Instructions to use aithingies/Oil_Painting_Scenery with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use aithingies/Oil_Painting_Scenery with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("aithingies/Oil_Painting_Scenery") prompt = "<lora:(SDXL)OilPaintingStyle_Scenery-000004:0.65>oilpnt,autumn,forest,leaves,lake,1boat,wooden boat,cliff,sunset,masterpiece,nature,best quality,beautiful,cute scenery,dreamy" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
[SDXL] Oil Painting Scenery

- Prompt
- <lora:(SDXL)OilPaintingStyle_Scenery-000004:0.65>oilpnt,autumn,forest,leaves,lake,1boat,wooden boat,cliff,sunset,masterpiece,nature,best quality,beautiful,cute scenery,dreamy
- Negative Prompt
- bad quality,worst quality,ugly,deformed,bad anatomy,blurred,characters,humans,bad proportions

- Prompt
- <lora:(SDXL)OilPaintingStyle_Scenery-000004:0.6>oilpnt,beautiful scenery,mountain,rocky cliff,1 building,lighthouse,sunset,sea,waves
- Negative Prompt
- bad quality,worst quality,ugly,deformed,bad anatomy,blurred

- Prompt
- <lora:(SDXL)OilPaintingStyle_Scenery-000004:0.7>oilpnt,beautiful scenery,1 waterfall,forest,trees,stream,water
- Negative Prompt
- bad quality,worst quality,ugly,deformed,bad anatomy,blurred

- Prompt
- <lora:(SDXL)OilPaintingStyle_Scenery-000004:0.65>oilpnt,pitch-black night,1 castle,1 building,medium mountains, snowy peaks, dim moonlight, heavy shadows
- Negative Prompt
- bad quality,worst quality,ugly,deformed,bad anatomy,blurred,characters,humans,water,lake,river,bad proportions

- Prompt
- <lora:(SDXL)OilPaintingStyle_Scenery-000004:0.5>oilpnt,oil painting,scenery,clouds,trees,field,rural,beautiful,best quality,highly detailed,masterpeice
- Negative Prompt
- bad quality,worst quality,ugly,deformed,bad anatomy,blurred,characters,humans

- Prompt
- UNICODE<lora:(SDXL)OilPaintingStyle_Scenery-000004:0.5>oilpnt,autumn,forest,trees,lake,1building,masterpeice,best quality,beautiful,cute scenery,dreamy
Model description
Recommended weight: 0.5 - 0.7 Recommended CFG scale: 4.5 - 8 Trigger word: oilpnt
This scenery LoRA in the oil painting style was trained on ~110 scenery images (about 40 of them were synthetic). It's my first trained LoRA, so any feedback, comments, or suggestions are very welcome :D
Tagged by WD ViT Tagger v3 Trained on Kohya_ss
Please note that you'll have to do some mental gymnastics in order to generate a good image that includes both night and fog
Trigger words
You should use oilpnt to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 30
Model tree for aithingies/Oil_Painting_Scenery
Base model
stabilityai/stable-diffusion-xl-base-1.0