topogoogles/nanotopo 🖼️🔢❓📝✓ → 🖼️

▶️ 11 runs 📅 Sep 2025 ⚙️ Cog 0.13.6

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:

"nanotopo posing with an honest facial expression of satisfaction"

Output

Performance Metrics

28.35s Prediction Time

28.36s Total Time

All Input Parameters

{
  "mask": "https://replicate.delivery/pbxt/NozsYTt49CN9O5UxF0dppRqXuVqeMdOBFz8KY936PI50NzxZ/aa8c32ef-357f-460d-b09f-232f85f385c1-face.png",
  "image": "https://replicate.delivery/pbxt/NozsYkt4okMbAPGa7Znm6BGv42eYiN3FIIIRjhh0r5EhDgG8/aa8c32ef-357f-460d-b09f-232f85f385c1.jpeg",
  "model": "schnell",
  "prompt": "nanotopo posing with an honest facial expression of satisfaction",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "16:9",
  "output_format": "png",
  "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=26223360135168
Downloading weights
2025-10-03T18:33:59Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp6dobaht2/weights url=https://replicate.delivery/xezq/EjDaYp7DiqayAJkgX0tGiMpZDtFlZMJqoEV1Qi2LmSmgonWF/flux-lora.tar
2025-10-03T18:33:59Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-10-03T18:33:59Z | 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
2025-10-03T18:33:59Z | INFO  | [ Redirect ] redirect_url=https://replicate.delivery/xezq/EjDaYp7DiqayAJkgX0tGiMpZDtFlZMJqoEV1Qi2LmSmgonWF/flux-lora.tar url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/EjDaYp7DiqayAJkgX0tGiMpZDtFlZMJqoEV1Qi2LmSmgonWF/flux-lora.tar
2025-10-03T18:34:01Z | INFO  | [ Complete ] dest=/tmp/tmp6dobaht2/weights size="172 MB" total_elapsed=1.286s url=https://replicate.delivery/xezq/EjDaYp7DiqayAJkgX0tGiMpZDtFlZMJqoEV1Qi2LmSmgonWF/flux-lora.tar
Downloaded weights in 1.35s
Loaded LoRAs in 1.83s
Using seed: 21814
Prompt: nanotopo posing with an honest facial expression of satisfaction
Input image size: 1408x768
[!] Resizing input image from 1408x768 to 1408x768
[!] inpaint mode
  0%|          | 0/23 [00:00<?, ?it/s]
  4%|▍         | 1/23 [00:00<00:21,  1.01it/s]
  9%|▊         | 2/23 [00:01<00:20,  1.04it/s]
 13%|█▎        | 3/23 [00:02<00:18,  1.05it/s]
 17%|█▋        | 4/23 [00:03<00:17,  1.06it/s]
 22%|██▏       | 5/23 [00:04<00:16,  1.06it/s]
 26%|██▌       | 6/23 [00:05<00:15,  1.06it/s]
 30%|███       | 7/23 [00:06<00:15,  1.06it/s]
 35%|███▍      | 8/23 [00:07<00:14,  1.06it/s]
 39%|███▉      | 9/23 [00:08<00:13,  1.07it/s]
 43%|████▎     | 10/23 [00:09<00:12,  1.07it/s]
 48%|████▊     | 11/23 [00:10<00:11,  1.07it/s]
 52%|█████▏    | 12/23 [00:11<00:10,  1.07it/s]
 57%|█████▋    | 13/23 [00:12<00:09,  1.06it/s]
 61%|██████    | 14/23 [00:13<00:08,  1.06it/s]
 65%|██████▌   | 15/23 [00:14<00:07,  1.06it/s]
 70%|██████▉   | 16/23 [00:15<00:06,  1.06it/s]
 74%|███████▍  | 17/23 [00:16<00:05,  1.06it/s]
 78%|███████▊  | 18/23 [00:16<00:04,  1.06it/s]
 83%|████████▎ | 19/23 [00:17<00:03,  1.06it/s]
 87%|████████▋ | 20/23 [00:18<00:02,  1.06it/s]
 91%|█████████▏| 21/23 [00:19<00:01,  1.06it/s]
 96%|█████████▌| 22/23 [00:20<00:00,  1.06it/s]
100%|██████████| 23/23 [00:21<00:00,  1.13it/s]
100%|██████████| 23/23 [00:21<00:00,  1.07it/s]
Total safe images: 4 out of 4

Version Details

Version ID: b4e3820afb64efe29384de32814b3902ca7d69c0969e5c6d7ee1e74da4ffd3ed
Version Created: September 30, 2025

Run on Replicate →