README.md

---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: a chibi astronaut, nm22 minimalist style
  output:
    url: images/2YdKgP8iFDlQOkOT_UdTM_618efde27c2e469fb6901aa3cdb7781c.png
- text: a chibi astronaut, nm22 minimalist style
  output:
    url: images/OvpSq_oh4uzuQpgzb7SqE_8834795b886949f8998de674401c6879.png
- text: a pink frog, nm22 minimalist style
  output:
    url: images/T6Es-tWGWY7zv99Ps-CsC_d13d3b126e3243208dce293d54662037.png
- text: a girl wearing a flower crown, nm22 anime style
  output:
    url: images/g2P_Z7B8YzzJq-hX1S_Ky_3e1847a5aaf94c6baabb47c4fa367e6f.png
- text: a girl wearing a flower crown, nm22 style
  output:
    url: images/IhfUnD9Wf2sqHpKnTuNaK_29c9437bd0594404825d2afba24c7489.png
- text: a cute creature, nm22 style
  output:
    url: images/QfWbZpmcf6cLy4r5Mar4n_6a85f5f6ae9f4a788f1e85087fe4527e.png
- text: >-
    a girl with brown-blonde hair and big round glasses, tired, white tank top,
    jeans, nm22 style
  output:
    url: images/uqAuIMqA6Z7mvPkHg4qJE_f4c3cbe64e0349e7b946d02adeacdca3.png
- text: >-
    a girl with brown-blonde hair and big round glasses, tired, white tank top,
    jeans, nm22 illustration style
  output:
    url: images/29Jaqg8PDwDJKH3RGezGN_7a2aab7043eb40c3b2483860d9000e37.png
- text: girl, neck tuft, white hair ,sheep horns, blue eyes, nm22 style
  output:
    url: images/yHLPgQUCu6knr1wvjajNZ_b34f211660124020ae77377fff2970ef.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: nm22 style
license: creativeml-openrail-m
---
# Sonny Anime Fixed (Flux Dev)

<Gallery />

## Model description 

This is one of two Flux LoRAs on this style, this particular version being more fixed. This means it doesn&#39;t do as well with a lot of anime style prompt additions, and tends to stick to anime style really closely. If you want a more flexible version, check out the Flex LoRA. 

Typically if the linework seems like its falling apart a bit, it can be fixed by removing any additional stylization words you&#39;ve added. I also find it produces fewer artifacts if you don&#39;t add too many stylizations like &quot;anime&quot; or &quot;illustration&quot;.

I have included some examples with and without Anime prompts to show some of the difference.

Some words I like to use with the model:
- pastelcore
- lofi
- minimalist

Warning: This model seem hallucinate fake art signatures from time to time. This is less present this version vs. the Flex version, and I did not include any images with that kind of artifact in them. It seems it may have more to do with the underlying model, apologies if it causes a challenge for you!

Also big thank you to Fal for sponsoring credits for me to do some test trainings on platform!


![image/png](https://cdn-uploads.huggingface.co/production/uploads/635dd6cd4fabde0df74aeae6/EGabeugdoxAx0-TUy3hQM.png)


## Trigger words

You should use `nm22 style` to trigger the image generation.


## Download model

Weights for this model are available in Safetensors format.

[Download](/alvdansen/sonny-anime-fixed/tree/main) them in the Files & versions tab.