anon987654321/ra2 🔢📝✓❓🖼️ → 🖼️

▶️ 32 runs 📅 Sep 2025 ⚙️ Cog 0.16.2

image-lora-training text-to-image

About

Example Output

Prompt:

"norwegian woman RA2 as prime minister of norway, election victory"

Output

Performance Metrics

43.04s Prediction Time

43.06s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/Nmcp5il1zNAbK5legwYDb9H39B6mWtKKs1dpukpfBdaiI0rO/image.png",
  "model": "dev",
  "prompt": "norwegian woman RA2 as prime minister of norway, election victory",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 2.35,
  "output_quality": 100,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 42
}

Input Parameters

seed Type: integer: Set a seed for reproducibility. Random by default.
width Type: integerRange: 512 - 2048: Custom width in pixels. Provide both width and height for custom dimensions (overrides aspect_ratio/image_size).
height Type: integerRange: 512 - 2048: Custom height in pixels. Provide both width and height for custom dimensions (overrides aspect_ratio/image_size).
prompt (required) Type: string: The main prompt for image generation
go_fast Type: booleanDefault: false: Use LCM-LoRA to accelerate image generation (trades quality for 8x speed)
guidance Type: numberDefault: 4Range: 0 - 10: Guidance scale for image generation. Defaults to 1 if go_fast, else 3.5.
image_size Default: optimize_for_quality: Image size preset (quality = larger, speed = faster). Ignored if width and height are both provided.
lora_scale Type: numberDefault: 1Range: 0 - 3: Scale for LoRA weights (0 = base model, 1 = full LoRA)
aspect_ratio Default: 16:9: Aspect ratio for the generated image. Ignored if width and height are both provided.
output_format Default: webp: Format of the output images
enhance_prompt Type: booleanDefault: false: Automatically enhance the prompt for better image generation
output_quality Type: integerDefault: 80Range: 0 - 100: Quality when saving images (0-100, higher is better, 100 = lossless)
negative_prompt Type: stringDefault:: Things you do not want to see in your image
replicate_weights Type: string: Path to LoRA weights file. Leave blank to use base model.
num_inference_steps Type: integerDefault: 50Range: 0 - 50: Number of denoising steps. More steps = higher quality. Defaults to 4 if go_fast, else 28.

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Loaded LoRAs in 0.49s
Using seed: 63111
Prompt: norwegian woman RA2 as prime minister of norway, election victory
Input image size: 2449x1378
[!] Resizing input image from 2449x1378 to 1440x816
[!] img2img mode
  0%|          | 0/34 [00:00<?, ?it/s]
  3%|▎         | 1/34 [00:00<00:28,  1.15it/s]
  6%|▌         | 2/34 [00:01<00:31,  1.01it/s]
  9%|▉         | 3/34 [00:03<00:32,  1.03s/it]
 12%|█▏        | 4/34 [00:04<00:31,  1.05s/it]
 15%|█▍        | 5/34 [00:05<00:30,  1.06s/it]
 18%|█▊        | 6/34 [00:06<00:29,  1.07s/it]
 21%|██        | 7/34 [00:07<00:29,  1.07s/it]
 24%|██▎       | 8/34 [00:08<00:28,  1.08s/it]
 26%|██▋       | 9/34 [00:09<00:27,  1.08s/it]
 29%|██▉       | 10/34 [00:10<00:25,  1.08s/it]
 32%|███▏      | 11/34 [00:11<00:24,  1.08s/it]
 35%|███▌      | 12/34 [00:12<00:23,  1.08s/it]
 38%|███▊      | 13/34 [00:13<00:22,  1.08s/it]
 41%|████      | 14/34 [00:14<00:21,  1.09s/it]
 44%|████▍     | 15/34 [00:16<00:20,  1.09s/it]
 47%|████▋     | 16/34 [00:17<00:19,  1.09s/it]
 50%|█████     | 17/34 [00:18<00:18,  1.09s/it]
 53%|█████▎    | 18/34 [00:19<00:17,  1.09s/it]
 56%|█████▌    | 19/34 [00:20<00:16,  1.09s/it]
 59%|█████▉    | 20/34 [00:21<00:15,  1.09s/it]
 62%|██████▏   | 21/34 [00:22<00:14,  1.09s/it]
 65%|██████▍   | 22/34 [00:23<00:13,  1.09s/it]
 68%|██████▊   | 23/34 [00:24<00:11,  1.09s/it]
 71%|███████   | 24/34 [00:25<00:10,  1.09s/it]
 74%|███████▎  | 25/34 [00:26<00:09,  1.09s/it]
 76%|███████▋  | 26/34 [00:28<00:08,  1.09s/it]
 79%|███████▉  | 27/34 [00:29<00:07,  1.09s/it]
 82%|████████▏ | 28/34 [00:30<00:06,  1.09s/it]
 85%|████████▌ | 29/34 [00:31<00:05,  1.09s/it]
 88%|████████▊ | 30/34 [00:32<00:04,  1.09s/it]
 91%|█████████ | 31/34 [00:33<00:03,  1.09s/it]
 94%|█████████▍| 32/34 [00:34<00:02,  1.09s/it]
 97%|█████████▋| 33/34 [00:35<00:01,  1.09s/it]
100%|██████████| 34/34 [00:36<00:00,  1.09s/it]
100%|██████████| 34/34 [00:36<00:00,  1.08s/it]
Total safe images: 4 out of 4

Version Details

Version ID: 983967a65f090aa0ced0d227e809ae57b29f2d1d1ae4f84a17dd25176e0d313d
Version Created: September 27, 2025

Run on Replicate →