Instructions to use LyliaEngine/lowlight with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use LyliaEngine/lowlight with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("LyliaEngine/Pony_Diffusion_V6_XL", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("LyliaEngine/lowlight") prompt = "score_9, source_anime, glowing eyes, 1girl, solo, red eyes, slit pupils, expressionless, looking away, red hoodie, long sleeves, shorts, blonde hair, short hair, outdoors, urban, concrete, from side, sitting, upper body, <lora:SawatariAkanePDXL:1> <lora:lowlight_1721964122_1721964450_dim32_sv_fro_dp0.92_1721964790_1722820361:2>" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
| tags: | |
| - text-to-image | |
| - stable-diffusion | |
| - lora | |
| - diffusers | |
| - template:sd-lora | |
| widget: | |
| - text: >- | |
| score_9, source_anime, glowing eyes, 1girl, solo, red eyes, slit pupils, | |
| expressionless, looking away, red hoodie, long sleeves, shorts, blonde hair, | |
| short hair, outdoors, urban, concrete, from side, sitting, upper body, | |
| <lora:SawatariAkanePDXL:1> | |
| <lora:lowlight_1721964122_1721964450_dim32_sv_fro_dp0.92_1721964790_1722820361:2> | |
| parameters: | |
| negative_prompt: >- | |
| blurry, cropped, messy, score_4, score_5, score_6, censored, mosaic | |
| censor, source_pony, source_cartoon, source_furry, 3d, realistic, | |
| hyperrealistic, photo, | |
| output: | |
| url: images/00063-2214885482.png | |
| - text: >- | |
| score_9, source_anime, glowing eyes, cheek swirl, sitting,, grass, pleated | |
| skirt, forest, trees, dawn \(pokemon\), blue eyes, blue hair, scarf, beanie, | |
| hat, skirt, sleeveless black shirt, upper body, half-closed eyes, looking at | |
| viewer, parted lips, expressionless, | |
| <lora:lowlight_1721964122_1721964450_dim32_sv_fro_dp0.92_1721964790_1722820361:2:lbw=XYZ> | |
| <lora:zeon_data | |
| ponyDiffusionV6XL_v6StartWithThisOne__1722314605_1722322530:1> | |
| parameters: | |
| negative_prompt: >- | |
| monochrome, greyscale, blurry, cropped, messy, score_4, score_5, score_6, | |
| censored, mosaic censor, source_pony, source_cartoon, source_furry, 3d, | |
| realistic, hyperrealistic, photo, | |
| output: | |
| url: images/00018-2254569595.png | |
| base_model: LyliaEngine/Pony_Diffusion_V6_XL | |
| instance_prompt: None | |
| license: cdla-permissive-2.0 | |
| # lowlight | |
| <Gallery /> | |
| ## Model description | |
| A modification of an existing LoRA by @Camel10 thanks for your work! | |
| With the goal of being lighter touch and trim out ineffective parts of the network to really emphasise the effect. As a derived LoRA, this would have similar effects and limitations. | |
| Future work will include different hues instead of just dark blue. | |
|  | |
| ## Source | |
| https://civitai.com/models/623662/low-light-for-pony-variant?modelVersionId=697211 | |
| ## Credit | |
| https://civitai.com/user/rred | |
| ## Trigger words | |
| You should use `None` to trigger the image generation. | |
| ## Download model | |
| Weights for this model are available in Safetensors format. | |
| [Download](/LyliaEngine/lowlight/tree/main) them in the Files & versions tab. | |