Instructions to use scrapware/highPixelar with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use scrapware/highPixelar with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Lykon/AnyLoRA", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("scrapware/highPixelar") prompt = " masterpiece, best quality, 1girl, solo, pixelar" 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: ' masterpiece, best quality, 1girl, solo, pixelar' | |
| parameters: | |
| negative_prompt: >- | |
| lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, | |
| fewer digits, cropped, worst quality, low quality, normal quality, jpeg | |
| artifacts, signature, watermark, username, blurry | |
| output: | |
| url: images/highPixelar_v1AF.preview.png | |
| - text: ' masterpiece, best quality, 1girl, solo, pixelar' | |
| parameters: | |
| negative_prompt: >- | |
| lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, | |
| fewer digits, cropped, worst quality, low quality, normal quality, jpeg | |
| artifacts, signature, watermark, username, blurry | |
| output: | |
| url: images/highPixelarDOS_v1AF.preview.png | |
| - text: ' masterpiece, best quality, 1girl, solo, pixelar' | |
| parameters: | |
| negative_prompt: >- | |
| lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, | |
| fewer digits, cropped, worst quality, low quality, normal quality, jpeg | |
| artifacts, signature, watermark, username, blurry | |
| output: | |
| url: images/highPixelarMomokoS_v1AF.preview.png | |
| - text: ' masterpiece, best quality, 1girl, solo, pixelar' | |
| parameters: | |
| negative_prompt: >- | |
| lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, | |
| fewer digits, cropped, worst quality, low quality, normal quality, jpeg | |
| artifacts, signature, watermark, username, blurry | |
| output: | |
| url: images/highPixelarLM_v1AF.preview.png | |
| base_model: Lykon/AnyLoRA | |
| instance_prompt: null | |
| license: openrail | |
| # highPixelar | |
| <Gallery /> | |
| ## Model description | |
| New version lite DIM(128) 1024 resolution LoRA. | |
| (!) Version number is pending for complete so have same number between beta version. | |
| <b>difference of old version:</b> differ than have painting style. | |
| <!-- | |
| ### AnyLoRA(Defaults) | |
|  | |
| ### DosMix | |
|  | |
| ### MomokoS | |
|  | |
| ### Lametta | |
|  | |
| --> | |
| ## Download model | |
| Weights for this model are available in Safetensors format. | |
| [Download](/scrapware/highPixelar/tree/main) them in the Files & versions tab. | |