Hyper
Surprise!
Recommended Settings:
Resolution up to 1024
DPM+ SDE with 6 Steps
CFG scale 2
Clip Skip 1
No VAE
Hires Fix with 2 steps, upscale by 1,5
FINAL
Final Version / Goal reached
Works with resolutions up to 1024x1024
You can use HiRes-Fix and any Sampler
Use negative prompts to improve (goal of this checkpoint was always to get realistic images without prompting too much)
Enjoy!
PRO
Improved Version
better and easier prompting
better at high resolutions
even more realism
Recommended Settings:
Clip skip 1
DPM++ 2M Karras or DPM++ SDE Karras with 12-30 steps
High res fix with 10 steps and any realistic upscaler (4x UltraSharp /4x NMKD etc.)
Denoising 0.25 - 0.35
CFG 7
V2 and BETA
Goal is to get better eyes and better light compared to v1. No need to prompt too much, basicly a beginner Checkpoint. Enjoy and share your creations, helps me to improve.
BEGINNER
Use simple prompts (see generation info in images)
No need to use "best quality, 8k, photorealistic..."
No negative prompts unless there's something wrong
EXPERIENCED
Try realistic stuff, SFW, NSFW, Art, everything is possible.
You can keep it simple to get good results.
Negativ template:
(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime), text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck
V1
Use simple prompts (see generation info in images)
No need to use "best quality, 8k, photorealistic..."
Negative template:
(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime), text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck
unStable Illusion - v2 BETA VAE baked is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user Peli86. Derived from the powerful Stable Diffusion (SD 1.5) model, unStable Illusion - v2 BETA VAE baked has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that unStable Illusion - v2 BETA VAE baked is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as 3d, person, photorealistic.
With a rating of 0 and over 0 ratings, unStable Illusion - v2 BETA VAE baked is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of unStable Illusion - v2 BETA VAE baked from here.
To use unStable Illusion - v2 BETA VAE baked, download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like unStable Illusion - v2 BETA VAE baked, check out our crash course in AI image generation.
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.