Instructions to use LyliaEngine/PHM_style_IL_v3.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use LyliaEngine/PHM_style_IL_v3.3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("OnomaAIResearch/Illustrious-xl-early-release-v0", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("LyliaEngine/PHM_style_IL_v3.3") prompt = "(masterpiece, best quality:1.2), amazing quality, very aesthetic, 32k, absurdres, newest, scenery, " 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: | |
| - output: | |
| url: images/6ee717c4-16f8-4082-b971-8ef93ffcce3f.png | |
| text: >- | |
| (masterpiece, best quality:1.2), amazing quality, very aesthetic, 32k, | |
| absurdres, newest, scenery, | |
| parameters: | |
| negative_prompt: >- | |
| worst aesthetic, (worst quality, low quality, bad quality:1.4), lowres, | |
| worst detail, scan artifacts, jpeg artifacts, lossy-lossless, aliasing, | |
| downscaled, ai-generated, old, | |
| - output: | |
| url: images/93ca54e1-d23d-4589-a116-d85d4010a069.png | |
| text: >- | |
| (masterpiece, best quality:1.2), amazing quality, very aesthetic, 32k, | |
| absurdres, newest, scenery, | |
| parameters: | |
| negative_prompt: >- | |
| worst aesthetic, (worst quality, low quality, bad quality:1.4), lowres, | |
| worst detail, scan artifacts, jpeg artifacts, lossy-lossless, aliasing, | |
| downscaled, ai-generated, old, | |
| - output: | |
| url: images/305d376d-3a7d-4ce1-8efc-d0b798f4c6cc.png | |
| text: >- | |
| (masterpiece, best quality:1.2), amazing quality, very aesthetic, 32k, | |
| absurdres, newest, scenery, | |
| parameters: | |
| negative_prompt: >- | |
| worst aesthetic, (worst quality, low quality, bad quality:1.4), lowres, | |
| worst detail, scan artifacts, jpeg artifacts, lossy-lossless, aliasing, | |
| downscaled, ai-generated, old, | |
| base_model: OnomaAIResearch/Illustrious-xl-early-release-v0 | |
| instance_prompt: None | |
| license: cdla-permissive-2.0 | |
| # PHM_style_IL_v3.3 | |
| <Gallery /> | |
| ## Model description | |
| A set of styles I trained for my own use, now shared for others to use. | |
| These styles are also available on tensor.art | |
| Feel free to use them and share your works. | |
| 👑PHM v3 - This is the most popular and I think the most powerful style. When collecting the dataset, I tried to balance with different things while preserving a beautiful visual look. Good for SFW, with v3 extended to perform better in NSFW. | |
| PHM v2 | |
| ALYX - Mature female style with a unique look. Mostly NSFW. | |
| TRT - Girls with huge breasts. Mostly NSFW. | |
| MSS v2 | |
| MSS - Female characters with a CG look and anime aesthetics. Mostly NSFW. | |
| MNK - Mature female style with a unique look. Mostly NSFW. | |
| LMB v2 | |
| LMB - Mature female style with a unique look. Best for NSFW. | |
| UKI - Anime style female characters. Mostly NSFW. | |
| Deprecated | |
| PHM (depracated, don't use) | |
| ALX (depracated, don't use) | |
| MOS (depracated, don't use) | |
| ## Trigger words | |
| You should use `None` to trigger the image generation. | |
| ## Source | |
| https://civitai.red/models/1060551/illustrious-style-pack?modelVersionId=1570070 | |
| ## Credit | |
| https://civitai.red/user/Icecrown1 | |
| ## Download model | |
| [Download](/LyliaEngine/PHM_style_IL_v3.3/tree/main) them in the Files & versions tab. | |