How is captioning labeled for Lumina-T2I models?

Alpha-VLLM / Lumina-T2X

Lumina-T2X is a unified framework for Text to Any Modality Generation

MIT License

1.82k stars 74 forks source link

Closed nunbuzor closed 1 week ago

gaopengpjlab commented 1 week ago

We use mixture-of-captioner to label images.

TruthSearcher commented 1 week ago

We use mixture-of-captioner to label images.

do you use an VLM to caption images for natural language prompts for T2I?