model request by JimPoison
Model trained with a dataset of DanMumford Style images, use highres fix and non square image sizes for best results!
Example prompt:
By danmumford extremely epic illustration portrait of a car
Negative prompt: bad eyes, jpeg large artifacts, jpeg small artifacts, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, blurry, bad anatomy, blurred, watermark, grainy, signature, cut off, draft, not finished drawing, unfinished image
Steps: 40, Sampler: Euler a, CFG scale: 13.5, Seed: 2830161464, Size: 512x720, Model hash: 588c693bb3, Denoising strength: 0.3, ENSD: 31337, Hires upscale: 2, Hires upscaler: 4x_foolhardy_Remacri
Description
mixed with vintedois v.01
FAQ
Comments (2)
amazing model! can you please share the settings you used for training the first version, i tried training a model on dreambooth on dan mumford's images and it didn't work well. i'm trying to do style models but to little success.
and i actually made a mix of your original model with mine and i think the results look really similar to real dan mumford works
Dm me on discord if you want my settings pls Flonix #4022