🎉 New Year Sale: Get 20% OFF on all plans — Use code NEWYEAR2026.

Upgrade now
Werewolf FLUX LoRA - WEREWOLF FLUX LoRA v1 thumbnail

ModelsLab/Werewolf FLUX LoRA - WEREWOLF FLUX LoRA V1

werewolf-flux-lora-werewolf-flux-lora-v1
Text to Image Community ModelFree for Premium UsersLLMs.txt
Version 1: It can be used with just the word werewolf. Misty/Forest aren't needed I put them in trigger words because I used them a lot in training and if your image calls for it I think it will make your life easier. I recommend using 'mouth open', also if you want a specific eye glow especially yellow, red, orange, or yellow orange it should work fine using "eyes glowing color name"Prompting the fur style works pretty well for natural wolflike colors and blending those colors, I do not think it will do rainbow or neon, but you should be able to mix the natural wolf colors in unusual combinations for instance a 'creamy white and red blend' in either soft or rough textured fur should work.One quirk is that it often tunnels the image, centering dirt paths or roads under the werewolf, giving the sense that the creature is blocking your way. This was intentional, but it can limit versatility if you need a different setup. The goal was to create an image that conveys the futility of confronting this creature.Often I imagine I am one of the people at the beginning of the horror movie that have no idea there is a monster lurking in the neighborhood and when I am ambushed I have only a second or two to decide how I'm going to make my last stand. Can I somehow scar this monster before it rips me apart because there is no escape and the hero that is going to take it down later will only do so after losing his best fighters and trapping it in an enclosed space with the MOAB packed full of silver ball bearings with an iron core because lets face it regular silver doesn't have the weight to damage this thing and anything without silver won't stop its regeneration and even after you take it down you better cut its head off...sorry for the rant.This is just Version 1. I plan to refine it before Halloween. If you post images using this model in 1024x1024, I ll try to incorporate community preferences into Version 2.
API PlaygroundAPI Documentation

API Endpoint URL

Base URL for all API requests to this endpoint.

https://modelslab.com/api/v6/images/text2img

API Authentication

Authentication requires a valid API key included in the request. Generate and manage your API keys from your developer dashboard. Include the key in the key parameter for all API requests.

Integration Examples

Production-ready code samples for API integration

{
"prompt": "R3alisticF, hauntingly beautiful oriental necromancer, long flowing brown hair, bangs, darkly tanned skin, earrings, bone necklaces, dark eyeshadow, red lips, vibrant, front-laced transparent, filmy silk blouse, cleavage, holding skull, in a sandstone room lit by candles, High Detail, Perfect Composition, high contrast, silhouetted, chiascuro",
"model_id": "fluxdev",
"lora_model": "werewolf-flux-lora-werewolf-flux-lora-v1",
"width": "1024",
"height": "1024",
"negative_prompt": "(worst quality:2), (low quality:2), (normal quality:2), (jpeg artifacts), (blurry), (duplicate), (morbid), (mutilated), (out of frame), (extra limbs), (bad anatomy), (disfigured), (deformed), (cross-eye), (glitch), (oversaturated), (overexposed), (underexposed), (bad proportions), (bad hands), (bad feet), (cloned face), (long neck), (missing arms), (missing legs), (extra fingers), (fused fingers), (poorly drawn hands), (poorly drawn face), (mutation), (deformed eyes), watermark, text, logo, signature, grainy, tiling, censored, nsfw, ugly, blurry eyes, noisy image, bad lighting, unnatural skin, asymmetry",
"num_inference_steps": "31",
"scheduler": "DPMSolverMultistepScheduler",
"guidance_scale": "7.5",
"enhance_prompt": false,
"key": "YOUR_API_KEY"
}

SDKs

Official SDKs

Production-ready SDKs and client libraries for all major programming languages

API Parameters

Technical specifications for API request parameters.

Field NameParameterTechnical Description
promptpromptprompt help in image generation
Modelmodel_idEnter model_id that can help in image generation
lora Modellora_modelNo description available
Widthwidthwidth of the image
Heightheightheight of the image
Negative Promptnegative_promptNegative prompt help in avoid things that you do not want in image
Stepsnum_inference_stepsNumber of inference steps
SchedulerschedulerSampling scheduler
Guidance Scaleguidance_scaleHow closely to follow the prompt (1-10)
enhance_promptenhance_promptAutomatically enhance the prompt