ModelsLab/0001SoftRealistic - V80bh

0001softrealistic-v80bh

Text to Image Community ModelFree for Premium Users LLMs.txt

PLEASE ADD YOUR IMAGES!

I created this model by mixing many different models from different sources. It took a long time to create the model, not being a professional, I did it by trial and error. I made the model for me and my friends and one day my friends told me to share my work on this site.

About the model.

This is a realistic model with a little touch of 3D from Pixar. It does quite well in a lot of different tasks, but it shows best in making images of people. Faces and bodies, including nudes, turn out very well from my point of view. I have used many different Lora's to generate images with my model, almost never had a problem. I used the following settings to get the best results - Sampling steps - 25, CFG Scale - 5, Sampling method - Euler. I also highly recommend to use Hires fix with upscaler ESRGAN_4x (hires steps - 25, Denoising strength - 0.3).

Some of the original models had a clear NSFW bias, because of this you can suddenly get an image of naked characters. To avoid this, write "nsfw, nudity" into the negative prompt.

The newer the version of the model, the more realism there is in it.

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": "0001softrealistic-v80bh",
  "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