Instructions to use Haruka041/decon with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Haruka041/decon with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Anima", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Haruka041/decon") 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
Commit History
Today
-
remove duplicate/baked .safetensors (single-file policy)
Verified signature42da94d -
reconvert: keep alpha tensors + all non-block modules (bf16)
Verified signaturebb57093 -
Upload rebaked LoRA with alpha/rank baked into W_down
Verified signature5ee5c0f
Yesterday
-
Upload README.md with huggingface_hub
Verified signature4310a0b -
Upload decon.safetensors with huggingface_hub
Verified signature88364af -
initial commit
Verified signature68ab618