Quality tags: masterpiece, best quality, newest, absurdres, highres,

Negative Tags: (bad quality:1.15), (worst quality:1.3)

Please use both for best results.

Illustrious Black Magic is my attempt toward adding the Black Magic touch to Illustrious. Aiming for a cleaner look with thicker outlines, I believe this model delivers. I recommend the CLEAN version for best prompt adherence

USE EULER KARRAS - I use cfg 5.8 -------- Please read more below, just the first few lines!

There are two versions of Illustrious Black Magic. One has Pony (1.0 & 1.69) and one does not (CLEAN).

I recommend the CLEAN version for the best Illustrious/Noob experience. It understands Booru tags, natural language and e621 tags

---

Clean Merge Information

2.7:

Trained synthetic data from old gens for 3 days for 74,800 steps total - 100 Epochs.

2.0:

Afterward, I trained it on a small amount of hand-picked images that I think represent the Black Magic style well, and trained it for 100 epochs. It's not much but it does change the bottom line to complete.

1.0:

SpatterXL (IllustriousXL X PonyXL) - Spatter2DV2.5 (no pony) | Illustrious Checkpoint | Civitai

&

Illustrious-XL - v0.1 | Illustrious Checkpoint | Civitai

&

Illustrious 2D Anime Enhancer - V1 | Illustrious LoRA | Civitai at .55 strength

THEN I merged the result into NoobAI-XL (NAI-XL) - Epsilon-pred 1.1-Version | Stable Diffusion XL Checkpoint | Civitai using the formula above

And baked in a little more of the same lora at .25 strength.

---

PONY MERGE INFORMATION

it's a merge with mostly Solmeleon | [IllustriousXL] - v1.0 | Illustrious Checkpoint | Civitai

and BLACK MAGIC PONY - v2.5 | Stable Diffusion Checkpoint | Civitai

Combined with

SDXL FaeTastic Details - v24 | Stable Diffusion XL LoRA | Civitai

and Black Magic 2-D Anime Enhancer for Pony - v1.0 | Stable Diffusion LoRA | Civitai

V1.69

Mixed V1.0 with NoobAI-XL (NAI-XL) - V-Pred-0.6-Version | Stable Diffusion XL Checkpoint | Civitai - EPS Edition

With Noob being largely dominant with the exclusion of the middle weights and reduction on the outer weights.

Model License

This model's license inherits from https://huggingface.co/OnomaAIResearch/Illustrious-xl-early-release-v0 fair-ai-public-license-1.0-sd and adds the following terms. Any use of this model and its variants is bound by this license.

I. Usage Restrictions

• Prohibited use for harmful, malicious, or illegal activities, including but not limited to harassment, threats, and spreading misinformation.

• Prohibited generation of unethical or offensive content.

• Prohibited violation of laws and regulations in the user's jurisdiction.

II. Commercial Prohibition

We prohibit any form of commercialization, including but not limited to monetization or commercial use of the model, derivative models, or model-generated products.

III. Open Source Community

To foster a thriving open-source community,users MUST comply with the following requirements:

• Open source derivative models, merged models, LoRAs, and products based on the above models.

• Share work details such as synthesis formulas, prompts, and workflows.

• Follow the fair-ai-public-license to ensure derivative works remain open source.

IV. Disclaimer

Generated models may produce unexpected or harmful outputs. Users must assume all risks and potential consequences of usage.

Thank you to everyone testing this out, I really appreciate your feedback.

Terms and conditions considerations: If anyone seriously asks, I'd be happy to provide all the metadata or resources used to create this model.

描述:

Trained synthetic data from old gens for 3 days for 74,800 steps total - 100 Epochs.

训练词语: