franfernandez93/generador_imagen_ia 🖼️🔢❓📝✓ → 🖼️

▶️ 194 runs 📅 Feb 2025 ⚙️ Cog 0.13.7
lora lora-person text-to-image

About

Example Output

Prompt:

"

The image features a stylized and strong character named TOK frfer93, designed in a minimalist and modern style. He is wearing a tech-inspired T-shirt or something with a subtle geeky touch. TOK frfer93 is holding a prediction board displaying a price forecast for Airbnb rentals, with numbers and trend lines indicating price variations. The text on the board says "Airbnb Price Prediction" in a clear, professional font.

The background is sleek and modern, using a combination of technology-themed colors like shades of blue, black, and white, with some vibrant accents to maintain visual appeal. Subtle references to programming and data science can be included in the background, such as blurred lines of code, small icons related to machine learning, or Airbnb-related symbols.

The overall design maintains a professional and trustworthy look, making it ideal for a GitHub repository focused on predicting Airbnb prices using data-driven models.

Let me know if you need any refinements!

.

"

Output

Example outputExample outputExample outputExample output

Performance Metrics

31.66s Prediction Time
32.09s Total Time
All Input Parameters 
{
  "model": "dev",
  "width": 741,
  "height": 630,
  "prompt": "The image features a stylized and strong character named TOK frfer93, designed in a minimalist and modern style. He is wearing a tech-inspired T-shirt or something with a subtle geeky touch. TOK frfer93 is holding a prediction board displaying a price forecast for Airbnb rentals, with numbers and trend lines indicating price variations. The text on the board says \"Airbnb Price Prediction\" in a clear, professional font.\n\nThe background is sleek and modern, using a combination of technology-themed colors like shades of blue, black, and white, with some vibrant accents to maintain visual appeal. Subtle references to programming and data science can be included in the background, such as blurred lines of code, small icons related to machine learning, or Airbnb-related symbols.\n\nThe overall design maintains a professional and trustworthy look, making it ideal for a GitHub repository focused on predicting Airbnb prices using data-driven models.\n\nLet me know if you need any refinements!\n\n\n\n\n\n\n\n\n\n\n.\n\n\n\n\n\n\n\n\n\n",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.88,
  "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=5725083320320
Downloading weights
2025-03-02T02:45:38Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp50ivl2_u/weights url=https://replicate.delivery/yhqm/IqO4o6CQNOrbKJEFi6lb0lXYLrcxuS21knLOsxCIhmHMlCFF/trained_model.tar
2025-03-02T02:45:42Z | INFO  | [ Complete ] dest=/tmp/tmp50ivl2_u/weights size="172 MB" total_elapsed=4.283s url=https://replicate.delivery/yhqm/IqO4o6CQNOrbKJEFi6lb0lXYLrcxuS21knLOsxCIhmHMlCFF/trained_model.tar
Downloaded weights in 4.31s
Loaded LoRAs in 4.86s
Using seed: 54439
Prompt: The image features a stylized and strong character named TOK frfer93, designed in a minimalist and modern style. He is wearing a tech-inspired T-shirt or something with a subtle geeky touch. TOK frfer93 is holding a prediction board displaying a price forecast for Airbnb rentals, with numbers and trend lines indicating price variations. The text on the board says "Airbnb Price Prediction" in a clear, professional font.
The background is sleek and modern, using a combination of technology-themed colors like shades of blue, black, and white, with some vibrant accents to maintain visual appeal. Subtle references to programming and data science can be included in the background, such as blurred lines of code, small icons related to machine learning, or Airbnb-related symbols.
The overall design maintains a professional and trustworthy look, making it ideal for a GitHub repository focused on predicting Airbnb prices using data-driven models.
Let me know if you need any refinements!
.
[!] txt2img mode
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:24,  1.09it/s]
  7%|▋         | 2/28 [00:01<00:21,  1.22it/s]
 11%|█         | 3/28 [00:02<00:21,  1.15it/s]
 14%|█▍        | 4/28 [00:03<00:21,  1.12it/s]
 18%|█▊        | 5/28 [00:04<00:20,  1.11it/s]
 21%|██▏       | 6/28 [00:05<00:20,  1.10it/s]
 25%|██▌       | 7/28 [00:06<00:19,  1.09it/s]
 29%|██▊       | 8/28 [00:07<00:18,  1.09it/s]
 32%|███▏      | 9/28 [00:08<00:17,  1.08it/s]
 36%|███▌      | 10/28 [00:09<00:16,  1.08it/s]
 39%|███▉      | 11/28 [00:10<00:15,  1.08it/s]
 43%|████▎     | 12/28 [00:10<00:14,  1.08it/s]
 46%|████▋     | 13/28 [00:11<00:13,  1.08it/s]
 50%|█████     | 14/28 [00:12<00:12,  1.08it/s]
 54%|█████▎    | 15/28 [00:13<00:12,  1.08it/s]
 57%|█████▋    | 16/28 [00:14<00:11,  1.08it/s]
 61%|██████    | 17/28 [00:15<00:10,  1.08it/s]
 64%|██████▍   | 18/28 [00:16<00:09,  1.08it/s]
 68%|██████▊   | 19/28 [00:17<00:08,  1.08it/s]
 71%|███████▏  | 20/28 [00:18<00:07,  1.08it/s]
 75%|███████▌  | 21/28 [00:19<00:06,  1.08it/s]
 79%|███████▊  | 22/28 [00:20<00:05,  1.08it/s]
 82%|████████▏ | 23/28 [00:21<00:04,  1.08it/s]
 86%|████████▌ | 24/28 [00:22<00:03,  1.08it/s]
 89%|████████▉ | 25/28 [00:23<00:02,  1.08it/s]
 93%|█████████▎| 26/28 [00:23<00:01,  1.08it/s]
 96%|█████████▋| 27/28 [00:24<00:00,  1.08it/s]
100%|██████████| 28/28 [00:25<00:00,  1.08it/s]
100%|██████████| 28/28 [00:25<00:00,  1.09it/s]
Total safe images: 4 out of 4
Version Details
Version ID
65691a43120f1bc7ce4adc8ab07fe62e6c458d0ed6b3e3822dbe91b0e33a1387
Version Created
March 1, 2025
Run on Replicate →