Instructions to use SidXXD/HAAD-kv with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SidXXD/HAAD-kv with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SidXXD/HAAD-kv", dtype=torch.bfloat16, device_map="cuda") prompt = "photo of a sks person" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Download All_layer_embeds_SD_v1_5/Embeds_layer_6_MidBlock.pt from SidXXD/HAAD-kv: direct link, hf CLI and curl.
- Browser
- Download file 329 kB
-
https://huggingface.co/SidXXD/HAAD-kv/resolve/main/All_layer_embeds_SD_v1_5/Embeds_layer_6_MidBlock.pt
- Command line
-
hf download hf://SidXXD/HAAD-kv/All_layer_embeds_SD_v1_5/Embeds_layer_6_MidBlock.pt
-
curl -L -o Embeds_layer_6_MidBlock.pt https://huggingface.co/SidXXD/HAAD-kv/resolve/main/All_layer_embeds_SD_v1_5/Embeds_layer_6_MidBlock.pt
329 kB
- Xet hash:
- 26882d9059c2a2e710b6fa8e8372ce35eb4b20e62d3a31971585eb45ee1fb3b8
- Size of remote file:
- 329 kB
- SHA256:
- c5df1ff8ce53f494e7faadde26d0278c4b7c502ca93200596cd22bb18d7c7854
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.