|
|
|
|
|
|
by proy24
697 days ago
|
|
|
Hi, thanks for trying it out. Currently the app is using
- Dall-e 3 for generation,
- Dalle-2 for edits,
- OpenAI TTS for speech,
- Suno for Music,
- Segment-anything for object-detection. More models will be added soon for each category, as well as a video generation model...(waiting on sora api to drop :) ) |
|
|