A merge series focusing on realism with room for creativity to pull away from stock photo vibes.
~ Adobi : I wanted a general model to get more experimental with my generations while still aiming for a realistic feel.
Update : Opensource alternative available as Adobi's Real Open Mix
Portraits, Landscapes
Realism, Paintings, Illustrations, CG, Concept Art
Sampling : Euler A (25), Heun, DDIM (60)
CFG Scale : 5.5 - 8.5
Hires. fix : R-ESRGAN 4x+, 25 Hires steps and Denoising strength 0.4
~ Mix'N'Match, don't need to use all of them
Realism : Cinematic film still, analog style, RAW photo, hyper real photo, ultrarealistic uhd faces, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3, photographed on a Canon EOS R5, 50mm lens, F/2.8, HDR, hyper-realistic, colorgraded, volumetric lighting, volumetric fog, moist, shallow depth of field, reflections
General : blurry, logo, watermark, signature, cropped, out of frame, worst quality, low quality, jpeg artifacts, poorly lit, overexposed, underexposed, glitch, error, out of focus
Realism / General : (semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, digital art, anime, manga:1.3), amateur
Realism / Portrait : (poorly drawn hands, poorly drawn face:1.2), deformed iris, deformed pupils, morbid, duplicate, mutilated, extra fingers, mutated hands, poorly drawn eyes, mutation, deformed, 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
SFW : nsfw, naked, exposed breasts, nude, nudity, erotic
~ will be adding more categories for suggestions soon...
analog style, modelshoot style, alluring blue eyes, cyborgdiffusion, erotic, nsfw, nudity, elden ring style, postapocalypse, knollingcase, swpunk, synthwave, dreamlikeart, mdjrny-v4 style, nousr robot, tiktok, instagram
~ comment if you pick up anything particularly interesting
Textual Inversions :
bad_prompt, bad-artist, EasyNegative, bad_quality, bad-hands-5, bad-image-v2-39000, NG_DeepNegative_V1_32T
Hypernets :
LORAs :
Reffed Models in version info.
credit to phantasion for some of the example pics.
Adobi's Real Flexible Mix [aah!] is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user ArtificeArthouse. Derived from the powerful Stable Diffusion (SD 1.5) model, Adobi's Real Flexible Mix [aah!] 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 Adobi's Real Flexible Mix [aah!] is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as landscapes, character, portaits.
With a rating of 5 and over 9 ratings, Adobi's Real Flexible Mix [aah!] is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of Adobi's Real Flexible Mix [aah!] from here.
To use Adobi's Real Flexible Mix [aah!], 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 Adobi's Real Flexible Mix [aah!], check out our crash course in AI image generation.
Vae :
Recommended : vae-ft-mse-840000
Alternative : Anything VAE
Prime Models :
Dungeons N Waifu's v1.6
URPM v1.3
Noise Offset v1 / safetensors
Sub-Models :
QGO-10b, ChilloutMix, Doctor Diffusion, RPG, Liberty, Catto's Instagram Mix v7.0, DucHaitenAIart v1.2, VisionGen - Realism v1.0, Anything3.0, Art & Eros (aEros), Realistic Vision V1.3, 3DKX, Dreamlike-Diffusion, Protogen x3.4 (Photorealism), Protogen Eclipse Advanced, ZombiMix-v8, ZombiMix-v6
This model contains derivatives of dreamlike diffusion, their license can be found here.