Instructions to use lenML/Deep-Negative-Pony with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lenML/Deep-Negative-Pony 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("lenML/Deep-Negative-Pony") prompt = "green dragon, flying, sky, yellow eyes, teeth, wings up, tail, horns, solo, couds, score_9, score_8_up, score_7_up" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
| tags: | |
| - text-to-image | |
| - lora | |
| - diffusers | |
| - template:diffusion-lora | |
| widget: | |
| - text: >- | |
| green dragon, flying, sky, yellow eyes, teeth, wings up, tail, horns, solo, | |
| couds, score_9, score_8_up, score_7_up | |
| parameters: | |
| negative_prompt: ' deep_negative_pony' | |
| output: | |
| url: >- | |
| images/xyz_grid-1438-620372787-green dragon, flying, sky, yellow eyes, | |
| teeth, wings up, tail, horns, solo, couds, score_9, score_8_up, | |
| score_7_up__ _lora_Conce.png | |
| - text: >- | |
| score_9, score_8_up, score_7_up, score_6_up, GLSHS, 1girl, long hair, bug, | |
| butterfly, choker, wavy hair, butterfly on face, facing viewer, covered | |
| eyes, upper body, dark theme, blonde hair | |
| parameters: | |
| negative_prompt: ' deep_negative_pony' | |
| output: | |
| url: >- | |
| images/xyz_grid-1443-1043133765-score_9, score_8_up, score_7_up, | |
| score_6_up, GLSHS, 1girl, long hair, bug, butterfly, choker, wavy hair, | |
| butterfly on face, faci.png | |
| base_model: LyliaEngine/Pony_Diffusion_V6_XL | |
| instance_prompt: null | |
| license: unknown | |
| # Deep Negative Pony | |
| <Gallery /> | |
| ## Model description | |
| What does it do? | |
| DeepNegative is a negative embedding. it contain unsightly compositions and color patterns, such as inaccurate human anatomy, distasteful color combinations, disoriented spatial structures, and more. By put it in negative prompt, we can significantly reduce the occurrence of these elements. | |
| Suggestion | |
| Because this embedding is learning how to create disgusting concepts, it cannot improve the picture quality accurately, so it is best used with (worst quality, low quality, logo, text, watermark, username:1) these negative prompts. | |
| Of course, it is completely fine to use with other similar negative embeddings. | |
| ## Download model | |
| Weights for this model are available in Safetensors format. | |
| [Download](/lenML/Deep-Negative-Pony/tree/main) them in the Files & versions tab. | |