Seedream 4.0: Toward Next-generation Multimodal Image Generation Paper ⢠2509.20427 ⢠Published Sep 24, 2025 ⢠88 ⢠47
view reply Same boat here. We were running everything through closed APIs and the cost spiraled fast. Ended up using gpt-oss-20b locally for prompt rewriting and Veo 4 Video for the video side â way more sustainable for batch jobs.