Must the prompt and the image be needed all? if I only use the image or the prompt, what do I need to do ?

deepseek-ai / DreamCraft3D

[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior

https://mrtornado24.github.io/DreamCraft3D/

MIT License

1.88k stars 81 forks source link

Must the prompt and the image be needed all? if I only use the image or the prompt, what do I need to do ? #21

Closed maocaixia closed 6 months ago

MrTornado24 commented 6 months ago

Indeed, both a prompt and an image are necessary. If you only have an image, you can perform image captioning, either manually or by utilizing tools like GPT4-V. On the other hand, if you have a text prompt, you can employ text-to-image models to generate images according to your preferences.