Downloads · 30 days
2.3K
1% of all-time downloads
dreamshaper-xl-turbo
Lykon/dreamshaper-xl-turbo
dreamshaper-xl-turbo is a text-to-image model from Lykon. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as openrail++.
lykon/dreamshaper-xl-turbo is a Stable Diffusion model that has been fine-tuned on stabilityai/stable-diffusion-xl-base-1.0.
All-time downloads
431K
Public
Parameters
2.6B
34.7 GB on disk
Likes
46
Public
Repo makeup
Click a slice to open those files.
.safetensors34.7 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- openrail++
- Access
- Public
- Created
- Dec 5, 2023
- Updated
- Jan 17, 2024
- SHA
- 402d2e02
Model card
From the Hugging Face model README
Dreamshaper SDXL-Turbo
lykon/dreamshaper-xl-turbo is a Stable Diffusion model that has been fine-tuned on stabilityai/stable-diffusion-xl-base-1.0.
Please consider supporting me:
- on Patreon
- or buy me a coffee
Diffusers
For more general information on how to run text-to-image models with 🧨 Diffusers, see the docs.
- Installation
pip install diffusers transformers accelerate
- Run
from diffusers import AutoPipelineForText2Image, DPMSolverMultistepScheduler
import torch
pipe = AutoPipelineForText2Image.from_pretrained('lykon/dreamshaper-xl-turbo', torch_dtype=torch.float16, variant="fp16")
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
pipe = pipe.to("cuda")
prompt = "portrait photo of muscular bearded guy in a worn mech suit, light bokeh, intricate, steel metal, elegant, sharp focus, soft lighting, vibrant colors"
generator = torch.manual_seed(0)
image = pipe(prompt, num_inference_steps=6, guidance_scale=2).images[0]
image.save("./image.png")
- Task
- Text-to-Image
- Library
- diffusers
- License
- openrail++
- Languages
- en
- Created
- Dec 5, 2023
- Updated
- Jan 17, 2024