Hey, all, I'm back with another LoRA, and it's based on the stop-motion claymation style of Aardman Animations! I really enjoy their exaggerated cartoonish style of clay models from their works such as Chicken Run, Shaun The Sheep (one of my childhood favorites), Wallace & Gromit, and so much more! Trained this on over 77 images from their shows and movies.

Recommended settings:

LoRA weight: ~0.6-0.9 (I would highly recommend to put ~0.6-0.8 for the most accurate results if you're doing hires. fix)

If you're doing hires. fix, I suggest the denoising range of ~0.55-0.7

CFG scale: 5-7

Checkpoints: I recommend Deliberate since it's the one that I tested out the most, and provided accurate results (but you can experiment with others as well)

Samplers: Euler a, DPM++ 2M Karras, or DPM++ SDE Karras

Make sure you add "aardman style" to enable the effect on your prompt!

Negative prompt that works well:

paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), dot, mole, lowers, normal quality, monochrome, grayscale, lowers, text, error, cropped, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, out of frame, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, username, watermark, signature, less than five fingers, EasyNegative, ng_deepnegative_v1_75t

Suggestions and feedback are always welcome!

I hope you enjoy my LoRA!