tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: a boy in a sailor suit frowning, nm22 illustration style
output:
url: images/oH3_pMI4sHH78ep1Ts1NE_cd325176eda94c9ea826e9f780e14f76.png
- text: a girl wearing a flower crown, nm22 anime style
output:
url: images/iwR47KRPMr4FHvOw8MGgn_e35c500e7ba04b578f8d8156d4ce1954.png
- text: a pink frog, nm22 minimalist style
output:
url: images/GLuFasaLyEoBaAUQMREVf_20b5cf5b178a404296978e360a9ac435.png
- text: >-
a girl with brown-blonde hair and big round glasses, tired, white tank
top, jeans, nm22 illustration style
output:
url: images/l3LgGsAydCPyN4rzZJ6L6_209067c1c0ea469f907f0f1f887252dd.png
- text: girl, neck tuft, white hair ,sheep horns, blue eyes, nm22 style
output:
url: images/p6sGE_Hh_qCwexqg0I5rt_4db6dd66bb3946ca821642089a580c8d.png
- text: a little witch, nm22 minimalist style, pastelcore
output:
url: images/fwjmAF9gys3Qw2nDwWRDO_94b9c15fbc6c4583a62f39a5cc600c71.png
- text: a chibi astronaut, nm22 minimalist anime style, crayon style
output:
url: images/emGPosDE3_3HdVhS1lT5P_22704e4d663c4a2cbd04136baa0a23a1.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: nm22 [style] style
license: creativeml-openrail-m
Sonny Anime Flex (Flux Dev)
Model description
This one of a two model pair, trained to create soft gel line anime style images in a sort of cute lofi aesthetic. This is the FLEX version, that has more flexibility and can be pretty successfully pushed away from true anime towards cartoon art and more complex scenes. However, it is recommended to include the style direction in your trigger.
Example prompt: [subject], [colors/aesthetic description], nm22 [style direction] style
WARNING: The model tends to hallucinate teensy artist signatures, although they weren't at all present in the training data! Unfortunately not a lot I can do about it, may be worth exploring with an image to image workflow.
A big thank you to Fal for sponsoring credits that allowed me to create this LoRA!
Trigger words
You should use nm22 [style] style
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.