pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("kpsss34/FHDR_Uncensored", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]I trained this model using the Diffusers library by randomly selecting layers and blocks (not training every layer), which reduced the training time and is expected to yield better results.
import torch
from diffusers import FluxPipeline
pipe = FluxPipeline.from_pretrained("kpsss34/FHDR_Uncensored", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()
prompt = "a women..."
image = pipe(
prompt,
height=1024,
width=1024,
guidance_scale=4.0,
num_inference_steps=40,
max_sequence_length=512,
generator=torch.Generator("cpu").manual_seed(0)
).images[0]
image.save("outputs.png")
- Downloads last month
- 21,740
Hardware compatibility
Log In to add your hardware
4-bit
8-bit
# Gated model: Login with a HF token with gated access permission hf auth login