Instructions to use LyliaEngine/bismuthIllustrious_v70 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use LyliaEngine/bismuthIllustrious_v70 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/bismuthIllustrious_v70") prompt = "1girl, blue eyes, black hair, huge breasts, katana, fighting stance, front view, looking at viewer, long katana, dark atmosphere, blank gaze, blood on katana, blood on steel, dripping blood, masterpiece, best quality, highly detailed, good quality, newest" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
| tags: | |
| - text-to-image | |
| - lora | |
| - diffusers | |
| - template:diffusion-lora | |
| widget: | |
| - output: | |
| url: images/b6b904cb-bbca-4b0a-8ec6-de7f9bb1f3e4.png | |
| text: >- | |
| 1girl, blue eyes, black hair, huge breasts, katana, fighting stance, front | |
| view, looking at viewer, long katana, dark atmosphere, blank gaze, blood on | |
| katana, blood on steel, dripping blood, masterpiece, best quality, highly | |
| detailed, good quality, newest | |
| parameters: | |
| negative_prompt: >- | |
| bad quality, worst quality, lowres, deformed, bad hands, watermark, simple | |
| background | |
| - output: | |
| url: images/53f1d41f-8949-4812-84e9-3879077c9e90.png | |
| text: >- | |
| highres, hi res, best quality, masterpiece,(anime coloring, anime | |
| screencap:1.1), breast contest, rivalry, breast press, faceoff, | |
| face-to-face, stare down, eye contact, blush, hands on own hips, 2girls, | |
| from side, yuri, beach, outdoors, micro bikini, BREAK | |
| parameters: | |
| negative_prompt: bad quality, worst quality, lowres, deformed, bad hand, watermark | |
| - output: | |
| url: images/54712f7f-bef4-4603-9461-8151433edc7b.png | |
| text: >- | |
| 1girl, red panties, underwear, panties, solo, shirt, black hair, black | |
| shirt, t-shirt, hairclip, freckles, hair ornament, no pants, long hair, | |
| looking down, short sleeves, cowboy shot, breasts, black eyes, heart, shirt | |
| tug, changing room, | |
| parameters: | |
| negative_prompt: bad quality,worst quality,lowres, bad anatomy, bad hands | |
| base_model: OnomaAIResearch/Illustrious-xl-early-release-v0 | |
| instance_prompt: None | |
| license: cdla-permissive-2.0 | |
| # bismuthIllustrious_v70 | |
| <Gallery /> | |
| ## Model description | |
| My first mix in illustrious category aiming to bring more details and flexibility to animated style of this type of models. Various results can be achieved - from animated to semi-realistic style depending on the prompt. | |
| As always my gratitude and due respect to the creators of original models that are used in the mix: | |
| https://civitai.com/models/827184/wai-nsfw-illustrious-sdxl?modelVersionId=1490781 | |
| https://civitai.com/models/1231009/be-mix-illustrious?modelVersionId=1387129 | |
| https://civitai.com/models/959736/rillusm-realistic-il?modelVersionId=1448475 | |
| https://civitai.com/models/1412760/lunarcherrymix-illustrious?modelVersionId=1637795 | |
| https://civitai.com/models/1695253/smooth-mix-illustrious2-noobai | |
| https://civitai.com/models/1318945?modelVersionId=2319122 | |
| Version 6.0: Experimental formula with addition of new elements to the mix for future development. | |
| Version 5.0: Update with newer versions of the components. | |
| Version 4.0: Return to older (v2.1) formula with improvements in composition and prompt adherence. | |
| Version 3.0: Experimental mix with a little shift to more anime style and more vivid palette. | |
| Version 2.1: Improved stability, composition and faces. | |
| Version 2: Cranking up overall details and contrast. Colors look more vivid too. Needs further testing. Has more of its "own identity" compared to version 1.0. | |
| Version 1: Overall very decent prompt adherence and anatomy. Stylisticaly close to anime-semirealism. High flexibility: some combinations of LORAs give very interesting results (you can find examples in the images). | |
| Recommended setitings: | |
| Sampling method: Euler a, DPM++ 2M, DPM++ 2M SDE, DPM++ 2S a, DPM2 a, DEIS | |
| Schedule type: Karras, SGM Uniform | |
| Sampling steps: 20-50 | |
| CFG Scale: 3-7 | |
| Highres.fix + Adetailer for face are recommended | |
| ## Source | |
| https://civitai.com/models/1359028/bismuth-illustrious-mix?modelVersionId=2734657 | |
| ## Credit | |
| https://civitai.com/user/Axelros | |
| ## Trigger words | |
| You should use `None` to trigger the image generation. | |
| ## Download model | |
| [Download](/LyliaEngine/bismuthIllustrious_v70/tree/main) them in the Files & versions tab. | |