Instructions to use sanctia/lora-sd-finesse with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use sanctia/lora-sd-finesse with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("sanctia/lora-sd-finesse") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
LoRA text2image fine-tuning - sanctia/lora-sd-finesse
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were fine-tuned on the sanctia/finesse-image-generation dataset. You can find some example images in the following.
- Model and architecture details: https://www.notion.so/Design-document-Finesse-Generative-Challenge-4ed87ea624f84ff5a9ac09dc21885366
- Wandb report: https://wandb.ai/hpml3/text2image-fine-tune/runs/cdyy9un3?workspace=user-sanctia
- Downloads last month
- 3
Model tree for sanctia/lora-sd-finesse
Base model
runwayml/stable-diffusion-v1-5


