LoRa Commission (Stable Diffusion) Supports Illustrious, PonyXL, Animagine, etc

1 rating

Looking to enhance your AI-generated content with a custom-trained LoRa? I offer personalized LoRa training services focused on anime and illustration styles, delivering high-quality models tailored to your needs.

🎨 What I Offer:

🧍 Character LoRas
- I can train a LoRa inspired by the appearance or design of a specific character from anime or illustrations.
- If you'd like me to focus on a particular outfit, expression, or design element of the character, please provide detailed instructions.
🎨 Style LoRas
- Want a specific artistic style recreated? I can train LoRAs to capture the general look and feel you’re aiming for.
🌀 Concept LoRas
- LoRas trained for broader creative themes or conceptual aesthetics.

🧾 Requirements:

Specify the checkpoint you usually use.
You don’t need to send me any images or materials (unless it’s for manga, comics, or your original character).

💳 How to proceed with the request after payment?

After purchase, you’ll receive a confirmation email from Gumroad. Please reply with the details of your request, including: what you want trained, your preferred checkpoint and any other preferences. I’ll reply as soon as possible to confirm and guide you through the next steps.
Got any questions before buying? Just send me an email at contatoyumidreams@gmail.com

🎨 I offer two types of commissions:

✨ Standard LoRa Commissions

For characters, styles, and concepts.
👉 Just send your request and specify the checkpoint you usually use via email after purchase.
If the source reference is not from manga or comics, choose this option

📚 Manga & Comic LoRas

These commissions require extra work because manga and comic pages tend to contain a lot of visual noise. I need to carefully curate the dataset, which includes removing speech bubbles and other unwanted elements to capture the pure art style you are aiming for. This makes the process more time-consuming, but it ensures cleaner and more accurate results.
To proceed, you can either:
- Send me the pages directly (preferably in high resolution), or
- Send me a link where I can view them.
This way I’ll be able to build a clean, high-quality dataset and deliver the best results possible.

🚫 Limitations:

Supported Models: I only train LoRas for Stable Diffusion.
Unsupported Models: I do not train LoRas for models like Flux, Wan Video or any others that are not Stable Diffusion based.
No Video LoRas.
No Real-Life Individuals or realistic styles.
Tattoos and Symbols: It’s very difficult to reproduce symbols and especially tattoos with 100% accuracy in Stable Diffusion.
If the symbol has a very clear shape and isn’t too small, it might work. If you’re unsure, feel free to send it to me and I can check it for you beforehand.

⚙️ Training Method:

All LoRas are trained locally using the Kohya.ss framework, a reliable and well-known tool for high-quality model training in Stable Diffusion. This ensures the best possible results tailored to your specifications.

📤 Important Notices

1. Publication or Private Delivery
By default, I will send the file privately (through Google Drive). I will only publish it on my Civitai profile if you specifically request that. If published, other users will be able to use and review it.

2. Delivery Format
The LoRa will be delivered in .safetensors format, compatible with Stable Diffusion.

3. Required Tools
Before placing an order, please make sure you have the necessary tools to use the delivered material.

🧠 What is a LoRa?
A LoRa (Low-Rank Adaptation) is a specialized model designed to modify or enhance a base model in Stable Diffusion, enabling the generation of images with specific characteristics, such as styles or characters.
You will need a functional setup of Stable Diffusion and a checkpoint (e.g., IllustriousXL, PonyXL, Animangine, etc.) to use the LoRa. If you're generating inferences on Civitai, feel free to disregard this warning.

4. ⏱️Delivery Timeline
The maximum delivery time is five days after all client specifications are confirmed. However, in most cases, delivery is faster — sometimes even within a single day.

5. 🧾Short License Summary

By purchasing this commission, you acknowledge that:

You may use the LoRA and its outputs for personal or commercial purposes, including generating, selling, or redistributing the LoRA file(s).
Redistribution of the LoRA file(s) is permitted as long as it does not violate the underlying Stable Diffusion license or any applicable copyright laws.
The rights you receive apply only to the LoRA model file(s) as an AI tool.
No ownership of characters, styles, artworks, or any underlying intellectual property is transferred.
A full license PDF will be included with your delivery, containing detailed terms and conditions.
By completing the purchase, you agree to follow the terms outlined in the license.

6. 🧾Stable Diffusion License
The LoRAs created here are derivatives of Stable Diffusion XL 1.0, which is released under the CreativeML Open RAIL++-M License.

You may use the delivered LoRa and its outputs for personal or commercial purposes.
However, redistribution or usage must always respect the license restrictions.
Prohibited uses include (but are not limited to): exploitation of minors, harassment, defamation, discrimination, unlawful activities, medical advice, or surveillance/profiling for law enforcement or immigration.
By purchasing, you agree to comply with these terms.

Full license text: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0

Let me know if you'd like to tweak or expand any section further! 😊

📧 contatoyumidreams@gmail.com

🔗_yumidreams Civitai

🔗_yumidreams Linktree