Instructions to use LyliaEngine/Mirazhael with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use LyliaEngine/Mirazhael 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/Mirazhael") prompt = "miraz, scenery, masterpiece, best quality, newest, absurdres, highres, focus, depth of field, dynamic angle, cinematic lighting, volumetric lighting, 1girl, unworn mask, black hair, red eyes, animal ears, fox tail, solo, tattoo, unworn katana, fox mask, long hair, hair ornament, hairclip, rope, ear piercing, holding sakazuki, sheath, jewelry, tattoo, bangs, arm tattoo, yellow background, off shoulder kimono, nail polish, red nails, dutch angle, from behind, looking back, shoji, scenery, fine details, soft shading, gentle lighting, mysterious ambiance, soft textures, backless, sitting, mountainous horizon, panorama, plum blossoms, petals, <lora:Mirazhæl:1>" 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/83cd4f30-b54d-4265-9fb8-1cddfe8cdf90.png | |
| text: >- | |
| miraz, scenery, masterpiece, best quality, newest, absurdres, highres, | |
| focus, depth of field, dynamic angle, cinematic lighting, volumetric | |
| lighting, 1girl, unworn mask, black hair, red eyes, animal ears, fox tail, | |
| solo, tattoo, unworn katana, fox mask, long hair, hair ornament, hairclip, | |
| rope, ear piercing, holding sakazuki, sheath, jewelry, tattoo, bangs, arm | |
| tattoo, yellow background, off shoulder kimono, nail polish, red nails, | |
| dutch angle, from behind, looking back, shoji, scenery, fine details, soft | |
| shading, gentle lighting, mysterious ambiance, soft textures, backless, | |
| sitting, mountainous horizon, panorama, plum blossoms, petals, | |
| <lora:Mirazhæl:1> | |
| parameters: | |
| negative_prompt: >- | |
| lowres, (worst quality,bad quality,low quality:1.2), bad anatomy, | |
| signature, | |
| - output: | |
| url: images/bbda68b8-5d7f-4fb0-9b05-ca2af7bd3bfd.png | |
| text: >- | |
| miraz, scenery, high detail, intense focus, very awa, masterpiece, best | |
| quality, newest, absurdres, highres, flower, outdoors, sky, day, cloud, | |
| water, blue sky, tree, no humans, petals, white flower, grass, cloudy sky, | |
| plant, nature, pink flower, fish, reflection, yellow flower, rock, mountain, | |
| field, flower field, river, mountainous horizon, landscape, lily pad, | |
| goldfish, daisy, reflective water, pond, partially underwater shot, tropical | |
| fish, koi <lora:Mirazhæl:1> | |
| parameters: | |
| negative_prompt: >- | |
| lowres, (worst quality,bad quality,low quality:1.2), bad anatomy, | |
| signature, | |
| - output: | |
| url: images/6f94ed2d-d76b-4f02-ab88-d5dba7f073c5.png | |
| text: >- | |
| miraz, masterpiece,highres,best quality,absurdres,light particles,cinematic | |
| lighting,high contrast,colorful 1girl,solo,standing,serafuku,school uniform, | |
| swim,skinny dipping,freediving,underwater,back,window wall,french | |
| window,night,whale,fish,bubble,dark theme,reflecting ambient cyan hues from | |
| glass walls framing a glowing metropolis skyline with neon-lit skyscrapers. | |
| glowing city skyline dotted with lights outside the glass of | |
| aquarium,creating ethereal luminosity through suspended particles. the dimly | |
| lit deep blue aquarium with faint caustic light penetrating the water | |
| surface,strands of hair undulate like seaweed while semi-transparent | |
| jellyfish clusters provide organic coverage,their bioluminescent tentacles | |
| mirroring distant city lights. silver bubbles trace ascending paths | |
| alongside schools of angelfish,contrasting against dark indigo depths where | |
| a whale silhouette emerges. cinematic composition utilizes caustics lighting | |
| algorithms for underwater refraction. cool blue tones wash through the | |
| aquarium,creating relaxing atmospheric layers,ssr reflections on french | |
| window surfaces, <lora:Mirazhæl:1> | |
| parameters: | |
| negative_prompt: >- | |
| lowres, (worst quality,bad quality,low quality:1.2), bad anatomy, | |
| signature, | |
| base_model: OnomaAIResearch/Illustrious-xl-early-release-v0 | |
| instance_prompt: miraz, scenery | |
| license: cdla-permissive-2.0 | |
| # Mirazhael | |
| <Gallery /> | |
| ## Model description | |
| trigger : miraz, scenery, | |
| Scenery tag might be optional but since it's trained in, no harm putting it in your prompt. Give it a try with ligne claire, for a different style! | |
| Trained mostly on landscapes images! Great for mixing and improving the overall details of your backgrounds as long you describe it a bit. | |
| Fantasy or modern, mountains or plains, summer or winter, it can do it all as long you're prompting for it! | |
| Enjoy it, and show me beautiful stuff! | |
| ## Trigger words | |
| You should use `miraz` to trigger the image generation. | |
| You should use `scenery` to trigger the image generation. | |
| ## Source | |
| https://civitai.red/models/2443182/mirazhael-or-by-utdt69?modelVersionId=2747028 | |
| ## Credit | |
| https://civitai.red/user/UTdT_69 | |
| ## Download model | |
| [Download](/LyliaEngine/Mirazhael/tree/main) them in the Files & versions tab. | |