bextoper
A merge model, originally made to fix Featherfall's anatomy and prompt adherence issues.
EndFall 1.1 Style B:
A new merge. Besides Featherfall and Endlustria, it includes Janku and Amanatsu. It doesn't follow Featherfall's style as closely, and instead achieves a more soft and less rough style while still looking drawn. I'd say that it's closer to Amanatsu. It still can achieve rougher styles with sketch, colorized, painterly, oekaki and other tags.
Example images use Res Multistep Ancestral CFG++ with SGM Uniform at CFG 2.5, native 1024 x 1536. No Hires or Face Detailing.
EndFall 1.0:
A simple merge of Featherfall v1.1 and Endlustria v0.1, focused on fixing Featherfall's issues with anatomy and prompt adherence.
Recommended Parameters:
Sampler: Euler a, Res Multistep Ancestral, or their CFG++ counterparts.
Scheduler: SGM Uniform
Steps: 20-30
CFG: 4.5 - 5.5, or 2.0 - 2.5 with CFG++.
Supports both 1MP (1024 x 1024) and 1.5MP (1536 x 1536) resolutions. I recommend 832 x 1216, 1216 x 832, 1024 x 1536, 1536 x 1024, 1024 x 1024, 1536 x 1536.
What is EndFall Illustrious?
EndFall Illustrious is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user bextoper. Derived from the powerful Stable Diffusion (Illustrious) model, EndFall Illustrious 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 EndFall Illustrious is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as style, merge, sdxl.
With a rating of 0 and over 0 ratings, EndFall Illustrious is a popular choice among users for generating high-quality images from text prompts.
Can I download EndFall Illustrious?
Yes! You can download the latest version of EndFall Illustrious from here.
How to use EndFall Illustrious?
To use EndFall Illustrious, 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 EndFall Illustrious, check out our crash course in AI image generation.
Popularity
Info
Version v1.1 Style B: 1 File
About this version: v1.1 Style B
In addition to Featherfall v1.1 and Endlustria 0.1, I added JANKU v5, Featherfall v2 and Amanatsu v1.1. While my initial goal was to fight more anatomical issues of Featherfall while keeping its style, I achieved this overall default style. It should be much more soft than Featherfall and EndFall v1, with the style more akin to Amantsu, while keeping the knowledge and native 1.5MP resolution of JANKU and Illustrious 1.0/1.1/2.0 in general.
To achieve a more rough style, you can always use style tags like sketch, colorized, oekaki, painterly, etc. They work especially well on this model.
2 Versions
Go ahead and upload yours!
