Instructions to use khora-vie/khora-retarget-weights with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use khora-vie/khora-retarget-weights with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("khora-vie/khora-retarget-weights", 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
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
khora-retarget-weights (private)
Model cache for khora/khora-retargeting: everything its DiffuEraser
path (masks, scene depth, arm removal) loads, plus the golden-test inputs. The IK needs none of it.
Fetch and verify with ./download_models.sh in that repo (needs read access to this repo and hf auth login).
| Path | Source |
|---|---|
diffueraser/diffuEraser/ |
lixiaowen/diffuEraser |
diffueraser/stable-diffusion-v1-5/ |
stable-diffusion-v1-5/stable-diffusion-v1-5, only the files DiffuEraser loads (fp32 safetensors of the text encoder and safety checker, configs, tokenizer) |
diffueraser/sd-vae-ft-mse/ |
stabilityai/sd-vae-ft-mse |
diffueraser/PCM_Weights/sd15/ |
wangfuyun/PCM_Weights, the 2-step checkpoint run_diffueraser.py uses |
diffueraser/propainter/ |
sczhou/ProPainter releases (ProPainter, RAFT, flow completion) |
hf/grounding-dino-tiny/ |
IDEA-Research/grounding-dino-tiny @ a2bb814 |
hf/sam2.1-hiera-large/ |
facebook/sam2.1-hiera-large @ 665f8e2 |
hf/Depth-Anything-V2-Metric-Indoor-Large-hf/ |
depth-anything/Depth-Anything-V2-Metric-Indoor-Large-hf @ d2fc6a9 |
golden/ |
golden-test inputs: EgoDex ground-truth hands (arrange_topple_dominoes, 300 frames) and one EgoVerse v06 clip |
SHA256SUMS |
checksums of all of the above |
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support