ModelsLab/RobMix - Evolution V2.0

robmix-evolutionv20

Text to Image Community ModelFree for Premium Users LLMs.txt

RobMix Evolution builds on my first merge, RobMix Ultimate.

This version starts with RobMix Ultimate, then merged block-by-block with some fantastic models to draw out the best parts of each and mitigate the downsides. My goal was to expand the creative range of the model while retaining the photorealistic style.

You can read my process for early experiments with Evolution on Medium. Note that the models referenced in the post went into a personal merge that I called Evolution A and Evolution B—the models referenced in that post aren't included in Evolution D.

The final stage of Evolution, Evolution D, started by blending:

That blend was merged back into RobMix Ultimate.

Next, I added a block-by-block merge of Juggernaut v9, followed by a dash of ICBINP XL v4.

This model can be sensitive to high CFGs.

Recommended settings:

DPM++ 3M SDE
AlignYourSteps scheduler
CFG 3.0-4.0
40 steps
Clip Skip -3

The higher the CFG, the more steps you'll need. If it's speed you're looking for, you may want to look elsewhere. Alternatively, consider using the genius Automatic CFG node in Comfy and set your CFG wherever you'd like.

This model is generally very capable with only a single pass, but really shines in quality with a 1.5x latent upscale at 0.30 to 0.40 denoise with an additional 40 steps.

With this full workflow, a generation on my 3080 takes around 40 seconds.

To get the very best results, add the following optimizations:

Free U

b1: 1.05
b2: 1.08
s1: 0.95
s2: 0.88

Perturbed Attention Guidance

Scale: 1.5
Adaptive scale: 0.100

Token Downsampling

Depth 1: 2.00
Depth 2: 2.00

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": "robmix-evolutionv20",
  "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