Text-to-Image
Diffusers
Safetensors
English
StableDiffusionXLPipeline
stable-diffusion
stable-diffusion-diffusers
stable-diffusion-xl
stable-diffusion-xl-lightning
art
artistic
anime
dreamshaper
turbo
lcm
Instructions to use Lykon/dreamshaper-xl-lightning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Lykon/dreamshaper-xl-lightning with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Lykon/dreamshaper-xl-lightning", torch_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
Image generation comparison report
#9
by tedmasterwebgmail - opened
I'm working on a personal project that requires the creation of hundreds of "selfies" (headshots, actually). I compared 20 models and produced samples for each using the same prompt. I'm posting this here in case it can save anyone time when doing similar research. You can see the report here: https://www.chicagoitsystems.com/ai-model-samples/
I would love your feedback!
Ted Stresen-Reuter
FWIW, this model was a good choice but took too long to produce images
Indeed, i was using 20 passes for all models. I'll try again with 8 and see if that improves things. Thanks for the feedback!
