Instructions to use alvdansen/soft-and-squishy-linework with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use alvdansen/soft-and-squishy-linework with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("alvdansen/soft-and-squishy-linework") prompt = "a little faun boy with horns and curly hair, spots on his face, wearing an oversized t shirt" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Soft & Squishy Linework

- Prompt
- a little faun boy with horns and curly hair, spots on his face, wearing an oversized t shirt

- Prompt
- a toad

- Prompt
- a girl with blonde-brown hair and big round glasses, blue eyes, white t shirt, shorts, ram horns, tiefling

- Prompt
- a girl with blonde-brown hair and big round glasses, blue eyes, white t shirt, shorts

- Prompt
- a young girl with a gentle and thoughtful expression sitting on the floor surrounded by pills, soft blue eyes, big round glasses, pink hair, messy apartment, hollowness, glitch art
Model description
A really fun model to prompt with no trigger, intended for anime style soft and sort of lofi linework.
I like running it at 0.9 but it works at other weights as well. Better with Euler A in my opinion.
Sometimes I will use 'messy' and 'bad linework' for a small neg. prompt.
Download model
Weights for this model are available in Safetensors format.
Model release is for research purposes only. For commercial use, please contact me directly.
Download them in the Files & versions tab.
- Downloads last month
- 6
Model tree for alvdansen/soft-and-squishy-linework
Base model
stabilityai/stable-diffusion-xl-base-1.0