Deep under a mountain lives a sleeping giant, capable to eighter help humanity or create destruction...
A Colossus arise...
This is my first try to create a custom Flux KREA model...
If you like it, feel free to give me some feedback. Also if you want to support me you can do this here. I have spend some good money to build a computer that is capable to actually train Flux-models.. Also training and testing takes also a lot of time and electricity..
https://ko-fi.com/afroman4peace
I tried to improve Flux Krea by blockmerging some parts of Colossus Project into it. This is something I usually do when I get a new checkpoint. Don't expect much changes in some images.
This is a experimental merge between Colossus Project Flux V12 FP16
https://civitai.com/models/833086?modelVersionId=2026227
and Flux Krea DEV https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev
This could be my last full checkpoint I am publishing on civitai. I am currently looking into the upcomming AI law but first I need a break now.. I am tired and exhaused.
The checkpoint isn't well tested.. I had to upload it now because of the EU AI ACT...
Sadly I couldn't upload the FP16 version in time.. ( I have a ultra slow internet connection)
The sad part is here: I have just started to work on this thing. So I am currently testing every single and double blocks. This is just a first step into a real checkpoint. I know that I could get this much better.. And I could train on it too.. I really hope so that I can continue training new checkpoints.. (I mean a full training like I did with the Flux series.)
Credits:
As always a great shoutout for Black Forest Lab who created Flux Krea
Colossus_Project_KREA_Experimental_BASE is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user Afroman4peace. Derived from the powerful Stable Diffusion (Other) model, Colossus_Project_KREA_Experimental_BASE 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 Colossus_Project_KREA_Experimental_BASE is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, animals, space.
With a rating of 0 and over 0 ratings, Colossus_Project_KREA_Experimental_BASE is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of Colossus_Project_KREA_Experimental_BASE from here.
To use Colossus_Project_KREA_Experimental_BASE, 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 Colossus_Project_KREA_Experimental_BASE, check out our crash course in AI image generation.
This is a example workflow used for my latest tutorial. https://civitai.com/articles/17766
DISCLAIMER:
This tutorial/workflow is for private, scientific and educational use only. The settings in the workflow are just samples or suggestions. Feel free to try it with your own ones. I am not claiming any ownership for the results resulting of this workflow. This guide is not to supposed of sharing any checkpoints... just knowledge. Use your own checkpoints and settings..
If you outside the EU you still can share your results though... Your workflow, your model.. I am also interested in your results..
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.