ModelsLab/Impasto Oil Painting Style - Variant 3 (Florence2)

impasto-oil-painting-style-variant-3-florence2

Text to Image Community ModelFree for Premium Users LLMs.txt

I want to see if I can make the LoRA produce more "natural" brushstrokes. So I used images captioned with Florence 2, and removed images that have more "rectangular" brush strokes from the training set. The result does seem to work. This is probably going to be the last variant of this LoRA .To give you some idea of the images that went into the training set, you can see this post, which was created using the Florence 2 captions for the training set.This is epoch 11 from 12 epochs. The rest can be found here: tensor. art/models/804233992246203471/Impasto-Oil-V6-CapD6A3Cos5-2024-12-06-19:09:36-Ep-11FLUX.1 - dev-fp8Trigger: impasto oil paintingRepeat: 20 Epoch: 12 17 512x512 image (* 20 12 17)=4080 stepsUnet LR: 0.0005Scheduler: cosineOptimizer: AdamWNetwork Dim: 6 Alpha: 3Prompt: impasto oil painting of punk sailor moon playing a guitar at a heavy metal mosh pit, tattoos, pearcingSampler: dpmpp_2mEpoch Loss1 0.4412 0.4??3 0.4154 0.4065 0.3816 0.3837 0.3768 0.3569 0.3511 0.328 <- lowest11 0.330 probably test this one first12 0.342

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": "impasto-oil-painting-style-variant-3-florence2",
  "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