ModelsLab/Qasar - Qasar 3dcg

qasar-qasar-3dcg

Text to Image Community ModelFree for Premium Users LLMs.txt

Limitations noted:

trouble with hands, fingers on most images

Occasionally bad eyes (heterochromia issues)

sometimes will create splitframe, multiple characters or different views.

Recommended negative prompts:

If drawing women models, prompt out:

2girls, 3girls

The need for "watermark" appears to be an occasional need. I'd recommend you prompt "child" in the negative prompts to avoid childish features.

That's pretty much it. I usually develop a prompt that differs between landscape vs people promtps and often they are different for each new prompt. You can look at my example showcase pictures for exactly what I prompted for positive and negative, and if you're drawing the same type of image you may want to consider a similar approach.

You may find that I use unconventional prompting like the use of "::", ";", "_;", "AND", "_" and varied schedules without using "[" "]" around them. This is because I use the open source A1111 and I coded my own update to the prompt parser which allows the use of these symbols. I don't think I included sequences in these images, but other images that I've posted in the last month will have them.

For more information about that please see this article, or view my profile and look at my announcements for my github page. If you're feeling in the giving mood, I welcome all support here on my buy me a coffee page :)

Thanks and hope you enjoy :)

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": "qasar-qasar-3dcg",
  "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