Instructions to use kimi000/Flux1-Dev-4Step-V2-2000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kimi000/Flux1-Dev-4Step-V2-2000 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("kimi000/Flux1-Dev-4Step-V2-2000", 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
File size: 301 Bytes
e0d8ac7 | 1 2 3 4 5 6 7 8 9 | import torch
from diffusers import AutoencoderKL
class Flux1Autoencoder(AutoencoderKL):
@classmethod
def from_pretrained(cls, pretrained_model_name_or_path, **kwargs):
kwargs['torch_dtype']=torch.float32
return super().from_pretrained(pretrained_model_name_or_path, **kwargs)
|