Downloads · 30 days
34
8% of all-time downloads
strkyyy/claymation-3d
claymation-3d is a text-to-image model from strkyyy. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as openrail++.
Capture the charming and nostalgic aesthetic of stop-motion claymation with this LoRA. It brings to life handmade plasticine characters and sets, complete with visible fingerprints and slightly imperfect shapes. The w…
Downloads · 30 days
34
8% of all-time downloads
All-time downloads
421
Public
Repo size
105 MB
Likes
0
Public
Click a slice to open those files.
.safetensors93.1 MB · 89%
From the Hugging Face model README
Capture the charming and nostalgic aesthetic of stop-motion claymation with this LoRA. It brings to life handmade plasticine characters and sets, complete with visible fingerprints and slightly imperfect shapes. The warm soft lighting and tactile cozy charm create a unique visual style reminiscent of beloved animations like Wallace & Gromit.
Apply the trigger word 'cl4ym4tion' in your prompts for instant claymation vibes. Try a strength between 0.6 and 1.0, with around 0.85 being ideal. The DDIM sampler works well, but feel free to experiment with other samplers and step counts.
cl4ym4tion, warm lighting, cozy room with handmade claymation furniture
cl4ym4tion, portrait of a claymation character, side view, friendly expression
cl4ym4tion, action shot, toy car racing on a homemade track under soft lights
cl4ym4tion, abstract shapes, colorful and tactile plasticine textures in close-up
cl4ym4tion, evening mood, claymation street scene with quaint shops and warm glow
cl4ym4tion, detailed architecture, handmade claymation house with visible fingerprints
Activate with cl4ym4tion. Recommended strength: 0.9.

diffusersfrom diffusers import AutoPipelineForText2Image
import torch
pipe = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16).to("cuda")
pipe.load_lora_weights("strkyyy/claymation-3d")
image = pipe("cl4ym4tion, your prompt", num_inference_steps=30).images[0]