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

Upgrade now
Worms Team17 render mix [SDXL-PDXL-IlluXL-NoobXL] - SDXL V2 thumbnail

ModelsLab/Worms Team17 Render Mix [SDXL-PDXL-IlluXL-NoobXL] - SDXL V2

worms-team17-render-mix-sdxl-pdxl-illuxl-noobxl-sdxl-v2
Text to Image Community ModelFree for Premium UsersLLMs.txt
Okay, this update is LONG overdue. The main reason is: I wanted to upscale some images using Fooocus, but I found that the upscaled results would get a lot of strange details or miss some. I only upscaled a few of the lower-resolution images and did some mix-and-matching and manual fixes before I dumped this process for months, and recently I decided I would just go on and train V2 with what I have.That being said, I'll probably train Pony and Illustrious versions right after and focus on those because normal SDXL is a pain to use when it comes to Worms.IMAGE CHANGESREMOVED Scientist and Heavy worms. Worms should be now shaped more consistently with less negative prompting.Removed some images, mainly low-quality ones I couldn't find replacements for.Did some simple image editing to split multiple worm pictures into solo ones. There are still a few pictures with 2 worms and one with 5, all tagged "multiple worms".Added one new image.Applied Surface Blur to some images to cover up JPEG artifacts.As I said earlier, upscaled a few images and touched them up.43 images total.TAG CHANGESRemoved tags "limbless", "armless", "legless", "handless", "render", class-related tags and a bunch of others.Tags for hands are now "worm hands", "worm hand".Tags for subtle style control (may not work): for Worms 3D renders - "w3drender, black eyes, smooth worm body, sharp tail tip", for WFUS renders - "wfusrender, rounded eyebrows", for G4 game renders: "wg4render, black eyes, slim neck, folds on worm's body, rounded tail tip". I also added "low-contrast warm shading" to some G4 game renders, I find it to be kind of annoying.Some other minor edits, including adding tag "maw visible between clenched teeth" (may not work?)Trained against SD XL via Civitai
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": "boziorealvisxlv4",
"lora_model": "worms-team17-render-mix-sdxl-pdxl-illuxl-noobxl-sdxl-v2",
"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