Typ
Checkpoint
Veröffentlichungsdatum
2024-03-30
Basismodelle
SDXL 1.0
Versionsvorstellung
Introducing Aventis Horizon, a general purpose model, built using bleeding edge techniques for mixing prompt adherence with artistic and stylistic flair, improving emotional expression, improving artistic comprehension, and mixed media generation. Using custom trained for purpose models in combination with royalty free community resources for an artistic twist.
Now available on Run Diffusion~! https://app.rundiffusion.com/
Aventis Horizon Version 2 brings unparalleled creativity to your fingertips, with further improvements to prompt comprehension, and style improvements.
Improved prompt coherence (2.5 - 6.5 cfg, 20 - 250+ steps)
Improved stylisation coherence (More creativity with higher quality results)
Enhanced - Anime, Pixel Art, 2D (Additional improvements to these specific styles)
Enhanced mixed media styles integration.
For best results make use of stylistic descriptors, style types, and mixed styles prompting. If you have trouble with basic generations coming out oversaturated try adding the following styles to your negative: pixel, cartoon, anime
Now available on Run Diffusion~! https://app.rundiffusion.com/
Aventis Horizon Version 2 brings unparalleled creativity to your fingertips, with further improvements to prompt comprehension, and style improvements.
Improved prompt coherence (2.5 - 6.5 cfg, 20 - 250+ steps)
Improved stylisation coherence (More creativity with higher quality results)
Enhanced - Anime, Pixel Art, 2D (Additional improvements to these specific styles)
Enhanced mixed media styles integration.
For best results make use of stylistic descriptors, style types, and mixed styles prompting. If you have trouble with basic generations coming out oversaturated try adding the following styles to your negative: pixel, cartoon, anime
