DreamySoft is one preset in the deep-imager AI image generator style library — soft diffusion, not a new syntax.
Pick the style, then write a normal text to image brief.
What does DreamySoft actually change?
It biases the AI image generator toward soft light, gentle contrast, and painterly edges.
You still need a subject and a ratio. The preset is not a prompt.
How do you combine a preset with text to image?
Select DreamySoft, set 1:1 or 9:16, then describe subject and wardrobe in plain language.
Do not also paste “soft dreamy glow” five times; the preset already leans that way.
When should image to image walk the look back?
When faces or logos melted. Upload the still and ask for sharper edges, same composition.
Keep DreamySoft on or off consistently so the second credit is a correction, not a new look.
Does a preset cost extra credits?
No — a still still costs one generate. New users have 5 free credits; Basic is $1/month for 10.
Wait 30 seconds–2 minutes. Paid plans add commercial rights for campaign stills.
Start in text to image or image to image, pick a model such as GPT-4o image, then check pricing from $1/month and how credits work before a long run.