashion photography quality. The final image should loo
このプロンプトを試す →
Use the first image as the main subject reference and the second image as the outfit reference. Preserve the same male model, pose, body proportions, camera angle, studio background, and lighting from the first image. Replace his current black leather outfit with the clothing from the second image: a clean white T-shirt, navy blue shorts, white sneakers, and a beige straw hat. Make the outfit fit naturally on his body while keeping the dynamic fashion pose. Maintain realistic fabric texture, natural folds, accurate shadows, and commercial fashion photography quality. The final image should loo
このプロンプトを試す →
Use the first image as the main subject reference and the second image as the outfit reference. Preserve the same male model, pose, body proportions, camera angle, studio background, and lighting from the first image. Replace his current black leather outfit with the clothing from the second image: a clean white T-shirt, navy blue shorts, white sneakers, and a beige straw hat. Make the outfit fit naturally on his body while keeping the dynamic fashion pose. Maintain realistic fabric texture, natural folds, accurate shadows, and commercial fashion photography quality. The final image should loo
このプロンプトを試す →仕様
似たモデル
すべてのモデル →料金はレンダーごとで、レンダーが成功したときだけ残高から差し引かれます。失敗したレンダーは自動的に返金されます。作例はモデルにできることの一例で、実際の結果はプロンプトと設定によって変わります。