jjcall/admm 🖼️🔢❓📝✓ → 🖼️

▶️ 17 runs 📅 May 2025 ⚙️ Cog 0.13.6

About

Example Output

Prompt:

"A young woman laughing with her hands mid-gesture, standing in a sunlit urban alleyway. She wears a sleeveless black top and jeans. Shot in TOK style — Robert Frank-inspired black-and-white, strong contrast, unposed, expressive face clearly visible."

Output

Performance Metrics

17.31s Prediction Time

17.40s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "A young woman laughing with her hands mid-gesture, standing in a sunlit urban alleyway. She wears a sleeveless black top and jeans. Shot in TOK style — Robert Frank-inspired black-and-white, strong contrast, unposed, expressive face clearly visible.",
  "go_fast": false,
  "lora_scale": 1.28,
  "megapixels": "1",
  "num_outputs": 2,
  "aspect_ratio": "1:1",
  "output_format": "jpg",
  "guidance_scale": 2.53,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 32
}

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=27879409262592
Downloading weights
2025-05-31T23:32:06Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpxx0zjr2v/weights url=https://replicate.delivery/xezq/rfHEvxZvY1RCKyLFVwh8fgkBGwNM8Ak2jeeR7pTg5jyVKQJTB/flux-lora.tar
2025-05-31T23:32:06Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-05-31T23:32:06Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/rfHEvxZvY1RCKyLFVwh8fgkBGwNM8Ak2jeeR7pTg5jyVKQJTB/flux-lora.tar url=https://replicate.delivery/xezq/rfHEvxZvY1RCKyLFVwh8fgkBGwNM8Ak2jeeR7pTg5jyVKQJTB/flux-lora.tar
2025-05-31T23:32:06Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/d5f351c215bfbf7485453817c4dba790ec4862a9d90157357cbc97c40bf54110?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250531%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250531T233206Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=86a76c5e8fd4b42405d07f665696b44a533d60668ca1bcbbcce1f9ecc10a7b74 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/rfHEvxZvY1RCKyLFVwh8fgkBGwNM8Ak2jeeR7pTg5jyVKQJTB/flux-lora.tar
2025-05-31T23:32:07Z | INFO  | [ Complete ] dest=/tmp/tmpxx0zjr2v/weights size="172 MB" total_elapsed=0.268s url=https://replicate.delivery/xezq/rfHEvxZvY1RCKyLFVwh8fgkBGwNM8Ak2jeeR7pTg5jyVKQJTB/flux-lora.tar
Downloaded weights in 0.33s
Loaded LoRAs in 0.88s
Using seed: 43866
Prompt: A young woman laughing with her hands mid-gesture, standing in a sunlit urban alleyway. She wears a sleeveless black top and jeans. Shot in TOK style — Robert Frank-inspired black-and-white, strong contrast, unposed, expressive face clearly visible.
[!] txt2img mode
  0%|          | 0/32 [00:00<?, ?it/s]
  3%|▎         | 1/32 [00:00<00:15,  1.97it/s]
  6%|▋         | 2/32 [00:00<00:13,  2.20it/s]
  9%|▉         | 3/32 [00:01<00:13,  2.10it/s]
 12%|█▎        | 4/32 [00:01<00:13,  2.05it/s]
 16%|█▌        | 5/32 [00:02<00:13,  2.03it/s]
 19%|█▉        | 6/32 [00:02<00:12,  2.01it/s]
 22%|██▏       | 7/32 [00:03<00:12,  2.00it/s]
 25%|██▌       | 8/32 [00:03<00:12,  2.00it/s]
 28%|██▊       | 9/32 [00:04<00:11,  1.99it/s]
 31%|███▏      | 10/32 [00:04<00:11,  1.99it/s]
 34%|███▍      | 11/32 [00:05<00:10,  1.99it/s]
 38%|███▊      | 12/32 [00:05<00:10,  1.99it/s]
 41%|████      | 13/32 [00:06<00:09,  1.99it/s]
 44%|████▍     | 14/32 [00:06<00:09,  1.98it/s]
 47%|████▋     | 15/32 [00:07<00:08,  1.98it/s]
 50%|█████     | 16/32 [00:07<00:08,  1.99it/s]
 53%|█████▎    | 17/32 [00:08<00:07,  1.99it/s]
 56%|█████▋    | 18/32 [00:08<00:07,  1.99it/s]
 59%|█████▉    | 19/32 [00:09<00:06,  1.99it/s]
 62%|██████▎   | 20/32 [00:09<00:06,  1.99it/s]
 66%|██████▌   | 21/32 [00:10<00:05,  1.99it/s]
 69%|██████▉   | 22/32 [00:10<00:05,  1.99it/s]
 72%|███████▏  | 23/32 [00:11<00:04,  1.99it/s]
 75%|███████▌  | 24/32 [00:11<00:04,  1.99it/s]
 78%|███████▊  | 25/32 [00:12<00:03,  1.99it/s]
 81%|████████▏ | 26/32 [00:13<00:03,  1.99it/s]
 84%|████████▍ | 27/32 [00:13<00:02,  1.99it/s]
 88%|████████▊ | 28/32 [00:14<00:02,  1.99it/s]
 91%|█████████ | 29/32 [00:14<00:01,  1.99it/s]
 94%|█████████▍| 30/32 [00:15<00:01,  1.99it/s]
 97%|█████████▋| 31/32 [00:15<00:00,  1.99it/s]
100%|██████████| 32/32 [00:16<00:00,  1.99it/s]
100%|██████████| 32/32 [00:16<00:00,  2.00it/s]
Total safe images: 2 out of 2

Version Details

Version ID: 5505f23ce5471dd6217d180ce0285edb3ad0201fcbe119ad174ae61f8bb6e4b8
Version Created: May 31, 2025

Run on Replicate →