This is an experimental base model that ended up producing great fantastical and photorealistic results!
I will be allocating monthly buzz to image submissions that showcase the model's capabilities or are just plain amazing. This model will continue to improve as a result and I am happy to award buzz for amazing prompts and images being shared.
π’ New
π΅ Production
π‘ Experimental Edge
π΄ Deprecated
This model started accidentally as I believe some of the good ones do. I have since merged LoRAs and fine-tuned this model with my own LoRAs to get it to a point where I like it. I wish I kept better track and could cite models used. However, over time, I have lost track of what all I merged. I am getting better about this.
I have had great results with a wide range of prompt formats including ChatGPT prompts. These I would venture to guess are great at prompting DALL E 3.
A basic starting point...
Steps: 20 - 60
Sampler: DPM++ SDE, DPM++ 2M SDE, or DPM++ 2S a
Schedule: Karras or Exponential
CFG: 3-6
For inspiration, take a look at some of the images I have shared for each of the model updates, please comment with any questions.
Disclaimer: Descent Engine XL is designed to deliver imaginative and high-quality image generation, but the output is shaped by sophisticated algorithms and user inputs. The responsibility for the content produced using this model rests with the user. Please use Descent Engine XL responsibly, and always follow ethical guidelines when creating and sharing your content.
Descent Engine XL is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user DarkDescent. Derived from the powerful Stable Diffusion (SDXL 1.0) model, Descent Engine XL 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 Descent Engine XL is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as general purpose, highly detailed, base model.
With a rating of 0 and over 0 ratings, Descent Engine XL is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of Descent Engine XL from here.
To use Descent Engine XL, 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 β 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 Descent Engine XL, check out our crash course in AI image generation.
Initial release.
Go ahead and upload yours!
Your query returned no results β please try removing some filters or trying a different term.