ModelsLab/DynaVision XL - All-In-One Stylized 3D SFW And NSFW Output, No Refiner Needed! - Beta 0.4.1.1-BakedVAE

dynavisionxlallinonestylized3dsfwandnsfwoutputnorefinerneeded-beta0411bakedvae

Text to Image Community ModelFree for Premium Users LLMs.txt

DynaVision XL Beta 0.4.1.1 Public Release 08/25/23

This had some major reworking under the hood, as I'm trying to replace some of the earlier LORA builders that have issues with watermarks and signatures. it's an ongoing process and right now they're still a known issue, but they'll be something I'll be actively working on to fix moving forward. The reworking has changed the color balance of the output somewhat to something a bit more neutral - in a way this is better for doing proper post color work, and it looks just fine on it's own, but when compared directly in an x/y, the shift in color balance is subtle, but it's there. I've found the best way to bring the color back now is to use a bit higher CFG, with 7.5 being the sweet spot I've found.

Look for coherence improvements, a bit more detailed backgrounds and skin (though not too much, I want to keep that realistic stylized cartoon feel), less issues with splotchy irises and less racial bias. This also had an update merge with NightVision XL 0.6.8.1

LORAs Added

xl_real_beta
Grit-SDXL
MovieStillMasteryV03
greengirl (CokCok1.0)

Known Issues

hands
signatures and watermarks
Nipples are acting up again, I've noticed on occasion they're showing up on clothes again, and occasionally show up malformed. It seems it's trying to add piercings to nipples sometimes, and I've had luck with adding "nipple piercing" to my negatives if you find them giving you grief.

API Playground API 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": "dynavisionxlallinonestylized3dsfwandnsfwoutputnorefinerneeded-beta0411bakedvae",
  "lora_model": [],
  "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

JavaScript

Python

PHP

API Parameters

Technical specifications for API request parameters.

Field Name	Parameter	Technical Description
prompt	`prompt`	prompt help in image generation
Model	`model_id`	Enter model_id that can help in image generation
lora Model	`lora_model`	No description available
Width	`width`	width of the image
Height	`height`	height of the image
Negative Prompt	`negative_prompt`	Negative prompt help in avoid things that you do not want in image
Steps	`num_inference_steps`	Number of inference steps
Scheduler	`scheduler`	Sampling scheduler
Guidance Scale	`guidance_scale`	How closely to follow the prompt (1-10)
enhance_prompt	`enhance_prompt`	Automatically enhance the prompt