Instructions to use diaskssq321/Makima with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use diaskssq321/Makima with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("diaskssq321/Makima") prompt = "UNICODE\u0000\u0000m\u0000a\u0000k\u0000i\u0000m\u0000a\u0000,\u0000 \u0000r\u0000e\u0000d\u0000 \u0000h\u0000a\u0000i\u0000r\u0000,\u0000 \u0000y\u0000e\u0000l\u0000l\u0000o\u0000w\u0000 \u0000r\u0000i\u0000n\u0000g\u0000e\u0000d\u0000 \u0000e\u0000y\u0000e\u0000s\u0000.\u0000 \u0000M\u0000a\u0000k\u0000i\u0000m\u0000a\u0000 \u0000s\u0000m\u0000i\u0000l\u0000i\u0000n\u0000g\u0000 \u0000a\u0000n\u0000g\u0000r\u0000i\u0000l\u0000y\u0000 \u0000a\u0000t\u0000 \u0000t\u0000h\u0000e\u0000 \u0000v\u0000i\u0000e\u0000w\u0000e\u0000r\u0000 \u0000l\u0000i\u0000k\u0000e\u0000 \u0000a\u0000 \u0000m\u0000e\u0000n\u0000a\u0000c\u0000e\u0000.\u0000 \u0000H\u0000e\u0000r\u0000 \u0000y\u0000e\u0000l\u0000l\u0000o\u0000w\u0000 \u0000e\u0000y\u0000e\u0000s\u0000 \u0000a\u0000r\u0000e\u0000 \u0000g\u0000l\u0000o\u0000w\u0000i\u0000n\u0000g\u0000 \u0000a\u0000n\u0000d\u0000 \u0000t\u0000h\u0000e\u0000 \u0000b\u0000a\u0000c\u0000k\u0000g\u0000r\u0000o\u0000u\u0000n\u0000d\u0000 \u0000i\u0000s\u0000 \u0000t\u0000h\u0000e\u0000 \u0000s\u0000k\u0000y\u0000l\u0000i\u0000n\u0000e\u0000 \u0000o\u0000f\u0000 \u0000t\u0000o\u0000k\u0000y\u0000o\u0000" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("diaskssq321/Makima")
prompt = "UNICODE\u0000\u0000m\u0000a\u0000k\u0000i\u0000m\u0000a\u0000,\u0000 \u0000r\u0000e\u0000d\u0000 \u0000h\u0000a\u0000i\u0000r\u0000,\u0000 \u0000y\u0000e\u0000l\u0000l\u0000o\u0000w\u0000 \u0000r\u0000i\u0000n\u0000g\u0000e\u0000d\u0000 \u0000e\u0000y\u0000e\u0000s\u0000.\u0000 \u0000M\u0000a\u0000k\u0000i\u0000m\u0000a\u0000 \u0000s\u0000m\u0000i\u0000l\u0000i\u0000n\u0000g\u0000 \u0000a\u0000n\u0000g\u0000r\u0000i\u0000l\u0000y\u0000 \u0000a\u0000t\u0000 \u0000t\u0000h\u0000e\u0000 \u0000v\u0000i\u0000e\u0000w\u0000e\u0000r\u0000 \u0000l\u0000i\u0000k\u0000e\u0000 \u0000a\u0000 \u0000m\u0000e\u0000n\u0000a\u0000c\u0000e\u0000.\u0000 \u0000H\u0000e\u0000r\u0000 \u0000y\u0000e\u0000l\u0000l\u0000o\u0000w\u0000 \u0000e\u0000y\u0000e\u0000s\u0000 \u0000a\u0000r\u0000e\u0000 \u0000g\u0000l\u0000o\u0000w\u0000i\u0000n\u0000g\u0000 \u0000a\u0000n\u0000d\u0000 \u0000t\u0000h\u0000e\u0000 \u0000b\u0000a\u0000c\u0000k\u0000g\u0000r\u0000o\u0000u\u0000n\u0000d\u0000 \u0000i\u0000s\u0000 \u0000t\u0000h\u0000e\u0000 \u0000s\u0000k\u0000y\u0000l\u0000i\u0000n\u0000e\u0000 \u0000o\u0000f\u0000 \u0000t\u0000o\u0000k\u0000y\u0000o\u0000"
image = pipe(prompt).images[0]Makima

- Prompt
- UNICODEmakima, red hair, yellow ringed eyes. Makima smiling angrily at the viewer like a menace. Her yellow eyes are glowing and the background is the skyline of tokyo

- Prompt
- UNICODEmakima, anime style, woman, high detail, solo, standing, vibrant red hair, long straight hair, yellow ringed eyes, confident smirk, white collared shirt, black tie, government uniform, pale skin, slender figure, control devil aura, glowing red lines, floating red strings, cherry blossom petals, Tokyo cityscape background, twilight sky, lens flare, dynamic pose, hands in pockets, sharp shadows, slight wind effect, ominous atmosphere, clean line art, vivid colors, smooth shading, sparkle effects, ethereal glow, official's coat draped over shoulders, floating shadowy devil silhouettes, magic circle under feet, hypnotic eye pattern
Trigger words
You should use Makima 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
- 11