Comment on Best text to image generator
rickdg@lemmy.world 10 months ago
Can you give an example of a complete prompt? Are you using Dall-E, Midjourney, Stable Diffusion…?
It seems that all models need to have prompts crafted specifically for them and you need to follow-up with corrections. The follow-up is critical for pretty much anything these LMMs output.
Ragdoll_X@lemmy.world 10 months ago
Image-to-image also helps a lot with SD. Even some roughly-drawn blobs can be the difference between the image almost matching what you had in mind vs. looking exactly how you intended it to.
BlueEther@no.lastname.nz 10 months ago
I just cant get img2img on SD to work for me to get images that are what I want(A1111 front end)