DiamondCoalMix版本DiamondCoalV2Pruned (ID: 55241)

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 hands" can greatly improve the result.

If you have any suggestions for improving my model, please leave them in the comments below. Thank you.

Prompts:

Pos: (European), beach, sea, (hand well), (finger well), (long braided hair), (bangs), with in frame, ultra-detailed, 8k, masterpiece, beautiful detailed face, (volumetric lighting), (beautiful detailed eyes), (ambient light), realistic shadows, (fullbody:1), (1girl), (cowboy shot), pattern shirts, pants, looking at viewer, perfect body, body well:1, leg well:1, arm well:1, dynamic pose

Neg: ((hands poor)), (fingers poor:1), (badquality), (bad anatomy), (nsfw), (legs poor), (inaccurate limb:1.2), (2girls), bad composition, inaccurate eyes, (extra hands:1.2), (inaccurate limb:1.2), (extra arms:1.2), (bad quality), bad face, (bad eyes), deformed, ((deformed fingers:1.2)), ((extra fingers, extra limbs)), bad hands, bad fingers, Asian

Pos: beach, sea, (hand well), (finger well), (long braided hair), (bangs), with in frame, ultra-detailed, 8k, masterpiece, beautiful detailed face, (volumetric lighting), (beautiful detailed eyes), (ambient light), realistic shadows, (fullbody:1), (1girl), (close up shot), pattern shirts, pants, looking at viewer, perfect body, body well:1, leg well:1, arm well:1

Neg: ((hands poor)), (fingers poor:1), (badquality), (bad anatomy), (nsfw), (legs poor), (inaccurate limb:1.2), (2girls), bad composition, inaccurate eyes, (extra hands:1.2), (inaccurate limb:1.2), (extra arms:1.2), (bad quality), bad face, (bad eyes), deformed, ((deformed fingers:1.2)), ((extra fingers, extra limbs)), bad hands, bad fingers

Pos: ((cartoon)), anime style, beach, sea, (hand well), (finger well), with in frame, ultra-detailed, 8k, masterpiece, beautiful detailed face, (volumetric lighting), (beautiful detailed eyes), (ambient light), realistic shadows, (fullbody:1), (1girl), (close up shot), pattern shirts, pants, looking at viewer, perfect body, body well:1, leg well:1, arm well:1, hand pose

Neg: ((hands poor)), (fingers poor:1), (badquality), (bad anatomy), (nsfw), (legs poor), (inaccurate limb:1.2), (2girls), bad composition, inaccurate eyes, (extra hands:1.2), (inaccurate limb:1.2), (extra arms:1.2), (bad quality), bad face, (bad eyes), deformed, ((deformed fingers:1.2)), ((extra fingers, extra limbs)), bad hands, bad fingers

描述:

This is a pruned version of the V2 model.
The original model may be too large for some people so I have decided to make a pruned version.
Base on some light testing, it seems almost no different from the full model one.
If you find any differences or issues please let me know :)

训练词语: