cozyuj/ev-car-maker 🖼️🔢❓📝✓ → 🖼️

▶️ 9 runs 📅 Sep 2025 ⚙️ Cog 0.15.3
automotive automotive-design car image-to-image lora text-to-image

About

Example Output

Prompt:

"

ultra realistic, hyper detailed, 8k, 16k, ultra high resolution, sharp focus, architectural visualization render, octane render, unreal engine quality

futuristic electric car concept, inspired by Hyundai Ioniq 6,
streamlined aerodynamic body with "curve of steel" design for optimized airflow,
parametric pixel inspired LED headlights and taillights, energy-efficient adaptive illumination,
integrated active cooling vents for battery thermal management, lightweight aluminum and carbon fiber panels,
sleek coupe-like design with aerodynamic underbody, solar roof panels for auxiliary power,
design influences:
Tesla futuristic clean surfaces, smooth minimalist glass roof, high efficiency aerodynamic silhouette::3,
Audi precision-engineered metallic minimalism, subtle sharp lines::2,
Bentley luxury craftsmanship with functional aerodynamics::2,
Porsche sporty curves minimal::0.2,

ultra realistic, hyper detailed, photorealistic automotive concept render, daylight and soft studio lighting, high fidelity reflections, 8k resolution, engineering concept visualization

hyper futuristic, visionary next-gen EV, photorealistic studio concept render, cinematic lighting, ultra detailed, 8k, sharp focus, high contrast reflections, concept art, innovative automotive design

no blurry, no lowres, no noisy, no distorted, no oversaturated, no cartoon, no anime, no low quality, no duplicate objects, no broken architecture, no text, no watermark

"

