ModelsLab/OC LoRA Tests - PriscaDys V1 33

oc-lora-s-priscadys-v1-33

Text to Image Community ModelFree for Premium Users LLMs.txt

Final version after applying image loopbacks. The LoRA prior to loopback has better details but somehow adding the loopback images caused the pupil shape to undertrain.Training Goals:Complex PupilsLower Body Outfit FidelityResults:Getting pupils correct will require inpainting or usage of adetailer. Inpainting manually has better results compared to adetailer. With some editing, the pupils can be obtained in a single inpaint pass. Otherwise use two passes. Pupil shape is correct but the shading is incorrect where the bottom half appears to be transparent.Lower Body is a massive struggle. I will attempt to create another character design to test some more theories as I am running to roadblocks now.UndertrainingHairlineskirt designpupil shadingOvertrainingPoseAugmentationsStyleCameraCensorClose-upsLoopbackIssues: Due to the usage of lower quality images, antialiasing artifacts are present. This is fixable but I'm too lazy to do so. Main cause is that I did not upscale every base image consistently. Poses are overtrained and might need emphasis to workConcept bleeding is present for outfits around 'dress' or shirt based designsRecommended to use style LoRAs to get around style bleeding.

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": "boziorealvisxlv4",
  "lora_model": "oc-lora-s-priscadys-v1-33",
  "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