05ac2459-f50b-4fcc-88d5-63c3523a591d.png

2ccc4a7d-4a6d-49bb-8fcb-b78ade351af2.png

5b35b780-27be-469f-98db-1e27950e6ad3.png

555fe4dc-60a0-4429-a4b5-d17a76b655e2.png

3a63f044-1cf7-4879-bb71-4744e102b077.png

a904f85a-8053-4bdd-bd1a-96ce67ebbddd.png

405ad7ca-7d5f-4475-ba97-0da1866671b1.png

fa78c404-121d-48b3-a8a8-7029cddaec7d.png

ce112f10-9795-4221-b3e4-039621671178.png

19ccf475-88a2-4848-9df2-523389e68729.png

High saturation is much less frequently an issue in this version at 7 CFG than the last. But if it happens again, it helps to pull back to 6.

`<neg-sketch-2>` negative embedding highly recommended for realism and 3D style images (among others). It can be found here: https://huggingface.co/JPPhoto/neg-sketch-2

When prompting for paintings, I suggest using "framed, borders, photo" as your negative prompt to get fullscreen images and cut out any weird 3D-like people.

When prompting for illustrations, I like to use "photo" or "realistic" as my negative prompt.

When prompting for realism, I normally use a negative prompt of `<neg-sketch-2>` at 1.1 weight and "(anime, render, pixar, illustration, sketch)" at 1.2 weight.

[Garbage-bin concepts LoRA](https://civitai.com/models/95391?modelVersionId=101827) recommended for any intense silliness.

[Example images hosted on Civitai](https://civitai.com/models/15022?modelVersionId=132011) were generated in InvokeAI's Nodes using latent upscaling from close to ~512x resolution up a few hundred pixels each side at 0.55-0.65 strength w/ DDIM. This was followed up with an ESRGAN model upscale, then converting the image to latents and using ControlNet Tile in a latent to latent stage at 0.2-0.4 strength w/ DDIM.

526Mix-V1.5

526christian/526mix-v1.5