Quick Generate
Select a style, write what you want to see and click Generate
full color (Grafitti art) of nude squatting cyberpunk woman with cyberpunk-sunglasses, high heel shoes, (perfect hourglass figure),(perfect perky tits), (((Grafitti art) (by Carne Griffiths))), on a photographic red-brick wall background, insane details, intricate details, hyperdetailed, low contrast, soft cinematic light, dim colors, exposure blend, hdr, faded
an alien xenomorph hugs ripley
What you want in the image.
Clear
Random

Model Description by Creator

V3 is now live!
As always you can check all the details, get all the data we used, parameters, and code snippets on our substack https://followfoxai.substack.com/p/impact-of-tags-on-sd-general-model

Check out our upcoming roadmap below - lots of exciting things ahead!


About V3

note - this might be a great base for your LORA needs - model is very neutral, can react to all ranges of prompt styles, and can perform across multiple image types


We have added a subset of Booru tags to our images, so now it can react to those tags!

Tags that you should try:

  • Solo - puts one character in the generated image, works quite consistently

  • looking at viewer - has a strong female bias but does a good job of making the character to be centered and look at the camera

  • outdoors - works consistently to generate an outdoor environment or place characters there.

  • blurry - empty generations consistently generate blurry images. When tested as a negative prompt, it has some improvements

  • Blurry background - works quite well to mimic the bokeh style of MidJourney. Here is an example of using it as a positive prompt

  • Jewelry - generates images of jewelry or adds them to the generation

  • indoors - works similarly to the outdoor prompt

Image Generation Recommendations

The model is versatile, and you can prompt it in almost any style. Whether it is MidJourney style prompts or anything from Civitai or Lexica, you should expect some interesting results in most cases.

Additionally, you can now experiment with the tags that we discussed above.

And finally, we highly recommend using some form of upscale method. Here are two of our favorites:

Hires. Fix

Enable Hires. Fix, set denoising strength between 0.3-0.5, upscale by 1.5-2x, and use Latent (nearest exact) or 4x-Ultrasharp upscaler. The rest of the parameters are quite flexible for experimentation.

ControlNet + Ultimate SD Upscale

Check the ControlNet tile upscale method from our previous post (link).

Upcoming Roadmap

Vodka Series:

  • Vodka V3 (complete) - adding tags to captions to see their impact

  • Vodka V4 (in progress) - addressing the ‘frying’ issue by decoupling UNET and Text Encoder training parameters

  • Vodka V5 (data preparation stage) - training with a new improved dataset and all prior learnings

  • Vodka V6 (TBD) - re-captioning the whole data to see the impact of using AI-generated captions vs. original user prompts

  • Vodka V7+, for now, is a parking lot for a bunch of ideas, from segmenting datasets and adjusting parameters accordingly to fine-tuning VAE, adding specific additional data based on model weaknesses, and so on.

Cocktail Series:

These models will be our mixes based on Vodka (or other future base models).

  • Bloody Mary V1 (complete, unreleased) - Our first mix is based on Vodka V2. Stay tuned for this: Vodka V2 evolved from generating good images with the proper effort to a model where most generations are very high quality. The model is quite flexible and interesting.

  • Bloody Mary V2+ (planned): nothing concrete for now except for ideas based on what we learned from V1 and improvements in Vodka base models.

  • Other cocktails (TBD) - we have plans and ideas to prepare other cocktails but nothing is worth sharing for now.

LORAs, Textual Inversions, and other add-ons:

We have started a few explorations on add-on type releases to boost the capabilities of our Vodka and Cocktail series, so stay tuned for them.

Please note that we will share the posts on these explorations regardless of the success. Some will likely fail, but most importantly, we will learn from the process.

Full User Experiences and Solutions:

This is just the first hint on some of our upcoming releases. We are working on translating some of our accumulated experience and our vision into full release products. Stay tuned as we will be sharing more and more about some of our most exciting projects!

Older Versions and History of Vodka

Overview

TLDR: We are releasing Vodka_V2 by FollowFox.AI, a general-purpose model fine-tuned on an updated dataset - now from Midjourney V5.1. And as usual, in this post, we will share all the details how we got there. What you should expect from the mode:

  • We used an objectively better dataset - 2.5x larger, which was cleaned better.

  • The resulting model is quite similar to V1 but marginally better. It’s a step up but not a breakthrough-type improvement.

