Text-to-Image
Diffusers
Safetensors
StableDiffusionXLPipeline
stable-diffusion-xl
stable-diffusion
lora
merged
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("BraceZHY/sdxl-DPO100K")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Merged SDXL Model
This model is a merged version of stabilityai/stable-diffusion-xl-base-1.0 with trained LoRA weights.
Model Details
- Base Model: stabilityai/stable-diffusion-xl-base-1.0
- LoRA Weights: Merged from ./sdxl-DPO100K
- Model Type: Stable Diffusion XL
- Format: Diffusers
Usage
from diffusers import StableDiffusionXLPipeline
import torch
pipeline = StableDiffusionXLPipeline.from_pretrained(
"BraceZHY/sdxl-DPO100K",
torch_dtype=torch.float16,
use_safetensors=True
)
pipeline = pipeline.to("cuda")
prompt = "Your prompt here"
image = pipeline(prompt).images[0]
image.save("output.png")
Training Details
This model was created by training LoRA weights and then merging them with the base model for easier deployment and faster inference.
- Downloads last month
- 6
Model tree for BraceZHY/sdxl-DPO100K
Base model
stabilityai/stable-diffusion-xl-base-1.0