Sonny Anime (Flux) - Flex
by ModelsLabThis 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] styleWARNING: 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 wordsYou should use nm22 [style] style to trigger the image generation.
sonny-anime-flux-flexInput
Per image generation will cost 0.0047$
For premium plan image generation will cost 0.00$ i.e Free.
Output
Unknown content type
Related Models
Discover similar models you might be interested in
![Text Improver [FLUX] - FLUX v0.4](https://images.stablediffusionapi.com/?Image=https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/cdb00713-5561-4418-97f2-ab7960651ed4/width=752/32143192.mp4)
![[Pinkie] Dark Ink Style - [Flux] - Flux](https://images.stablediffusionapi.com/?Image=https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/ab27f365-1444-42e3-a165-8a5dbc939f0c/width=832/25615400.jpeg)
![Diamond, a fake person [Flux+SDXL] - FLUX](https://images.stablediffusionapi.com/?Image=https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/ff04742b-04b4-45c4-b309-b72aa764c9ee/width=768/56812790.mp4)
Sonny Anime (Flux) - Flex Readme
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] styleWARNING: 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 wordsYou should use nm22 [style] style to trigger the image generation.