criandonegocioia/fotosdavid 🖼️🔢❓📝✓ → 🖼️

▶️ 650 runs 📅 Feb 2026 ⚙️ Cog 0.15.3
lora lora-person text-to-image

About

Example Output

Prompt:

"

Para Fotos (Instagram Style)

A candid smartphone photo of TOK, a handsome man in his early 30s, [DESCRIÇÃO DA ROUPA], standing in [LOCALIZAÇÃO]. Shot on iPhone 15 Pro, natural morning light, vertical aspect ratio, slightly grainy texture, motion blur, casual pose, authentic skin texture with visible pores and slight imperfections, 4k resolution, raw photography

Ambiente de Escritório: TOK sitting at a minimalist desk with a MacBook, soft cinematic office lighting, 85mm lens, blurred background.
Lifestyle/Café: Close-up of TOK holding a coffee cup in a high-end coffee shop, bokeh, morning sun rays hitting the face, high detail.
Outdoor/Urbano: TOK walking in a busy modern street, blurred city traffic in background, shot on 35mm lens, street photography style.

Ou variação sugerida no prompt de envio pelo agent

Para Vídeos (HeyGen/Talking Photo)
Para o HeyGen, a foto inicial precisa ser limpa para que o movimento da boca seja natural.

Prompt Base para Vídeo: Frontal portrait of TOK looking directly at the camera, neutral expression, clean studio lighting, high-end production, plain background, 4k, sharp focus on lips and eyes.

"

