ModelsLab/Future Noir: Retro SF Illustration Style (Syd Mead) - V1.2

future-noir-retro-sf-illustration-style-syd-mead-v1-2

Text to Image Community ModelFree for Premium Users LLMs.txt

Because the training images are mostly panoramic, I decide to trained again at 1024x1024. This is version 1.2 because I was not happy with v1.1 (which was trained captionless at 1024x1024 with network dim of 8, and it had problem reproducing the spinner!)The training image set was also captioned using Florence 2 rather than captionless as in V1. The captions are edited for two images depicting the iconic Blade Runner Spinner, which were labeled as "motorcycle". I changed them to "hovercraft". I didn't want to use the term car since there are other cars in the training set and I don't want Flux to combine them.The result seems to be better, capturing more of Syd Mead's "industrial design" look, and the images are sharper and more coherent.This is epoch 10, the other epoch can be found at tensor. art/models/810970807363733178/Syd-Mead-6-CapD6A3Cos5-2024-12-24-05:30:32-Ep-10FLUX.1 - dev-fp8Trigger: sydme1 paintingRepeat: 20 Epoch: 10 (Trained on 18 images at 1024x1024, total of 3600s steps)Unet LR: 0.0005 Scheduler: cosine Optimizer: AdamWNetwork Dim: 6 Alpha: 3Sampler: dpmpp_2mEpoch Loss1 0.4042 0.3893 0.3874 0.3805 0.3786 0.3707 0.3648 0.3679 0.349 <- lowest10 0.354

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": "future-noir-retro-sf-illustration-style-syd-mead-v1-2",
  "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