Instructions to use HopeTD/consulting with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use HopeTD/consulting with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ByteDance/Hyper-SD", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("HopeTD/consulting") prompt = "Hopedesigns" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Download pretrain.yaml from HopeTD/consulting: direct link, hf CLI and curl.
- Browser
- Download file 506 Bytes
-
https://huggingface.co/HopeTD/consulting/resolve/main/pretrain.yaml
- Command line
-
hf download hf://HopeTD/consulting/pretrain.yaml
-
curl -L -o pretrain.yaml https://huggingface.co/HopeTD/consulting/resolve/main/pretrain.yaml
506 Bytes
| train_file: ['/export/share/junnan-li/VL_pretrain/annotation/coco_karpathy_train.json', | |
| '/export/share/junnan-li/VL_pretrain/annotation/vg_caption.json', | |
| ] | |
| laion_path: '' | |
| # size of vit model; base or large | |
| vit: 'base' | |
| vit_grad_ckpt: False | |
| vit_ckpt_layer: 0 | |
| image_size: 224 | |
| batch_size: 75 | |
| queue_size: 57600 | |
| alpha: 0.4 | |
| # optimizer | |
| weight_decay: 0.05 | |
| init_lr: 3e-4 | |
| min_lr: 1e-6 | |
| warmup_lr: 1e-6 | |
| lr_decay_rate: 0.9 | |
| max_epoch: 20 | |
| warmup_steps: 3000 | |