  • In the current state, we can generate some cool images with some effort

  • The model is still far from effortlessly and consistently generating MidJourney or even top SD models level output


You can read all the details about the model training process on followfox.ai (link to the post), as we can embrace the open-source nature of this community. You can recreate the process, see exactly how we got here, and provide feedback and suggestions on individual aspects of the protocol.

Parameters and Workflow that Works Well for Vodka V2

There is a lot more to test here, but we will share a few observations:

  • Compared to V1, you can try a wider range of CFG values; anything from 3 to 7.5 can generate good output

  • Booru tag-only prompts do not work well since we didn’t tag the dataset

  • Human sentence-type description followed by adjectives and “magic words” works quite well

  • Almost all samplers seem to generate interesting results.

  • SD upscale workflow (outlined below) with tile ControlNet enhances the image quality of this model

  • Using EasyNegative TI (link) is recommended. “blurry” in negative prompts also helps.

Upscale Workflow to Try in Automatic1111

After generating the initial image you like in the txt2img tab (we recommend doing a grid of different samplers and CFG values for each prompt to find the promising ones), send it to img2img.

  • Use the same prompt and sampler as in the original generation

  • Set sample steps high; in our case, we used 150 for most of the images

  • Set width and height to 2x the original. So 512x512 should have 1024x1024

  • Set the denoising strength to something low; we used 0.2 to 0.25.

  • For the CFG value, we used the (original - 0.5) formula. So if the original image was generated at 7.0, we would set it to 6.5.

  • ControlNet settings: enable it; for preprocessor select “tile_resample,” and for model ‘control_v11f1e_sd15_tile’. You can also switch to the “ControlNet is more important” option. No need to adjust any other settings.

  • Make sure to have the “Ultimate SD upscale” extension installed. Select it from the Script dropdown, select the 4x-UltraSharp upscaler, and set tile width and height to 640x640.

  • Press generate, wait a bit, and you should have a decent output. You can repeat the process to go even higher resolution.

Conclusions and Next Steps

We believe the model development is going in the right direction, and we will continue releasing the new versions. And, of course, we will document and release every step of that journey.

For the V3 release, we already have a working hypothesis of where the blurriness and lack of details in some of the generations might be coming from, and we will try to deal with that.

