Instructions to use whosouravsharma/diffusiondb-sd15-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use whosouravsharma/diffusiondb-sd15-lora with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("whosouravsharma/diffusiondb-sd15-lora") prompt = "a anthropomorphic lion wizard, diffuse lighting, fantasy, intricate, elegant, highly detailed, lifelike, photorealistic, digital painting, artstation, illustration, concept art, smooth, sharp focus, naturalism, trending on byron's - muse, by greg rutkowski and greg staples" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Download checkpoints/checkpoint-2000/state.json from whosouravsharma/diffusiondb-sd15-lora: direct link, hf CLI and curl.
- Browser
- Download file 335 Bytes
-
https://huggingface.co/whosouravsharma/diffusiondb-sd15-lora/resolve/main/checkpoints/checkpoint-2000/state.json
- Command line
-
hf download hf://whosouravsharma/diffusiondb-sd15-lora/checkpoints/checkpoint-2000/state.json
-
curl -L -o state.json https://huggingface.co/whosouravsharma/diffusiondb-sd15-lora/resolve/main/checkpoints/checkpoint-2000/state.json
335 Bytes
| { | |
| "step": 2000, | |
| "epoch": 4, | |
| "base_model": "runwayml/stable-diffusion-v1-5", | |
| "lora_rank": 32, | |
| "lora_alpha": 32, | |
| "resolution": 512, | |
| "scaling_factor": 0.18215, | |
| "learning_rate": 0.0001, | |
| "batch_size": 8, | |
| "grad_accum": 4, | |
| "caption_dropout": 0.1, | |
| "latents": "whosouravsharma/text-to-image-diffusiondb-2M@latents-512" | |
| } |