Output

Example output

Performance Metrics

8.77s Prediction Time
8.84s Total Time
All Input Parameters 
{
  "model": "dev",
  "width": 854,
  "height": 857,
  "prompt": "Para Fotos (Instagram Style)\n\nA candid smartphone photo of TOK, a handsome man in his early 30s, [DESCRIÇÃO DA ROUPA], standing in [LOCALIZAÇÃO]. Shot on iPhone 15 Pro, natural morning light, vertical aspect ratio, slightly grainy texture, motion blur, casual pose, authentic skin texture with visible pores and slight imperfections, 4k resolution, raw photography\n\nAmbiente de Escritório: TOK sitting at a minimalist desk with a MacBook, soft cinematic office lighting, 85mm lens, blurred background.\nLifestyle/Café: Close-up of TOK holding a coffee cup in a high-end coffee shop, bokeh, morning sun rays hitting the face, high detail.\nOutdoor/Urbano: TOK walking in a busy modern street, blurred city traffic in background, shot on 35mm lens, street photography style.\n\nOu variação sugerida no prompt de envio pelo agent\n\nPara Vídeos (HeyGen/Talking Photo)\nPara o HeyGen, a foto inicial precisa ser limpa para que o movimento da boca seja natural.\n\nPrompt Base para Vídeo: Frontal portrait of TOK looking directly at the camera, neutral expression, clean studio lighting, high-end production, plain background, 4k, sharp focus on lips and eyes.",
  "go_fast": false,
  "lora_scale": 0.9,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "9:16",
  "output_format": "jpg",
  "guidance_scale": 3.4,
  "output_quality": 98,
  "prompt_strength": 0.9,
  "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=22954368684032
Downloading weights
2026-02-19T14:45:57Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmphvry35kd/weights url=https://replicate.delivery/xezq/QgFr5iqDhZ5jFd2eS270xzUjGifXvBHtB9pKEgFrFel86ESsA/trained_model.tar
2026-02-19T14:45:57Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2026-02-19T14:45:57Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/QgFr5iqDhZ5jFd2eS270xzUjGifXvBHtB9pKEgFrFel86ESsA/trained_model.tar url=https://replicate.delivery/xezq/QgFr5iqDhZ5jFd2eS270xzUjGifXvBHtB9pKEgFrFel86ESsA/trained_model.tar
2026-02-19T14:45:57Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric2.cwlota.com/758071c9f5fd69893eaa347901a3353963413c03ff21723a260d72ee02815986?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWYAFKQUBIDDRADP%2F20260219%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20260219T144557Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=9cf88d0fec25521d22bc4fe227ec9f0f4e455dc428aa59fc48a618e9f25e59ac url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/QgFr5iqDhZ5jFd2eS270xzUjGifXvBHtB9pKEgFrFel86ESsA/trained_model.tar
2026-02-19T14:45:58Z | INFO  | [ Complete ] dest=/tmp/tmphvry35kd/weights size="172 MB" total_elapsed=0.240s url=https://replicate.delivery/xezq/QgFr5iqDhZ5jFd2eS270xzUjGifXvBHtB9pKEgFrFel86ESsA/trained_model.tar
Downloaded weights in 0.31s
Loaded LoRAs in 1.29s
Using seed: 47341
Prompt: Para Fotos (Instagram Style)
A candid smartphone photo of TOK, a handsome man in his early 30s, [DESCRIÇÃO DA ROUPA], standing in [LOCALIZAÇÃO]. Shot on iPhone 15 Pro, natural morning light, vertical aspect ratio, slightly grainy texture, motion blur, casual pose, authentic skin texture with visible pores and slight imperfections, 4k resolution, raw photography
Ambiente de Escritório: TOK sitting at a minimalist desk with a MacBook, soft cinematic office lighting, 85mm lens, blurred background.
Lifestyle/Café: Close-up of TOK holding a coffee cup in a high-end coffee shop, bokeh, morning sun rays hitting the face, high detail.
Outdoor/Urbano: TOK walking in a busy modern street, blurred city traffic in background, shot on 35mm lens, street photography style.
Ou variação sugerida no prompt de envio pelo agent
Para Vídeos (HeyGen/Talking Photo)
Para o HeyGen, a foto inicial precisa ser limpa para que o movimento da boca seja natural.
Prompt Base para Vídeo: Frontal portrait of TOK looking directly at the camera, neutral expression, clean studio lighting, high-end production, plain background, 4k, sharp focus on lips and eyes.
[!] txt2img mode
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:07,  3.76it/s]
  7%|▋         | 2/28 [00:00<00:06,  4.19it/s]
 11%|█         | 3/28 [00:00<00:06,  4.03it/s]
 14%|█▍        | 4/28 [00:01<00:06,  3.95it/s]
 18%|█▊        | 5/28 [00:01<00:05,  3.91it/s]
 21%|██▏       | 6/28 [00:01<00:05,  3.88it/s]
 25%|██▌       | 7/28 [00:01<00:05,  3.87it/s]
 29%|██▊       | 8/28 [00:02<00:05,  3.86it/s]
 32%|███▏      | 9/28 [00:02<00:04,  3.85it/s]
 36%|███▌      | 10/28 [00:02<00:04,  3.85it/s]
 39%|███▉      | 11/28 [00:02<00:04,  3.85it/s]
 43%|████▎     | 12/28 [00:03<00:04,  3.85it/s]
 46%|████▋     | 13/28 [00:03<00:03,  3.84it/s]
 50%|█████     | 14/28 [00:03<00:03,  3.84it/s]
 54%|█████▎    | 15/28 [00:03<00:03,  3.84it/s]
 57%|█████▋    | 16/28 [00:04<00:03,  3.84it/s]
 61%|██████    | 17/28 [00:04<00:02,  3.84it/s]
 64%|██████▍   | 18/28 [00:04<00:02,  3.84it/s]
 68%|██████▊   | 19/28 [00:04<00:02,  3.84it/s]
 71%|███████▏  | 20/28 [00:05<00:02,  3.84it/s]
 75%|███████▌  | 21/28 [00:05<00:01,  3.84it/s]
 79%|███████▊  | 22/28 [00:05<00:01,  3.84it/s]
 82%|████████▏ | 23/28 [00:05<00:01,  3.84it/s]
 86%|████████▌ | 24/28 [00:06<00:01,  3.84it/s]
 89%|████████▉ | 25/28 [00:06<00:00,  3.83it/s]
 93%|█████████▎| 26/28 [00:06<00:00,  3.84it/s]
 96%|█████████▋| 27/28 [00:06<00:00,  3.84it/s]
100%|██████████| 28/28 [00:07<00:00,  3.84it/s]
100%|██████████| 28/28 [00:07<00:00,  3.86it/s]
Total safe images: 1 out of 1
Version Details
Version ID
09bd17494266a98f493d3ae0c69aeb05636eb06ddb085768d59e387782ac452b
Version Created
February 21, 2026
Run on Replicate →