OpenArt: “Pinterest” for Dalle-2 images and prompts
1–10 of 101 posts
Re: OpenArt: “Pinterest” for Dalle-2 images and prompts
#2Re: OpenArt: “Pinterest” for Dalle-2 images and prompts
#3would it be possible for the site to allow toggling between Dalle-2 and the recent Stable Diffusion model release?
edit: I mean, letting you filter between images from Dalle-2 and Stable Diffusion, not actually running the same prompt through the models, which this site obviously does not do
given that the latter has weights available for download, and apparently fits in a consumer GPU, there might soon be more demand for that than for Dalle-2...
Re: OpenArt: “Pinterest” for Dalle-2 images and prompts
#4Re: OpenArt: “Pinterest” for Dalle-2 images and prompts
#5this is great. it's really helpful to see what impact certain keywords and phrases have on the output. would it be possible for the site to allow toggling between Dalle-2 and the recent Stable Diffusion model release? edit: I mean, letting you filter between images from Dalle-2 and Stable Diffusion, not actually running the same prompt through the models, which this site obviously does not do given that the latter ha…
Any other feedback or suggestions? :)
Re: OpenArt: “Pinterest” for Dalle-2 images and prompts
#6Re: OpenArt: “Pinterest” for Dalle-2 images and prompts
#7Re: OpenArt: “Pinterest” for Dalle-2 images and prompts
#8Adding model provenance would be a good idea so you can support multiple. I was wondering if DALLE 2 embeds any metadata in the images but haven't had a chance to investigate.
I also think you should consider adding the option to clarify copyright status ... in particular, allow users to dedicate the image to the public domain via CC0 (https://creativecommons.org/share-your-work/public-domain/cc...), or maybe put it under a CC BY license. May be debatable what the legal status of the images is, but a CC0 dedication would at least get rid of any ambiguity.
Re: OpenArt: “Pinterest” for Dalle-2 images and prompts
#9I had this exact idea, so glad it exists :) Adding model provenance would be a good idea so you can support multiple. I was wondering if DALLE 2 embeds any metadata in the images but haven't had a chance to investigate. I also think you should consider adding the option to clarify copyright status ... in particular, allow users to dedicate the image to the public domain via CC0 ( https://creativecommons.org/share-you…
Great idea to add model provenance.
I'm not sure if Dalle-2 embeds any metadata, but openAI also has this CLIP model https://openai.com/blog/clip/ that lets you get embeddings. So we will be using this for our search functionality. It works amazingly well. Stay tuned for the search functionality. It is super powerful for prompt engineering.
Thanks for pointing out the copyright status. Most of the images in Discover are crawled on the web, and you can see all the sources under each image. However for the images that people post on our platform, we should definitely add the clarification for copyright status.