vyvo/ale-dev-01 🖼️🔢❓📝✓ → 🖼️

▶️ 25 runs 📅 Sep 2025 ⚙️ Cog 0.13.6

About

Example Output

Prompt:

"Candid Instagram-style photo of ALE in Paris, smiling casually with the Eiffel Tower in the background. The shot looks organic and improvised, as if taken by a real person on their phone. Natural daylight, slightly off-center framing, authentic tourist vibe, and unposed expression for a genuine social media post look."

Output

Performance Metrics

51.02s Prediction Time

51.05s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "Candid Instagram-style photo of ALE in Paris, smiling casually with the Eiffel Tower in the background. The shot looks organic and improvised, as if taken by a real person on their phone. Natural daylight, slightly off-center framing, authentic tourist vibe, and unposed expression for a genuine social media post look.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 2,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 50
}

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=22374940409856
Downloading weights
2025-09-07T23:08:39Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp20a1n9q7/weights url=https://replicate.delivery/xezq/lL2BN4Yic5JzAlrqPxLj7F1DpLL5e5BuT1oVHgsPPPVC3dpKA/flux-lora.tar
2025-09-07T23:08:39Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-09-07T23:08:39Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/lL2BN4Yic5JzAlrqPxLj7F1DpLL5e5BuT1oVHgsPPPVC3dpKA/flux-lora.tar url=https://replicate.delivery/xezq/lL2BN4Yic5JzAlrqPxLj7F1DpLL5e5BuT1oVHgsPPPVC3dpKA/flux-lora.tar
2025-09-07T23:08:39Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/47d259ff03e7fd2282583b5e46811e95633d9da6d62b7e0686149584f0b39c9d?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250907%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250907T230839Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=fb0fc881a4e313fe4ae9dda8c6b4aab629359c71fa48a1e1583a61d5e40a4a45 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/lL2BN4Yic5JzAlrqPxLj7F1DpLL5e5BuT1oVHgsPPPVC3dpKA/flux-lora.tar
2025-09-07T23:08:39Z | INFO  | [ Complete ] dest=/tmp/tmp20a1n9q7/weights size="172 MB" total_elapsed=0.242s url=https://replicate.delivery/xezq/lL2BN4Yic5JzAlrqPxLj7F1DpLL5e5BuT1oVHgsPPPVC3dpKA/flux-lora.tar
Downloaded weights in 0.30s
Loaded LoRAs in 1.26s
Using seed: 41315
Prompt: Candid Instagram-style photo of ALE in Paris, smiling casually with the Eiffel Tower in the background. The shot looks organic and improvised, as if taken by a real person on their phone. Natural daylight, slightly off-center framing, authentic tourist vibe, and unposed expression for a genuine social media post look.
[!] txt2img mode
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:47,  1.03it/s]
  4%|▍         | 2/50 [00:01<00:41,  1.16it/s]
  6%|▌         | 3/50 [00:02<00:43,  1.09it/s]
  8%|▊         | 4/50 [00:03<00:43,  1.06it/s]
 10%|█         | 5/50 [00:04<00:43,  1.05it/s]
 12%|█▏        | 6/50 [00:05<00:42,  1.04it/s]
 14%|█▍        | 7/50 [00:06<00:41,  1.03it/s]
 16%|█▌        | 8/50 [00:07<00:40,  1.03it/s]
 18%|█▊        | 9/50 [00:08<00:39,  1.03it/s]
 20%|██        | 10/50 [00:09<00:39,  1.02it/s]
 22%|██▏       | 11/50 [00:10<00:38,  1.02it/s]
 24%|██▍       | 12/50 [00:11<00:37,  1.02it/s]
 26%|██▌       | 13/50 [00:12<00:36,  1.02it/s]
 28%|██▊       | 14/50 [00:13<00:35,  1.02it/s]
 30%|███       | 15/50 [00:14<00:34,  1.02it/s]
 32%|███▏      | 16/50 [00:15<00:33,  1.02it/s]
 34%|███▍      | 17/50 [00:16<00:32,  1.02it/s]
 36%|███▌      | 18/50 [00:17<00:31,  1.02it/s]
 38%|███▊      | 19/50 [00:18<00:30,  1.02it/s]
 40%|████      | 20/50 [00:19<00:29,  1.02it/s]
 42%|████▏     | 21/50 [00:20<00:28,  1.02it/s]
 44%|████▍     | 22/50 [00:21<00:27,  1.02it/s]
 46%|████▌     | 23/50 [00:22<00:26,  1.02it/s]
 48%|████▊     | 24/50 [00:23<00:25,  1.02it/s]
 50%|█████     | 25/50 [00:24<00:24,  1.02it/s]
 52%|█████▏    | 26/50 [00:25<00:23,  1.02it/s]
 54%|█████▍    | 27/50 [00:26<00:22,  1.02it/s]
 56%|█████▌    | 28/50 [00:27<00:21,  1.02it/s]
 58%|█████▊    | 29/50 [00:28<00:20,  1.02it/s]
 60%|██████    | 30/50 [00:29<00:19,  1.02it/s]
 62%|██████▏   | 31/50 [00:30<00:18,  1.02it/s]
 64%|██████▍   | 32/50 [00:31<00:17,  1.02it/s]
 66%|██████▌   | 33/50 [00:32<00:16,  1.02it/s]
 68%|██████▊   | 34/50 [00:33<00:15,  1.02it/s]
 70%|███████   | 35/50 [00:34<00:14,  1.02it/s]
 72%|███████▏  | 36/50 [00:35<00:13,  1.02it/s]
 74%|███████▍  | 37/50 [00:36<00:12,  1.02it/s]
 76%|███████▌  | 38/50 [00:37<00:11,  1.02it/s]
 78%|███████▊  | 39/50 [00:38<00:10,  1.02it/s]
 80%|████████  | 40/50 [00:38<00:09,  1.02it/s]
 82%|████████▏ | 41/50 [00:39<00:08,  1.02it/s]
 84%|████████▍ | 42/50 [00:40<00:07,  1.02it/s]
 86%|████████▌ | 43/50 [00:41<00:06,  1.02it/s]
 88%|████████▊ | 44/50 [00:42<00:05,  1.02it/s]
 90%|█████████ | 45/50 [00:43<00:04,  1.02it/s]
 92%|█████████▏| 46/50 [00:44<00:03,  1.02it/s]
 94%|█████████▍| 47/50 [00:45<00:02,  1.02it/s]
 96%|█████████▌| 48/50 [00:46<00:01,  1.02it/s]
 98%|█████████▊| 49/50 [00:47<00:00,  1.02it/s]
100%|██████████| 50/50 [00:48<00:00,  1.02it/s]
100%|██████████| 50/50 [00:48<00:00,  1.02it/s]
Total safe images: 4 out of 4

Version Details

Version ID: accef7a94f938f6151f5bc965f4575a8b6c0c32ba375e9d738576fbd703ecc97
Version Created: September 7, 2025

Run on Replicate →