Models that make up the merge:
https://civarchive.com/models/334673/divinity
https://civarchive.com/models/337719?modelVersionId=378139
https://civarchive.com/models/355569/worldofgoddesses
It is strictly prohibited to distribute, inside and outside civit ai, this model or respond anywhere or hosting services, in third-party image generation services, you can use it for personal use, if you know who distributed it without my consent , report it immediately
Sweety dream was made for you and creates beautiful sweets to be enjoyed by beautiful women, young people and girls!
Note: This model already has the vae included!
This model has many features, discover its maximum potential!
I recommend using the Adetailer extension.
Use this extension to fix hand errors:
https://github.com/licyk/advanced_euler_sampler_extension
Recommended settings:
Standard resolutions 512 x 768, 768 x 512 and 1024x 1024
Resolution: 540x540 mark the Hires.fix, result 1080 x 1080 pixel
Resolution: 540x960 mark the Hires.fix, result 1080 x 1920 pixel
Use this configuration recommended settings:
Sampling method: Euler _Max
Sampling steps: 20-30
CFG Scale: 3.5 -7.0
Clip Skip: 1-2
Use this configuration recommended settings:
Sampling method: Euler a
Sampling steps: 20-30
CFG Scale: 3.5 -7.0
Clip Skip: 1-2
Sampling method: DPM++ 2M Karras
Sampling steps: 20-40
CFG Scale: 3.5 -7.0
Clip Skip: 1-2
Sampling method: DPM++ SDE Karras
Sampling steps: 20-30
CFG Scale: 3.5 -7.0
Clip Skip: 1-2
Hide
Description
Base model design_pixar v2 merged with flux1-dev-bnb-nf4-v2. This model will generate photographic, realistic, anime, and 3d images!
If you want to have the pizar effect, enter these words in the prompt:
medium eyes, detailed eyes, expressive eyes, realistic, disney pixar style, 3d, 3d rendering
Resolution settings:
Standard resolutions 512 x 768, 768 x 512, 540 x 960 and 1024 x1024
Resolution: 540x540 select the Hires.fix checkbox, result 1080 x 1080 pixels
Resolution: 540x960 select the Hires.fix checkbox, result 1080 x 1920 pixels
Use these recommended settings for generation:
Sampling method: Euler-simple
Sampling steps: 20
CFG Scale: 2.0 - 7.0
FAQ
Comments (5)
@Dxdesignia
How are you able to merge a SD 1.5 model with a Flux NF4 model?
The mentioned models are all made by the same author, so I would assume this model was trained on the combination of their source data.
the hybrid fusion of different models, 70% is a fine-tuned model and 30% sd models including loras models, in the merge
Can't load this model in any ComfyUI flux workflow, that work for FLUX Dev or FLUX Dev FP8.
I recommend using this model with stable diffusion forge most updated version f2.0.1v1.10.1, to work with ComfyUI, you need a workflow