cristianpopeishon/crism3 🖼️🔢❓📝✓ → 🖼️

▶️ 63 runs 📅 Aug 2025 ⚙️ Cog 0.13.6

About

Example Output

Prompt:

"Crism3 profesional studio image
not smiling man of 38 years old with a black collar
traditional portrait
without letters in shirt
focused look
looking at the camera
black&white portrait
dark diffuse background
With a serious expresion
135mm lens used"

Output

Performance Metrics

25.04s Prediction Time

25.62s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "Crism3  profesional studio image\nnot smiling man of 38 years old with a black collar\ntraditional portrait\nwithout letters in shirt\nfocused look\nlooking at the camera\nblack&white portrait\ndark diffuse background\nWith a serious expresion\n135mm lens used",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 2,
  "aspect_ratio": "3:4",
  "output_format": "jpg",
  "guidance_scale": 3,
  "output_quality": 95,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 49
}

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

Loaded LoRAs in 0.50s
Using seed: 28777
Prompt: Crism3  profesional studio image
not smiling man of 38 years old with a black collar
traditional portrait
without letters in shirt
focused look
looking at the camera
black&white portrait
dark diffuse background
With a serious expresion
135mm lens used
[!] txt2img mode
  0%|          | 0/49 [00:00<?, ?it/s]
  2%|▏         | 1/49 [00:00<00:23,  2.03it/s]
  4%|▍         | 2/49 [00:00<00:20,  2.30it/s]
  6%|▌         | 3/49 [00:01<00:21,  2.17it/s]
  8%|▊         | 4/49 [00:01<00:21,  2.11it/s]
 10%|█         | 5/49 [00:02<00:21,  2.08it/s]
 12%|█▏        | 6/49 [00:02<00:20,  2.06it/s]
 14%|█▍        | 7/49 [00:03<00:20,  2.05it/s]
 16%|█▋        | 8/49 [00:03<00:20,  2.04it/s]
 18%|█▊        | 9/49 [00:04<00:19,  2.04it/s]
 20%|██        | 10/49 [00:04<00:19,  2.03it/s]
 22%|██▏       | 11/49 [00:05<00:18,  2.03it/s]
 24%|██▍       | 12/49 [00:05<00:18,  2.03it/s]
 27%|██▋       | 13/49 [00:06<00:17,  2.03it/s]
 29%|██▊       | 14/49 [00:06<00:17,  2.03it/s]
 31%|███       | 15/49 [00:07<00:16,  2.03it/s]
 33%|███▎      | 16/49 [00:07<00:16,  2.03it/s]
 35%|███▍      | 17/49 [00:08<00:15,  2.03it/s]
 37%|███▋      | 18/49 [00:08<00:15,  2.03it/s]
 39%|███▉      | 19/49 [00:09<00:14,  2.03it/s]
 41%|████      | 20/49 [00:09<00:14,  2.02it/s]
 43%|████▎     | 21/49 [00:10<00:13,  2.02it/s]
 45%|████▍     | 22/49 [00:10<00:13,  2.02it/s]
 47%|████▋     | 23/49 [00:11<00:12,  2.02it/s]
 49%|████▉     | 24/49 [00:11<00:12,  2.02it/s]
 51%|█████     | 25/49 [00:12<00:11,  2.02it/s]
 53%|█████▎    | 26/49 [00:12<00:11,  2.02it/s]
 55%|█████▌    | 27/49 [00:13<00:10,  2.02it/s]
 57%|█████▋    | 28/49 [00:13<00:10,  2.02it/s]
 59%|█████▉    | 29/49 [00:14<00:09,  2.02it/s]
 61%|██████    | 30/49 [00:14<00:09,  2.02it/s]
 63%|██████▎   | 31/49 [00:15<00:08,  2.02it/s]
 65%|██████▌   | 32/49 [00:15<00:08,  2.02it/s]
 67%|██████▋   | 33/49 [00:16<00:07,  2.02it/s]
 69%|██████▉   | 34/49 [00:16<00:07,  2.02it/s]
 71%|███████▏  | 35/49 [00:17<00:06,  2.02it/s]
 73%|███████▎  | 36/49 [00:17<00:06,  2.02it/s]
 76%|███████▌  | 37/49 [00:18<00:05,  2.02it/s]
 78%|███████▊  | 38/49 [00:18<00:05,  2.02it/s]
 80%|███████▉  | 39/49 [00:19<00:04,  2.02it/s]
 82%|████████▏ | 40/49 [00:19<00:04,  2.02it/s]
 84%|████████▎ | 41/49 [00:20<00:03,  2.02it/s]
 86%|████████▌ | 42/49 [00:20<00:03,  2.02it/s]
 88%|████████▊ | 43/49 [00:21<00:02,  2.02it/s]
 90%|████████▉ | 44/49 [00:21<00:02,  2.02it/s]
 92%|█████████▏| 45/49 [00:22<00:01,  2.02it/s]
 94%|█████████▍| 46/49 [00:22<00:01,  2.02it/s]
 96%|█████████▌| 47/49 [00:23<00:00,  2.02it/s]
 98%|█████████▊| 48/49 [00:23<00:00,  2.02it/s]
100%|██████████| 49/49 [00:24<00:00,  2.02it/s]
100%|██████████| 49/49 [00:24<00:00,  2.03it/s]
Total safe images: 2 out of 2

Version Details

Version ID: ff0e62888d3f64a7fcaf77cf793c6c50b291d888a4e54fd4455f477fb9dba2b5
Version Created: August 13, 2025

Run on Replicate →