Search
Results for “open source”
2 models, tools and templates match.
Showing 1–2 of 2
smart_toy
auto_fix_highImage Effects
minimax/h3-image-edit
MiniMax H3 Image Edit is the image-editing mode of MiniMax H3 — also known as Hailuo 3.0 — the open-weights multimodal model MiniMax launched in July 2026. Feed it up to nine reference images and a written instruction and it re-renders the subject into a new scene, outfit or style while holding on to their identity, at 1K or 2K.
Minimax
bolt3~20s
Try itsmart_toy
image_searchImage to Text
wowmachine/florence-2-large
Florence-2 Large is Microsoft's specialist image-captioning model — pass one image, get a text description back. Pick the caption verbosity (`Caption` for alt-text, `Detailed` for a sentence, `More Detailed` for a paragraph). Fast, cheap, ideal for batch metadata work on product catalogues.
bolt1~3s
Try it