LocalLLaMA

4 readers

4 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 2 years ago

MODERATORS

Is there a fine tune or dataset that focuses on creating prompts that are used in image generation like stable diffusion? (alien.top)

submitted 2 years ago by gee842@alien.top to c/localllama@poweruser.forum

1 comments fedilink hide all child comments

Prompt refinement is something I've been working on and its been tricky to get 3.5-turbo to adhere to my requirements; the images that get produced are pretty mid

you are viewing a single comment's thread
view the rest of the comments

[–] vatsadev@alien.top 1 points 2 years ago

There are plenty of datasets, Just take the ones meant for stable diff training, rip out the prompt text, profit

Heres some high quality captions used for dalle3, etc:

https://huggingface.co/datasets/laion/dalle-3-dataset https://huggingface.co/datasets/laion/gpt4v-dataset https://huggingface.co/datasets/laion/wuerstchen-dataset https://huggingface.co/datasets/laion/220k-GPT4Vision-captions-from-LIVIS https://huggingface.co/datasets/laion/gpt4v-emotion-dataset