Instructions to use bdsqlsz/HunYuanDiT-V1.2-fp16-pruned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use bdsqlsz/HunYuanDiT-V1.2-fp16-pruned with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("bdsqlsz/HunYuanDiT-V1.2-fp16-pruned", 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
Original Model: https://huggingface.co/Tencent-Hunyuan/HunyuanDiT-v1.2
The directory structure is for this PR in kohya-ss/sd-scripts:
https://github.com/kohya-ss/sd-scripts/pull/1378
How to use this
- Download them into a folder and use the script in the PR above.
- Download them and then rename the folder for other usage
- Reference of folder name:
- denoiser -> model
- clip -> clip_text_encoder
- mt5 -> mt5
- vae -> sdxl-vae-fp16-fix
- tokenizer have been placed into clip folder as well
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support