Img2Prompt – Get prompts from stable diffusion generated images
1–10 of 78 posts
Re: Img2Prompt – Get prompts from stable diffusion generated images
#2I'm having a lot of fun dropping in my Midjourney images, getting a more detailed prompt, then putting it back into Midjourney for more interesting variations
Re: Img2Prompt – Get prompts from stable diffusion generated images
#3So I tried it with an image of a monkey that I often use for profile pictures (https://mathstodon.xyz/@OscarCunningham). This image wasn't made by Stable Diffusion. It gave me this prompt:
> a monkey plushie on a white background, photograph taken by steve buscemi from a zoom lens, studio lighting, ultrarealistic
Can someone tell me what Steve Buscemi is doing here?
Re: Img2Prompt – Get prompts from stable diffusion generated images
#4So I tried it with an image of a monkey that I often use for profile pictures ( https://mathstodon.xyz/@OscarCunningham ). This image wasn't made by Stable Diffusion. It gave me this prompt: > a monkey plushie on a white background, photograph taken by steve buscemi from a zoom lens, studio lighting, ultrarealistic Can someone tell me what Steve Buscemi is doing here?
Pictures with zoom lenses, obviously :D
Re: Img2Prompt – Get prompts from stable diffusion generated images
#5So I tried it with an image of a monkey that I often use for profile pictures ( https://mathstodon.xyz/@OscarCunningham ). This image wasn't made by Stable Diffusion. It gave me this prompt: > a monkey plushie on a white background, photograph taken by steve buscemi from a zoom lens, studio lighting, ultrarealistic Can someone tell me what Steve Buscemi is doing here?
Can you clarify whether or not Steve Buscemi actually took the photo?
Re: Img2Prompt – Get prompts from stable diffusion generated images
#6So I tried it with an image of a monkey that I often use for profile pictures ( https://mathstodon.xyz/@OscarCunningham ). This image wasn't made by Stable Diffusion. It gave me this prompt: > a monkey plushie on a white background, photograph taken by steve buscemi from a zoom lens, studio lighting, ultrarealistic Can someone tell me what Steve Buscemi is doing here?
This sounds a lot like the results you get from CLIP interrogation. Maybe they just use that and made another online service for it?
Re: Img2Prompt – Get prompts from stable diffusion generated images
#7So I tried it with an image of a monkey that I often use for profile pictures ( https://mathstodon.xyz/@OscarCunningham ). This image wasn't made by Stable Diffusion. It gave me this prompt: > a monkey plushie on a white background, photograph taken by steve buscemi from a zoom lens, studio lighting, ultrarealistic Can someone tell me what Steve Buscemi is doing here?
Steve Buscemi -> Parting Glances -> AIDS -> monkeys ???
Re: Img2Prompt – Get prompts from stable diffusion generated images
#8interesting.. but my guess is it's using a big library of generated image and prompt pairs? So all its suggested prompts are right out of someones 'stable diffusion prompt cheatsheet.pdf' . That is to say overly outputting commonly known artists, and things like 'trending on deviant art'
Re: Img2Prompt – Get prompts from stable diffusion generated images
#9It's not terribly bad at guessing!
I made a few generic military guys for a side project and the actual prompt isn't too far from what I used.
Re: Img2Prompt – Get prompts from stable diffusion generated images
#10How is this different from image captioning when the model used is a booru model? That's already a thing people do with making their training data for fine tuning these models.