HomoDiffusion 2 HomoVision

Model author - Deniryer :

HomoVision (I do like cheesy names... sue me :v) Contrary to Homo Diffusion 2 & Homo Diffusion 2 Anime this model aims to be as photorealistic you can be with SD1.5.

Merged in CyberRealistic V3.1, Realistic Vision V3.0 (No VAE), Deliberate V2 and RPG V4 with HomoDiffusion 2.0

Mix is capable of producing same quality images as HomoDiffusion 2.0. Only two differences are the fact that my trained data haven't been converted to more stylistic/illustrative version and due to merging via SmoothAdd MT it inherited more realistic style of all aforementioned models.

Both style of prompting will work i.e anime tags and normal, natural language.

Recommended VAE:

vae-ft-mse-840000-ema-pruned

General Tips

Sentence or prompt structure matters in both SD Next and InvokeAI 3.0. They both handle them differently due to different pipelines, parser and underlining optimisations. Additionally depending on WebUI and it's version some of prompts will be restricted to 75 tokens, meaning anything above that count will be either completely ignored or just split up. Latest version of InvokeAI & SD.Next support up to 225 tokens.

Recommended settings:

SD Next:

Step Count:

From 20 to 70

Samplers:

Euler A, DPM++ a Karras, DPM++ 2M/2S a Karras

Second Pass & Upscaler:

4x-UltraSharp with denoising strength between 0.1 to 0.3, 5 to 50 steps. For second pass sampler you can use combination of sampler mentioned above. Some of them will handle better adding details, textures, some might cause extra issues like double glands, elongated limbs, missing limbs or blurriness.

Refiner:

Since SD Next lets you mix&match not only samplers but refiner for SD 0.9 XL with SD 1.5 base models I do recommend to at least play with new refiners to increase fidelity of generations, get crispy details or to fix some issues.

aDetailer:

Face either mediapipe mesh/full or yolov8s,

Detection threshold varies from 0.3 to 0.45,

Steps count for aDetailer model 12-30,

Resolution for in-painting from 512x512 to 768x768 - it will slowdown generation significantly.

Resolution:

from 512px to 1024px with aspect ratio from 4:3, 3:4 or 16:9, 9:16.

InvokeAI 3.0