Images Generated With This Model

photo of old man, professional close-up portrait, hyper-realistic, highly detailed, 24mm, dim lighting,  high resolution, iPhoneX, by Peter Kemp vodka_portraits <lora:vodka_v4_portraits:0.7>
N/A
Hidden For Public Users
photo of old man, professional close-up portrait, hyper-realistic, highly detailed, 24mm, dim lighting, high resolution, iPhoneX, by Peter Kemp vodka_portraits <lora:vodka_v4_portraits:0.7>
an alien xenomorph hugs ripley
N/A
Hidden For Public Users
an alien xenomorph hugs ripley
sanji from onepiece, hyunjin from straykids, super-detailed, real, cinematic, movie style, high resolution vodka_portraits <lora:vodka_v4_portraits:0.7>
N/A
Hidden For Public Users
sanji from onepiece, hyunjin from straykids, super-detailed, real, cinematic, movie style, high resolution vodka_portraits <lora:vodka_v4_portraits:0.7>
solo, Katze Pirat Lustige Katze Pirat Halloween, anime style, Trigger Studio style, manga art, comics, inking, graffiti art, graphic, poster bright colors, golden ratio composition, tee shirt crazy intricate design on white background vodka_portraits <lora:vodka_v4_portraits:0.75>
N/A
Hidden For Public Users
solo, Katze Pirat Lustige Katze Pirat Halloween, anime style, Trigger Studio style, manga art, comics, inking, graffiti art, graphic, poster bright colors, golden ratio composition, tee shirt crazy intricate design on white background vodka_portraits <lora:vodka_v4_portraits:0.75>
solo, Katze Pirat Lustige Katze Pirat Halloween, anime style, Trigger Studio style, manga art, comics, inking, graffiti art, graphic, poster bright colors, golden ratio composition, tee shirt crazy intricate design on white background vodka_portraits <lora:vodka_v4_portraits:0.75>
N/A
Hidden For Public Users
solo, Katze Pirat Lustige Katze Pirat Halloween, anime style, Trigger Studio style, manga art, comics, inking, graffiti art, graphic, poster bright colors, golden ratio composition, tee shirt crazy intricate design on white background vodka_portraits <lora:vodka_v4_portraits:0.75>
a 25-year-old American dancer female without makeup with a blue dress, in the style of light purple and dark gray, photo taken with provia, slumped/draped, karencore, amber, timeless grace, american barbizon University vodka_portraits <lora:vodka_v4_portraits:0.75>
N/A
Hidden For Public Users
a 25-year-old American dancer female without makeup with a blue dress, in the style of light purple and dark gray, photo taken with provia, slumped/draped, karencore, amber, timeless grace, american barbizon University vodka_portraits <lora:vodka_v4_portraits:0.75>
vodka_portraits, (Masterpiece, Top Quality, Best Quality, Official Art, Aesthetics :1.2), (A Girl :1.3), from behind, power pose, (Fractal Art :1.3), Movie Light, (Hell Building), Death Light, ((red Particles):1.2), Demon, Moon, clouds, Bright Moonlight Skull, Very long hair, clothes with ridiculous Details, Whirlwinds,  <lora:vodka_portraits:0.7>
N/A
Hidden For Public Users
vodka_portraits, (Masterpiece, Top Quality, Best Quality, Official Art, Aesthetics :1.2), (A Girl :1.3), from behind, power pose, (Fractal Art :1.3), Movie Light, (Hell Building), Death Light, ((red Particles):1.2), Demon, Moon, clouds, Bright Moonlight Skull, Very long hair, clothes with ridiculous Details, Whirlwinds, <lora:vodka_portraits:0.7>
in the style of cyberpunk futurism, african influence, etam cru, light blue and gold, michael creese, steelpunk, michael hussar, white background, best quality, high quality, editorial photo, absurdres, masterpiece, intricate detail, film grain,
N/A
Hidden For Public Users
in the style of cyberpunk futurism, african influence, etam cru, light blue and gold, michael creese, steelpunk, michael hussar, white background, best quality, high quality, editorial photo, absurdres, masterpiece, intricate detail, film grain,
((4k,masterpiece,best quality)), shuimobysim, traditional chinese ink painting, lotus, hanfu, maxiskit, dress conservatively 1 girl, solo, white hair, long hair, fox ears, white, bikini, fish, many fish near girl, look at viewer, tease
N/A
Hidden For Public Users
((4k,masterpiece,best quality)), shuimobysim, traditional chinese ink painting, lotus, hanfu, maxiskit, dress conservatively 1 girl, solo, white hair, long hair, fox ears, white, bikini, fish, many fish near girl, look at viewer, tease
portrait, border collie, black, red, claret color, black beckground, by Tyrus Wong
N/A
Hidden For Public Users
portrait, border collie, black, red, claret color, black beckground, by Tyrus Wong
Dreamy roses and cherries , soft blue, pale pink, craft paper, charming flowers, intricate watercolor details, ambient occlusion shading
N/A
Hidden For Public Users
Dreamy roses and cherries , soft blue, pale pink, craft paper, charming flowers, intricate watercolor details, ambient occlusion shading
A mesmerizing female cyberpunk street artist, creating a vivid and detailed holographic mural in a neon-lit urban alley, ([Diane Lane|Scarlett Johansson|Kate Upton]:0.8), closeup, Amazing fine detail, glowing eyes, [(colorful explosion psychedelic paint colors:1.21)::0.15], detailed background, round cute face, green eyes, detailed clothes, skinny, shinny glossy skin, subsurface scattering, (gothic:0.8), double bun, bangs, frills, skirt, Nikon D850 film stock photograph Kodak Portra 400 camera f1.6 lens, rich colors, lifelike texture, dramatic lighting, unreal engine, trending on ArtStation, cinestill 800 tungsten
N/A
Hidden For Public Users
A mesmerizing female cyberpunk street artist, creating a vivid and detailed holographic mural in a neon-lit urban alley, ([Diane Lane|Scarlett Johansson|Kate Upton]:0.8), closeup, Amazing fine detail, glowing eyes, [(colorful explosion psychedelic paint colors:1.21)::0.15], detailed background, round cute face, green eyes, detailed clothes, skinny, shinny glossy skin, subsurface scattering, (gothic:0.8), double bun, bangs, frills, skirt, Nikon D850 film stock photograph Kodak Portra 400 camera f1.6 lens, rich colors, lifelike texture, dramatic lighting, unreal engine, trending on ArtStation, cinestill 800 tungsten

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.