Re:Stable Video Diffusion
by achileas on Tuesday November 21, 2023 @08:38PM
(#38373461)
> Has anyone come across a solution where model can iterate (eg, with prompts like "move the bicycle to the left side of the photo")? It feels like we're close.
Nearly all of the available models have this, even the highly commercialized ones like in Adobe Firefly and Canva, it’s called inpainting in most tools.
Re:Stable Video Diffusion
by btbuildem on Wednesday November 22, 2023 @09:05AM
(#38379277)
I think that's more "inpainting" where the existing software solution uses AI to accelerate certain image editing tasks. I was looking for whole-image manipulation at the "conceptual" level.
Re:Stable Video Diffusion
by achileas on Monday November 27, 2023 @04:02PM
(#38438236)
They have this. Inpainting is just a subset of the image-to-image workflow and you don't have to provide a region if you want to do whole-image manipulation.
Nearly all of the available models have this, even the highly commercialized ones like in Adobe Firefly and Canva, it’s called inpainting in most tools.