topogoogles/nanotopo 🖼️🔢❓📝✓ → 🖼️

▶️ 17 runs 📅 Sep 2025 ⚙️ Cog 0.13.6

image-to-image lora lora-person text-to-image

Performance

11.4sTypical run time

17Total runs

About

This model began from a single selfie. I crafted a unique Flux-LoRA model unlocking an endless creative potential with a whole bunch of new possibilities.

Example Output

Prompt:

"Cinematic editorial portrait of nanotopo as a man in his mid-40s, 2mm salt-and-pepper scruff, tight buzzcut faded-to-zero on the sides, weathered mature skin with fine lines and subtle age spots, intense gaze, dramatic rim lighting, neutral dark gray backdrop, shot on Hasselblad X2D 100C, 85mm f/1.4, shallow depth of field, hyperrealistic, high-contrast cinematic look"

Output

Performance Metrics

11.42s Prediction Time

11.52s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "Cinematic editorial portrait of nanotopo as a man in his mid-40s, 2mm salt-and-pepper scruff, tight buzzcut faded-to-zero on the sides, weathered mature skin with fine lines and subtle age spots, intense gaze, dramatic rim lighting, neutral dark gray backdrop, shot on Hasselblad X2D 100C, 85mm f/1.4, shallow depth of field, hyperrealistic, high-contrast cinematic look",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "16:9",
  "output_format": "png",
  "guidance_scale": 2,
  "output_quality": 100,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 38
}

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=23953236627456
Downloading weights
2026-08-10T12:43:39Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpbubay3s6/weights url=https://replicate.delivery/xezq/EjDaYp7DiqayAJkgX0tGiMpZDtFlZMJqoEV1Qi2LmSmgonWF/flux-lora.tar
2026-08-10T12:43:39Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2026-08-10T12:43:39Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/EjDaYp7DiqayAJkgX0tGiMpZDtFlZMJqoEV1Qi2LmSmgonWF/flux-lora.tar url=https://replicate.delivery/xezq/EjDaYp7DiqayAJkgX0tGiMpZDtFlZMJqoEV1Qi2LmSmgonWF/flux-lora.tar
2026-08-10T12:43:39Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric2.cwlota.com/96ac546cfffecae5376871f29929a6559bd5ff584e172df7291bc8de678c219d?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWVOGIYODJJPRECK%2F20260810%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20260810T124339Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=230740de89f0222ffef49a572968e023d0c6d2ccd3bebb0dfa5aafb14653e6bd url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/EjDaYp7DiqayAJkgX0tGiMpZDtFlZMJqoEV1Qi2LmSmgonWF/flux-lora.tar
2026-08-10T12:43:40Z | INFO  | [ Complete ] dest=/tmp/tmpbubay3s6/weights size="172 MB" total_elapsed=0.500s url=https://replicate.delivery/xezq/EjDaYp7DiqayAJkgX0tGiMpZDtFlZMJqoEV1Qi2LmSmgonWF/flux-lora.tar
Downloaded weights in 0.56s
Loaded LoRAs in 1.09s
Using seed: 34811
Prompt: Cinematic editorial portrait of nanotopo as a man in his mid-40s, 2mm salt-and-pepper scruff, tight buzzcut faded-to-zero on the sides, weathered mature skin with fine lines and subtle age spots, intense gaze, dramatic rim lighting, neutral dark gray backdrop, shot on Hasselblad X2D 100C, 85mm f/1.4, shallow depth of field, hyperrealistic, high-contrast cinematic look
[!] txt2img mode
  0%|          | 0/38 [00:00<?, ?it/s]
  3%|▎         | 1/38 [00:00<00:09,  3.86it/s]
  5%|▌         | 2/38 [00:00<00:08,  4.37it/s]
  8%|▊         | 3/38 [00:00<00:08,  4.13it/s]
 11%|█         | 4/38 [00:00<00:08,  3.99it/s]
 13%|█▎        | 5/38 [00:01<00:08,  3.93it/s]
 16%|█▌        | 6/38 [00:01<00:08,  3.90it/s]
 18%|█▊        | 7/38 [00:01<00:07,  3.88it/s]
 21%|██        | 8/38 [00:02<00:07,  3.87it/s]
 24%|██▎       | 9/38 [00:02<00:07,  3.86it/s]
 26%|██▋       | 10/38 [00:02<00:07,  3.85it/s]
 29%|██▉       | 11/38 [00:02<00:07,  3.85it/s]
 32%|███▏      | 12/38 [00:03<00:06,  3.85it/s]
 34%|███▍      | 13/38 [00:03<00:06,  3.84it/s]
 37%|███▋      | 14/38 [00:03<00:06,  3.84it/s]
 39%|███▉      | 15/38 [00:03<00:05,  3.84it/s]
 42%|████▏     | 16/38 [00:04<00:05,  3.84it/s]
 45%|████▍     | 17/38 [00:04<00:05,  3.84it/s]
 47%|████▋     | 18/38 [00:04<00:05,  3.84it/s]
 50%|█████     | 19/38 [00:04<00:04,  3.84it/s]
 53%|█████▎    | 20/38 [00:05<00:04,  3.84it/s]
 55%|█████▌    | 21/38 [00:05<00:04,  3.84it/s]
 58%|█████▊    | 22/38 [00:05<00:04,  3.84it/s]
 61%|██████    | 23/38 [00:05<00:03,  3.84it/s]
 63%|██████▎   | 24/38 [00:06<00:03,  3.84it/s]
 66%|██████▌   | 25/38 [00:06<00:03,  3.85it/s]
 68%|██████▊   | 26/38 [00:06<00:03,  3.85it/s]
 71%|███████   | 27/38 [00:06<00:02,  3.85it/s]
 74%|███████▎  | 28/38 [00:07<00:02,  3.85it/s]
 76%|███████▋  | 29/38 [00:07<00:02,  3.85it/s]
 79%|███████▉  | 30/38 [00:07<00:02,  3.85it/s]
 82%|████████▏ | 31/38 [00:08<00:01,  3.84it/s]
 84%|████████▍ | 32/38 [00:08<00:01,  3.84it/s]
 87%|████████▋ | 33/38 [00:08<00:01,  3.84it/s]
 89%|████████▉ | 34/38 [00:08<00:01,  3.85it/s]
 92%|█████████▏| 35/38 [00:09<00:00,  3.85it/s]
 95%|█████████▍| 36/38 [00:09<00:00,  3.86it/s]
 97%|█████████▋| 37/38 [00:09<00:00,  3.85it/s]
100%|██████████| 38/38 [00:09<00:00,  3.86it/s]
100%|██████████| 38/38 [00:09<00:00,  3.86it/s]
Total safe images: 1 out of 1

Version Details

Version ID: b4e3820afb64efe29384de32814b3902ca7d69c0969e5c6d7ee1e74da4ffd3ed
Version Created: September 30, 2025

Run on Replicate →