Text-to-Image
Diffusers
Safetensors
English
fd-loss
jit
imf
pmf
image-generation
class-conditional
imagenet
Instructions to use BiliSakura/FD-Loss-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use BiliSakura/FD-Loss-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("BiliSakura/FD-Loss-diffusers", 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
|
Download pMF-B-32-SIM/README.md from BiliSakura/FD-Loss-diffusers: direct link, hf CLI and curl.
- Browser
- Download file 894 Bytes
-
https://huggingface.co/BiliSakura/FD-Loss-diffusers/resolve/main/pMF-B-32-SIM/README.md
- Command line
-
hf download hf://BiliSakura/FD-Loss-diffusers/pMF-B-32-SIM/README.md
-
curl -L -o README.md https://huggingface.co/BiliSakura/FD-Loss-diffusers/resolve/main/pMF-B-32-SIM/README.md
894 Bytes
metadata
license: mit
library_name: diffusers
pipeline_tag: text-to-image
tags:
- diffusers
- pmf
- image-generation
- class-conditional
- imagenet
inference: true
pMF-B-32-SIM
Self-contained Diffusers variant for pMF-B/32 (FD-SIM post-trained) (Pixel Mean Flows).
Recommended settings: guidance_scale=6.5, interval [0.1, 0.7], noise_scale=2.0.
Load
from pathlib import Path
from diffusers import DiffusionPipeline
import torch
model_dir = Path("./pMF-B-32-SIM")
pipe = DiffusionPipeline.from_pretrained(
str(model_dir),
local_files_only=True,
custom_pipeline=str(model_dir / "pipeline.py"),
trust_remote_code=True,
torch_dtype=torch.bfloat16,
).to("cuda")
image = pipe(
class_labels=207,
num_inference_steps=1,
guidance_scale=6.5,
guidance_interval_min=0.1,
guidance_interval_max=0.7,
noise_scale=2.0,
).images[0]