EnthusiastAI/DiamondCoalMix

I have created my first Checkpoint model that is suitable for mostly realistic styles, but I added some of my own trained cartoon style models for extra flares. I focused on refining the hand and feet issues as much as possible. Based on the images I have generated so far, it seems to be fine most of the time. I avoid using the word "dynamic" as it can cause the hand to go wild. For the example images, I used the same prompts, and all the displayed images are completely raw without any additional support from Loras or Embeddings. However, using negative embeddings like "bad artist" or "bad han

<iframe src="https://silytics.si/embed/item/e62d7b46-c270-4386-9055-ef875ce6efbe" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 16 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.