If you like what I do, leave me a ❤️ to receive notifications of future updates and follow me here on Civitai. Remember that it is a hobby for me and it costs a lot of time and everything is shared entirely for free, I appreciate that you make a review and share your creations on this wall.
Small and final fixes before the next version is released. This will be the last Beta version.
I am currently working only on training hands and human anatomy in general from scratch. I have had several failed trainings, but at least it has helped me to better learn what modifies what. The next update will take a few weeks to arrive, due to lack of time.
This Beta X version is very valid for some things as shown in the sample images that do not have any upscale. After trying Flux, I must say that I am even more committed to bringing this model forward. Flux is very good and does incredible things light years away from Stable Diffusion 3. But my PC burns in hell generating images with it, and it takes too long for me, at least for now. SD3 in that sense is much more manageable for me, and I suppose for many more people like me with a modest PC.
We'll see where this journey takes us...
I hope you'll join me on the journey of Project Zeus SD3.
See you in the next update.
We're out of the Alpha testing phase and I finally have a finished Beta version of Project Zeus SD3 to publish and show you all.
What are the differences between the Alpha and Beta versions, you might ask?
Well, the answer is easy and not so easy. The font change is actually more for me than for the user who downloads the checkpoint and starts generating images. I consider that I have already acquired some knowledge about the Stable Diffusion 3 model and I'm not going so blind anymore.
There is so little information about SD3 training that the concept of trial and error is constant. And it takes a lot of hours because the few tools that exist for it are not well optimized.
Despite the current bad reputation of SD3, I must say that I am pleasantly surprised by the potential it has, it is much more powerful than I expected, despite the fact that the release version of the medium model is a real piece of junk. But there is hope, I am convinced that in a few months there will be a checkpoint that will be on par with the best of SDXL. But we'll see about that, the license, despite having changed, is still a big problem at a commercial level.
Meanwhile, I continue to enjoy racking my brains and publishing this first update of Project Zeus SD3.
I hope you enjoy it.
Sampling method: Euler Simple or DPM++ 2M SGM Uniform
Steps: Between 25-35
CFG Scale: 4-6
P.D. You need to download the necessary clips.
This checkpoint is the result of my preliminary tests and trials with the new Stable Diffusion 3. I have no doubt that despite its hasty release, SD3 has a great future. As well as modders, there is a lot of work ahead.
Here is the result of my first two weeks of work, I hope you enjoy it. It is an Alpha version, it has millions of errors, but you can get some pretty decent stuff out of it.
P.D. You need to download the necessary clips
Project Zeus SD3 is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user DeViLDoNia. Derived from the powerful Stable Diffusion (SD 3) model, Project Zeus SD3 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 Project Zeus SD3 is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as scifi, base model, fantasy.
With a rating of 0 and over 0 ratings, Project Zeus SD3 is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of Project Zeus SD3 from here.
To use Project Zeus SD3, 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 Project Zeus SD3, check out our crash course in AI image generation.
Alpha v0.5 TesT
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.