Instructions to use Shero448/kagefusa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Shero448/kagefusa with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("John6666/prefect-pony-xl-v2-cleaned-style-sdxl", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Shero448/kagefusa") prompt = "score_9, score_8_up, score_7_up,anime_source, source_anime, best background, detailed background, anime screencap, Kagefusa, upper body, tongue out, tsundere, indoors, <lora:JN_Manyuu_Kagefusa:0.8>" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
kagefusa

- Prompt
- score_9, score_8_up, score_7_up,anime_source, source_anime, best background, detailed background, anime screencap, Kagefusa, upper body, tongue out, tsundere, indoors, <lora:JN_Manyuu_Kagefusa:0.8>
- Negative Prompt
- pubic hair, 3d, cropped, censored, bar censoring, mosaic censoring, (simple background:1.0), siblings, bad legs, clones, monochrome, clones, sketch, rought lines, patreon username, logo, bad proportions, artist signature, artist name,
Trigger words
You should use kagefusa to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 3