Instructions to use digiplay/UNSTABLE_v1_by_dice with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use digiplay/UNSTABLE_v1_by_dice with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("digiplay/UNSTABLE_v1_by_dice", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Sample images
dice_unstable_v1_840000VAE.safetensors
(best quality, masterpiece:1.1), <lora:Better light:0.5>, close up, (1female), irritating face, golden hair, medium hair, messy hair, winter clothes, earmuffs, gloves, white scarf, ( (magazine, magazine cover background, simple background:1.1)),
Negative prompt: (low quality, worst quality:1.4), verybadimagenegative_v1.3, (negative_hand-neg:1.1), (extra fingers, fewer fingers, cutting leg, cutting arm:0.6), signiture, umbrella, (tattoo, clothing cutout, side slit, navel, stomach, underboob, latex, bodysuit, underwear, off shoulder, bare shoulder, nsfw, lewd:0.75)
Steps: 25, Sampler: DPM++ 2M Karras, CFG scale: 9, Seed: 1257330180, Size: 512x768, Model hash: 02996803f6, Clip skip: 2, Version: 1.6.1
Networks not found: Better light
Time taken: 11 min. 45.1 sec.
