This is axsUltraHorizonV21 - A new Mix collection. This series of professionally merged models is executed with careful planning and design. If the Recipe Ingredients are updated we will release revised versions as time goes on!
While this is an Anime Model, it makes great Photos and CGI too (below V2-Frost)
above using prompt: Photo, Pretty Woman in Green Dress, Sunset Horizon, looks towards the camera and smiling, anime key art by Greg Rutkowski, Bloom, dramatic lighting, bloom, medium shot, mid-shot, highly detailed, trending on Artstation, 4k, cinematic wallpaper by Stanley Artgerm Lau, WLOP (to8contrast style:1) <lora:theovercomer8sContrastFix_sd21768:0.6> <lora:johnsondesuv2-320-e1:0.6>
Negative prompt: (DangerHorse:1.1) (DangerMoose:1.5) (DangerGoose:1)
detailed explanation is below Examples
recommended utilities at the bottom
V2-Examples:
Above comparison using (DangerHorse:1.1) (DangerMoose:1.5) negatives
~
Below same prompt & seed comparison of V2 Versions
using only (DangerHorse:1.1) negative
all other V2 demo pics using (DangerHorse:1.1) (DangerMoose:1.5) negatives
V1-Examples:
Explanation
UNET Block Graphing is used to optimize the merging process.
For a long time we have advocated for the use of advanced merging with many profiles and we evaluated many graphs to test the optimal profile to producing the best outputs in the style we want to achieve. Examples and explanations are below.
This model merges two excellent models together using FCH.
Waifu Diffusion 1.5 Beta 1 (for UltraHorizon V1)
Waifu Diffusion 1.5 Beta 2 (for UltraHorizon V2)
Ultra Cmodel (on CivitAI)
Future versions will use later releases of either source model as an when they are released.
Merge Graph: " FAKE CUBIC HERMITE "
Merging comparisons:
( Ultra Horizon is the center column )
the left shows the merge of both parent models using the default merging process at 0.5 Alpha. The center shows the results using our merge graph and the right hand side is reversed.
Recommended Utilities:
LORA
Contrast Fix
High Key
JohnsonDesu
TI
DangerHorse
DangerMoose
DangerGoose
nfixer
VAE
kl-f8-anime2
Thanks for reading this far, any questions please hit the comments section thanks!
axs Ultra Horizon is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user axsthxticroot. Derived from the powerful Stable Diffusion (SD 2.1 768) model, axs Ultra Horizon 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 axs Ultra Horizon is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, manga, horizon.
With a rating of 0 and over 0 ratings, axs Ultra Horizon is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of axs Ultra Horizon from here.
To use axs Ultra Horizon, 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 axs Ultra Horizon, check out our crash course in AI image generation.