huguitto/claseflix-ia-1-07 🖼️🔢❓📝✓ → 🖼️

▶️ 8 runs 📅 Jul 2025 ⚙️ Cog 0.13.6

About

Example Output

Prompt:

"A friendly man claseflix-ia-1-07 with short hair and a trimmed beard, wearing glasses and a light beige sweater. He is smiling softly, resting his hands under his chin. Background is a digital green grid with glowing financial elements, futuristic style. High-resolution, well-lit, natural expression."

Output

Performance Metrics

34.23s Prediction Time

34.35s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "A friendly  man claseflix-ia-1-07 with short hair and a trimmed beard, wearing glasses and a light beige sweater. He is smiling softly, resting his hands under his chin. Background is a digital green grid with glowing financial elements, futuristic style. High-resolution, well-lit, natural expression.\n",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 3,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 2.9,
  "output_quality": 91,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 44
}

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=25634738290688
Downloading weights
2025-07-01T22:02:18Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp_b6l5d2t/weights url=https://replicate.delivery/xezq/X84CqNmhxrouOVKeoEEPS0RZXU7YG3LNhh7NZ6BtxYkL2NeUA/flux-lora.tar
2025-07-01T22:02:18Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-07-01T22:02:18Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/X84CqNmhxrouOVKeoEEPS0RZXU7YG3LNhh7NZ6BtxYkL2NeUA/flux-lora.tar url=https://replicate.delivery/xezq/X84CqNmhxrouOVKeoEEPS0RZXU7YG3LNhh7NZ6BtxYkL2NeUA/flux-lora.tar
2025-07-01T22:02:18Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/9b30913b6d9466ca224c7433b866d3e72a95a10b652c0c7d43ab4ed8ee287030?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250701%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250701T220218Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=d29b08a46c03086874ccf5ead044153851ea2e88f5fa6c3a1c14f60f0246b349 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/X84CqNmhxrouOVKeoEEPS0RZXU7YG3LNhh7NZ6BtxYkL2NeUA/flux-lora.tar
2025-07-01T22:02:19Z | INFO  | [ Complete ] dest=/tmp/tmp_b6l5d2t/weights size="172 MB" total_elapsed=0.401s url=https://replicate.delivery/xezq/X84CqNmhxrouOVKeoEEPS0RZXU7YG3LNhh7NZ6BtxYkL2NeUA/flux-lora.tar
Downloaded weights in 0.46s
Loaded LoRAs in 0.99s
Using seed: 17444
Prompt: A friendly  man claseflix-ia-1-07 with short hair and a trimmed beard, wearing glasses and a light beige sweater. He is smiling softly, resting his hands under his chin. Background is a digital green grid with glowing financial elements, futuristic style. High-resolution, well-lit, natural expression.
[!] txt2img mode
  0%|          | 0/44 [00:00<?, ?it/s]
  2%|▏         | 1/44 [00:00<00:31,  1.37it/s]
  5%|▍         | 2/44 [00:01<00:27,  1.54it/s]
  7%|▋         | 3/44 [00:02<00:28,  1.45it/s]
  9%|▉         | 4/44 [00:02<00:28,  1.41it/s]
 11%|█▏        | 5/44 [00:03<00:28,  1.39it/s]
 14%|█▎        | 6/44 [00:04<00:27,  1.38it/s]
 16%|█▌        | 7/44 [00:05<00:27,  1.37it/s]
 18%|█▊        | 8/44 [00:05<00:26,  1.36it/s]
 20%|██        | 9/44 [00:06<00:25,  1.36it/s]
 23%|██▎       | 10/44 [00:07<00:25,  1.36it/s]
 25%|██▌       | 11/44 [00:07<00:24,  1.35it/s]
 27%|██▋       | 12/44 [00:08<00:23,  1.35it/s]
 30%|██▉       | 13/44 [00:09<00:22,  1.35it/s]
 32%|███▏      | 14/44 [00:10<00:22,  1.35it/s]
 34%|███▍      | 15/44 [00:10<00:21,  1.35it/s]
 36%|███▋      | 16/44 [00:11<00:20,  1.35it/s]
 39%|███▊      | 17/44 [00:12<00:19,  1.35it/s]
 41%|████      | 18/44 [00:13<00:19,  1.35it/s]
 43%|████▎     | 19/44 [00:13<00:18,  1.35it/s]
 45%|████▌     | 20/44 [00:14<00:17,  1.35it/s]
 48%|████▊     | 21/44 [00:15<00:17,  1.35it/s]
 50%|█████     | 22/44 [00:16<00:16,  1.35it/s]
 52%|█████▏    | 23/44 [00:16<00:15,  1.35it/s]
 55%|█████▍    | 24/44 [00:17<00:14,  1.35it/s]
 57%|█████▋    | 25/44 [00:18<00:14,  1.35it/s]
 59%|█████▉    | 26/44 [00:19<00:13,  1.35it/s]
 61%|██████▏   | 27/44 [00:19<00:12,  1.35it/s]
 64%|██████▎   | 28/44 [00:20<00:11,  1.35it/s]
 66%|██████▌   | 29/44 [00:21<00:11,  1.35it/s]
 68%|██████▊   | 30/44 [00:22<00:10,  1.35it/s]
 70%|███████   | 31/44 [00:22<00:09,  1.35it/s]
 73%|███████▎  | 32/44 [00:23<00:08,  1.35it/s]
 75%|███████▌  | 33/44 [00:24<00:08,  1.35it/s]
 77%|███████▋  | 34/44 [00:25<00:07,  1.35it/s]
 80%|███████▉  | 35/44 [00:25<00:06,  1.35it/s]
 82%|████████▏ | 36/44 [00:26<00:05,  1.35it/s]
 84%|████████▍ | 37/44 [00:27<00:05,  1.35it/s]
 86%|████████▋ | 38/44 [00:27<00:04,  1.35it/s]
 89%|████████▊ | 39/44 [00:28<00:03,  1.35it/s]
 91%|█████████ | 40/44 [00:29<00:02,  1.35it/s]
 93%|█████████▎| 41/44 [00:30<00:02,  1.35it/s]
 95%|█████████▌| 42/44 [00:30<00:01,  1.35it/s]
 98%|█████████▊| 43/44 [00:31<00:00,  1.35it/s]
100%|██████████| 44/44 [00:32<00:00,  1.35it/s]
100%|██████████| 44/44 [00:32<00:00,  1.36it/s]
Total safe images: 3 out of 3

Version Details

Version ID: 0ec11e216893c971467a226b6fccce2937f855eaadd8a61170baa6d7aa034340
Version Created: July 1, 2025

Run on Replicate →