ModelsLab/Crosshatch Drawing Style - V1.1

crosshatch-drawing-style-v1-1

Text to Image Community ModelFree for Premium Users LLMs.txt

Version 1 is not as flexible as I would have like, so I tried to tweak the dataset a bit. This version seems to follow prompts a bit better. I took out two images whose lines seems a bit too strong for my taste, so the hatching looks finer in this version.This is epoch 11, the other epochs can be found here: tensor. art/models/809142070418814199/Crosshatch-V2-NoCD6A3Cos5E11-2024-12-20-00:34:58-Ep-11Crosshatch V2 NoCD6A3Cos5E11 2024-12-20 00:34:58Went back to Cos 5 and using 11 Epoch since there are only19 images (1 synthetic image of a full body Asian model)No caption training, but manually added these 3 captions:"two cherries", "Space marine from Warhammer 40K","An African baby with her left hand on her ear"FLUX.1 - dev-fp8Trigger: crosshatch drawingRepeat: 20 Epoch: 11 Nineteen 512x512 images (* 20 11 19)=4180Unet LR: 0.0005 Scheduler: cosine Optimizer: AdamWNetwork Dim: 6 Alpha: 3Prompt: crosshatch black and white drawing of a woman swimming underwater. The woman is wearing a one piece swimsuit, and she is wearing goggles on her eyes. Her arms are outstretched. To the right of the woman, a sea turtle is swimming in the water.Sampler: dpmpp_2mEpoch Loss1 0.3422 0.341 <-3 0.3244 0.35 0.36 0.37 0.38 0.29 0.210 0.2 <- lowest11 0.2

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": "fluxdev",
  "lora_model": "crosshatch-drawing-style-v1-1",
  "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