Trigger Word dcanchfutre.
This lora was inspired by https://x.com/Macbaconai who uses a range of different tools including midjourney to produce stunning images, This lora is based on his first generation style of images
Trained with AI-Toolkit for 7000 steps Rank 32 Tagged with detailed captions consisting of 100-150 words with GPT4o (224 Images Total)
All images have Prompts, generation details Workflow for ComfyUi just click the image you want, then save, then drop into ComfyUI or Open the image with notepad on pc and you can search all the metadata there. My workflow has multiple Upscalers to choose from Seedvr2, Flash VSR, SDXL TILED CONTROLNET, Ultimate SD Upscale and a DetailDaemon Upscaler and an Qwen 3 llm to describe images if needed
If you use this in a merge, to train a model or even use on another site generator please credit me by directing to my civitai page https://civarchive.com/user/dkpc69
Description
Z Image Base is better for making things look more vibrant, vast and monolithic, Flux Klein 9b has better smaller details, Both are really good in there own way, Both are bad at faces i will need to add more faces in dataset next time.