Output

Example output

Performance Metrics

8.93s Prediction Time
8.94s Total Time
All Input Parameters 
{
  "model": "dev",
  "prompt": "ultra realistic, hyper detailed, 8k, 16k, ultra high resolution, sharp focus, architectural visualization render, octane render, unreal engine quality\n\nfuturistic electric car concept, inspired by Hyundai Ioniq 6,  \nstreamlined aerodynamic body with \"curve of steel\" design for optimized airflow,  \nparametric pixel inspired LED headlights and taillights, energy-efficient adaptive illumination,  \nintegrated active cooling vents for battery thermal management, lightweight aluminum and carbon fiber panels,  \nsleek coupe-like design with aerodynamic underbody, solar roof panels for auxiliary power,  \ndesign influences:  \nTesla futuristic clean surfaces, smooth minimalist glass roof, high efficiency aerodynamic silhouette::3,  \nAudi precision-engineered metallic minimalism, subtle sharp lines::2,  \nBentley luxury craftsmanship with functional aerodynamics::2,  \nPorsche sporty curves minimal::0.2,  \n\nultra realistic, hyper detailed, photorealistic automotive concept render, daylight and soft studio lighting, high fidelity reflections, 8k resolution, engineering concept visualization\n\n\n\n\nhyper futuristic, visionary next-gen EV, photorealistic studio concept render, cinematic lighting, ultra detailed, 8k, sharp focus, high contrast reflections, concept art, innovative automotive design\n\n\n\nno blurry, no lowres, no noisy, no distorted, no oversaturated, no cartoon, no anime, no low quality, no duplicate objects, no broken architecture, no text, no watermark",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}
Input Parameters
mask Type: string
Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
seed Type: integer
Random seed. Set for reproducible generation
image Type: string
Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
model Default: dev
Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps.
width Type: integerRange: 256 - 1440
Width of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
height Type: integerRange: 256 - 1440
Height of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
prompt (required) Type: string
Prompt for generated image. If you include the `trigger_word` used in the training process you are more likely to activate the trained object, style, or concept in the resulting image.
go_fast Type: booleanDefault: false
Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16
extra_lora Type: string
Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
lora_scale Type: numberDefault: 1Range: -1 - 3
Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
megapixels Default: 1
Approximate number of megapixels for generated image
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of outputs to generate
aspect_ratio Default: 1:1
Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode
output_format Default: webp
Format of the output images
guidance_scale Type: numberDefault: 3Range: 0 - 10
Guidance scale for the diffusion process. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5
output_quality Type: integerDefault: 80Range: 0 - 100
Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
prompt_strength Type: numberDefault: 0.8Range: 0 - 1
Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
extra_lora_scale Type: numberDefault: 1Range: -1 - 3
Determines how strongly the extra LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
replicate_weights Type: string
Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
num_inference_steps Type: integerDefault: 28Range: 1 - 50
Number of denoising steps. More steps can give more detailed images, but take longer.
disable_safety_checker Type: booleanDefault: false
Disable safety checker for generated images.
Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs 
free=24471920779264
Downloading weights
2025-09-24T07:28:12Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpsk30x27e/weights url=https://replicate.delivery/xezq/w3rg1uiXZEJaONSqgyeCweeesg4ASm0R17khcep5cdgY7lCrC/trained_model.tar
2025-09-24T07:28:12Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-09-24T07:28:12Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/w3rg1uiXZEJaONSqgyeCweeesg4ASm0R17khcep5cdgY7lCrC/trained_model.tar url=https://replicate.delivery/xezq/w3rg1uiXZEJaONSqgyeCweeesg4ASm0R17khcep5cdgY7lCrC/trained_model.tar
2025-09-24T07:28:12Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/51078ed799b4bf06fc6262ce5ddf6497775ab711ec2481b3c57b720fe468df8f?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250924%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250924T072812Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=4f3f23a40ab5b4ac44ba8c0d70fac3b59c85bc2c6c05b9f8c0874b24114940cb url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/w3rg1uiXZEJaONSqgyeCweeesg4ASm0R17khcep5cdgY7lCrC/trained_model.tar
2025-09-24T07:28:12Z | INFO  | [ Complete ] dest=/tmp/tmpsk30x27e/weights size="172 MB" total_elapsed=0.250s url=https://replicate.delivery/xezq/w3rg1uiXZEJaONSqgyeCweeesg4ASm0R17khcep5cdgY7lCrC/trained_model.tar
Downloaded weights in 0.31s
Loaded LoRAs in 1.31s
Using seed: 54677
Prompt: ultra realistic, hyper detailed, 8k, 16k, ultra high resolution, sharp focus, architectural visualization render, octane render, unreal engine quality
futuristic electric car concept, inspired by Hyundai Ioniq 6,
streamlined aerodynamic body with "curve of steel" design for optimized airflow,
parametric pixel inspired LED headlights and taillights, energy-efficient adaptive illumination,
integrated active cooling vents for battery thermal management, lightweight aluminum and carbon fiber panels,
sleek coupe-like design with aerodynamic underbody, solar roof panels for auxiliary power,
design influences:
Tesla futuristic clean surfaces, smooth minimalist glass roof, high efficiency aerodynamic silhouette::3,
Audi precision-engineered metallic minimalism, subtle sharp lines::2,
Bentley luxury craftsmanship with functional aerodynamics::2,
Porsche sporty curves minimal::0.2,
ultra realistic, hyper detailed, photorealistic automotive concept render, daylight and soft studio lighting, high fidelity reflections, 8k resolution, engineering concept visualization
hyper futuristic, visionary next-gen EV, photorealistic studio concept render, cinematic lighting, ultra detailed, 8k, sharp focus, high contrast reflections, concept art, innovative automotive design
no blurry, no lowres, no noisy, no distorted, no oversaturated, no cartoon, no anime, no low quality, no duplicate objects, no broken architecture, no text, no watermark
[!] txt2img mode
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:07,  3.80it/s]
  7%|▋         | 2/28 [00:00<00:06,  4.30it/s]
 11%|█         | 3/28 [00:00<00:06,  4.06it/s]
 14%|█▍        | 4/28 [00:01<00:06,  3.94it/s]
 18%|█▊        | 5/28 [00:01<00:05,  3.88it/s]
 21%|██▏       | 6/28 [00:01<00:05,  3.85it/s]
 25%|██▌       | 7/28 [00:01<00:05,  3.83it/s]
 29%|██▊       | 8/28 [00:02<00:05,  3.82it/s]
 32%|███▏      | 9/28 [00:02<00:05,  3.80it/s]
 36%|███▌      | 10/28 [00:02<00:04,  3.79it/s]
 39%|███▉      | 11/28 [00:02<00:04,  3.80it/s]
 43%|████▎     | 12/28 [00:03<00:04,  3.79it/s]
 46%|████▋     | 13/28 [00:03<00:03,  3.79it/s]
 50%|█████     | 14/28 [00:03<00:03,  3.79it/s]
 54%|█████▎    | 15/28 [00:03<00:03,  3.79it/s]
 57%|█████▋    | 16/28 [00:04<00:03,  3.79it/s]
 61%|██████    | 17/28 [00:04<00:02,  3.78it/s]
 64%|██████▍   | 18/28 [00:04<00:02,  3.78it/s]
 68%|██████▊   | 19/28 [00:04<00:02,  3.79it/s]
 71%|███████▏  | 20/28 [00:05<00:02,  3.78it/s]
 75%|███████▌  | 21/28 [00:05<00:01,  3.78it/s]
 79%|███████▊  | 22/28 [00:05<00:01,  3.79it/s]
 82%|████████▏ | 23/28 [00:06<00:01,  3.78it/s]
 86%|████████▌ | 24/28 [00:06<00:01,  3.78it/s]
 89%|████████▉ | 25/28 [00:06<00:00,  3.78it/s]
 93%|█████████▎| 26/28 [00:06<00:00,  3.78it/s]
 96%|█████████▋| 27/28 [00:07<00:00,  3.77it/s]
100%|██████████| 28/28 [00:07<00:00,  3.78it/s]
100%|██████████| 28/28 [00:07<00:00,  3.81it/s]
Total safe images: 1 out of 1
Version Details
Version ID
17674c22cfbb06376cffdb6f53f7a4e544a5c21e9f71e645b7d30dd6f79b0255
Version Created
September 24, 2025
Run on Replicate →