Future Noir: Retro SF Illustration Style (Syd Mead) - V1.2
by ModelsLabBecause 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
future-noir-retro-sf-illustration-style-syd-mead-v1-2Input
Per image generation will cost 0.0047$
For premium plan image generation will cost 0.00$ i.e Free.
Output
Unknown content type
Looking for something different?
Models that trade off differently against the one you are viewing
Better quality
Newer flagship models that generally produce stronger results.
Faster turnaround
Built for speed when you are iterating on a prompt.
Related Models
Discover similar models you might be interested in
![Tracer (Overwatch 2) [FLUX] LoRA - v2.0](https://images.stablediffusionapi.com/?Image=https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/30a66fd1-f5a6-4cbc-bdb9-5e1233a5e2c9/width=896/24951811.jpeg)
![[Flux.1 D][Realistic] Sweet Dress Collection | - Style 4](https://images.stablediffusionapi.com/?Image=https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/4358a1b9-e266-4105-b099-b456ecf587b3/width=1152/46139299.jpeg)
![90s Hand drawn animation / cartoon style for backgrounds, illustrations and arts [Flux] - v3.0](https://images.stablediffusionapi.com/?Image=https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/3f85626d-0c24-4b78-ac2e-7a6b94393c3c/width=1024/35119251.jpeg)
About Future Noir: Retro SF Illustration Style (Syd Mead) - V1.2
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
Technical Specifications
- Model ID
- future-noir-retro-sf-illustration-style-syd-mead-v1-2
- Provider
- ModelsLab
- Category
- Image Models
- Task
- Text to Image
- Price
- $0.0047 per API call
- Added
- July 8, 2025
Key Features
- High-resolution AI image generation from text prompts
- Negative prompt support for precise control
- Multiple output formats and aspect ratios
- Adjustable inference steps and guidance scale
- Batch generation support via API
Quick Start
Integrate Future Noir: Retro SF Illustration Style (Syd Mead) - V1.2 into your application with a single API call. Get your API key from the pricing page to get started.
import requestsimport jsonurl = "https://modelslab.com/api/v6/images/text2img"headers = {"Content-Type": "application/json"}data = {"model_id": "future-noir-retro-sf-illustration-style-syd-mead-v1-2","prompt": "your prompt here","key": "YOUR_API_KEY"}try:response = requests.post(url, headers=headers, json=data)response.raise_for_status() # Raises an HTTPError for bad responses (4XX or 5XX)result = response.json()print("API Response:")print(json.dumps(result, indent=2))except requests.exceptions.HTTPError as http_err:print(f"HTTP error occurred: {http_err} - {response.text}")except Exception as err:print(f"Other error occurred: {err}")
Pricing
Future Noir: Retro SF Illustration Style (Syd Mead) - V1.2 API costs $0.0047 per API call. Pay only for what you use with no minimum commitments. View pricing plans
Use Cases
- Product photography and e-commerce visuals
- Marketing and social media content creation
- Concept art and design prototyping
- Custom illustrations and artwork
Future Noir: Retro SF Illustration Style (Syd Mead) - V1.2 FAQ
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 usi
You can integrate Future Noir: Retro SF Illustration Style (Syd Mead) - V1.2 into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "future-noir-retro-sf-illustration-style-syd-mead-v1-2" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation.
Future Noir: Retro SF Illustration Style (Syd Mead) - V1.2 costs $0.0047 per API call. ModelsLab plans start at $21/month (Basic), and the $149/month Open Source plan includes unlimited generation on open-source models.
The model ID for Future Noir: Retro SF Illustration Style (Syd Mead) - V1.2 is "future-noir-retro-sf-illustration-style-syd-mead-v1-2". Use this ID in your API requests to specify this model.
Yes. ModelsLab is subscription-based with no free tier — plans start at $21/month (Basic, 3,250 API calls). The $149/month Open Source Unlimited plan includes unlimited generation across open-source models; premium third-party models are billed per call from your wallet.