- You can download version 8.0 as Digital Product or with Membership September 2025 models collection.
- You can download version 7.0 as Digital Product or with Membership July 2025 models collection.
- You can download version 6.0 as Digital Product or with Membership July 2025 models collection.
- You can download version 5.0 as Digital Product or with Membership July 2025 models collection.
- You can download version 4.0 as Digital Product or with Membership July 2025 models collection.
- You can download version 3.0 as Digital Product or with Membership July 2025 models collection.
- You can download version 2.0 as Digital Product or with Membership July 2025 models collection.
- You can download version 1.0 as Digital Product or with Membership July 2025 models collection.
- More cool models.
How it works?
Choose Product or Subscribe:
Get this model via a Ko-fi product, or
Join the appropriate membership tier:
Model released during current month: Current Month Content
If model released in previous months: All Months Content
You will be prompted to link your Hugging Face and Ko-fi emails.
Hugging Face access is checked by email, which might be different from your Ko-fi email. You will receive a link from Ko-fi to add the email and continue.Request Access on Hugging Face:
After you acquired product or subscription, you’ll receive a link to a gated Hugging Face repository.Click "Request Access".
Your access will be approved automatically within a minute.
Download & Use:
You can then download and use the model under the license provided in the repository (LICENSE.md).
Why I Created My Own Access Control
I have been a creator on Civitai since December 2022. My goal has always been to help make model training, design, and development a sustainable, professional activity, not only for myself, but for other creators too. Supporting people who want to create models professionally is good for users, for creators, for the entire community, including Civitai itself.
Civitai has shared some of this vision and has tried to create ways to support creators. Unfortunately, their current Creators Program has serious problems:
Civitai was deplatformed by payment processors and operates at a loss.
The current compensation model pays creators mainly for model usage in the generator.
Early Access limits paid access to only 15 days, after which models must be free.
Buzz extraction value has dropped to ~45% of its original worth, making withdrawals basically a 55% fee.
Bugs and creator feedback are ignored for months, and several team members who used to listen have left.
I believe this system is unfair, harmful, and exploitative. Creators should be able to:
Sell models without arbitrary time limits.
Pay a fair platform fee of 15% or less.
Civitai briefly tested a much better system called Clubs in early 2024, which worked well for creators, but it was canceled after backlash from a loud minority that opposed fair creator compensation. I have long hoped Civitai would fix these issues, as I’ve suggested in my articles:
But nothing has changed. Bugs remain unresolved, feedback is ignored, and I’ve lost optimism about Civitai’s willingness to improve.
That’s why I’ve decided to experiment with my own alternative access control system, a fairer way to share models with users who value my work.
ℹ️ v8.0: This release marks a sharper, more confident step forward in the Five Stars lineage. While previous versions focused on balance, flow, and refinement, version 8.0 places emphasis on clarity, richness, and precision across every aspect of the image.
The most immediate difference is in color and light: palettes now feel more luminous, with better depth and tonal harmony. Lighting is more responsive, delivering stronger atmosphere and sharper separation between elements. Shadows and highlights layer more naturally, giving compositions a greater sense of space and weight.
Faces have been redefined with subtle but crucial adjustments, proportions are cleaner, skin textures more nuanced, and expressions more lifelike without losing the stylized semi-realistic charm of the model's identity. Figures carry improved balance in body proportions, blending natural flow with controlled stylization.
Other highlights include:
Sharper detail handling, from fine fabrics and jewelry to hair strands and reflections.
Improved shading fidelity, enabling smoother gradients and more deliberate contrasts.
Richer compositions, with enhanced framing awareness and a greater sense of visual hierarchy.
Crisper depth cues, giving images a layered, cinematic quality that feels more immersive.
Where earlier versions smoothed and polished, Five Stars Illustrious 8.0 sharpens and enriches, offering creators imagery that feels more alive, more dimensional, and more commanding in presence.
ℹ️ v7.0: This version is a refinement-focused update that continues the Five Stars legacy while advancing its signature look with care and precision. This version introduces enhanced contouring fidelity and sharper regional segmentation, giving characters and scenes greater definition and depth across both soft and high-contrast settings.
While maintaining the expressive semi-realistic aesthetic of previous versions, this iteration strengthens the interaction between light and form, offering more deliberate shadow sculpting and luminosity variance. From low-light glow to reflective highlights, the model now handles a wider tonal spectrum with cleaner transitions and stronger contrasts, allowing for bolder image dynamics without becoming oversaturated.
Other subtle upgrades include:
Slightly revised default facial profiles with a fresh, clearer finish.
Improved framing awareness, especially in portrait-oriented compositions.
Expanded color shade variety, supporting both subdued palettes and vibrant stylization.
Continued emphasis on high fidelity, with crisp linework and defined silhouettes in detailed scenes.
Importantly, I try to preserve the iterative evolution of the model, with Five Stars Illustrious 7.0 attempting to retain the creative DNA of previous versions and is best thought of as a polished enhancement rather than a dramatic changes. I hope it offers more control, more precision, and just a touch more expressive freedom for creators using it.
ℹ️ v6.0: This version expands the foundation of previous releases with a quiet but deliberate shift in tone and versatility. It integrates fresh components and refinements that subtly rebalance the aesthetic - gently easing the dial back from a naturalism bias and giving more space for expressive, stylized interpretations.
This update includes nuanced adjustments across multiple aspects: smoother transitions between soft and sharp detail, better compositional flow, and more flexible handling of lighting conditions. Characters remain lively and grounded, but with a slightly more creative energy that adds charm without losing form.
Each version is an opportunity for me to explore ideas and polish further. With this release, I aimed to achieve a well-rounded update that feels both stable and creatively adaptive. It retains the spirit of Five Stars while opening the door a bit wider for playfulness, softness, and imagination.
ℹ️ v5.0: This version is another step in the model’s evolution. It integrates a wide range of new components and enhancements, with a focus on more volumetric visuals. Skin tones and surface textures have been improved for more natural, lifelike results, especially in semi-realistic and softly rendered styles. Default faces have been rebalanced. The model also features better handling of complex lighting and increased detail density across a wide range of scenes. This version aims to bring a more lifelike feel and atmospheric mood to the outputs.
ℹ️ v4.0: Fortunately, I’ve been able to train and design plenty of checkpoints recently, which allowed me to incorporate new effects and refinements into this version. I’ve focused on improving the model’s overall capabilities - enhancing prompt responsiveness, increasing style fidelity, and strengthening its handling of composition, depth, and color grading. I’ve also worked to push its ability to generate more cohesive and imaginative scenes, while still preserving the original feel and stylistic identity of previous versions. This model marks an important step forward for me.
ℹ️ v3.0: I might have gotten a little carried away with this one. I made a new training with many more styles. The model has a stronger digital art style now. Color saturation is increased, and the model can now choose to use darker colors and blacks, which it used to avoid in the past. It can create both intricate and smooth images. Overall, it's a really great complementary version of the model, which I like very much.
ℹ️ v2.0: Added a few new components, and new training with adjustment to more mature Western default face types, slightly stronger colors and a little bit more details, with more focus on subjects. I tried and hopefully succeeded to preserve the diversity of results and wide capabilities of the model for styles and concepts.