klassenmedia/moris 🖼️🔢❓📝✓ → 🖼️

▶️ 351 runs 📅 May 2025 ⚙️ Cog 0.14.3

About

Example Output

Prompt:

"MORIS, a close-up portrait of a confident and charismatic professional speaker, well-groomed with short styled hair and a subtle smile, wearing a dark blazer and crisp shirt, studio background with soft gradient, sharp front lighting enhancing facial features, eyes focused and expressive, shot with a Canon EOS R3, 85mm f/1.2 lens, clean and neutral color tones with subtle warmth"

Output

Performance Metrics

9.83s Prediction Time

9.84s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "MORIS, a close-up portrait of a confident and charismatic professional speaker, well-groomed with short styled hair and a subtle smile, wearing a dark blazer and crisp shirt, studio background with soft gradient, sharp front lighting enhancing facial features, eyes focused and expressive, shot with a Canon EOS R3, 85mm f/1.2 lens, clean and neutral color tones with subtle warmth",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "2:3",
  "output_format": "png",
  "guidance_scale": 3.23,
  "output_quality": 100,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 37
}

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

Weights already loaded
Loaded LoRAs in 0.02s
Using seed: 42645
Prompt: MORIS, a close-up portrait of a confident and charismatic professional speaker, well-groomed with short styled hair and a subtle smile, wearing a dark blazer and crisp shirt, studio background with soft gradient, sharp front lighting enhancing facial features, eyes focused and expressive, shot with a Canon EOS R3, 85mm f/1.2 lens, clean and neutral color tones with subtle warmth
[!] txt2img mode
  0%|          | 0/37 [00:00<?, ?it/s]
  3%|▎         | 1/37 [00:00<00:09,  3.93it/s]
  5%|▌         | 2/37 [00:00<00:07,  4.45it/s]
  8%|▊         | 3/37 [00:00<00:08,  4.20it/s]
 11%|█         | 4/37 [00:00<00:08,  4.10it/s]
 14%|█▎        | 5/37 [00:01<00:07,  4.04it/s]
 16%|█▌        | 6/37 [00:01<00:07,  4.00it/s]
 19%|█▉        | 7/37 [00:01<00:07,  3.98it/s]
 22%|██▏       | 8/37 [00:01<00:07,  3.97it/s]
 24%|██▍       | 9/37 [00:02<00:07,  3.96it/s]
 27%|██▋       | 10/37 [00:02<00:06,  3.95it/s]
 30%|██▉       | 11/37 [00:02<00:06,  3.95it/s]
 32%|███▏      | 12/37 [00:02<00:06,  3.95it/s]
 35%|███▌      | 13/37 [00:03<00:06,  3.95it/s]
 38%|███▊      | 14/37 [00:03<00:05,  3.95it/s]
 41%|████      | 15/37 [00:03<00:05,  3.94it/s]
 43%|████▎     | 16/37 [00:04<00:05,  3.94it/s]
 46%|████▌     | 17/37 [00:04<00:05,  3.94it/s]
 49%|████▊     | 18/37 [00:04<00:04,  3.94it/s]
 51%|█████▏    | 19/37 [00:04<00:04,  3.94it/s]
 54%|█████▍    | 20/37 [00:05<00:04,  3.94it/s]
 57%|█████▋    | 21/37 [00:05<00:04,  3.94it/s]
 59%|█████▉    | 22/37 [00:05<00:03,  3.94it/s]
 62%|██████▏   | 23/37 [00:05<00:03,  3.94it/s]
 65%|██████▍   | 24/37 [00:06<00:03,  3.94it/s]
 68%|██████▊   | 25/37 [00:06<00:03,  3.94it/s]
 70%|███████   | 26/37 [00:06<00:02,  3.94it/s]
 73%|███████▎  | 27/37 [00:06<00:02,  3.94it/s]
 76%|███████▌  | 28/37 [00:07<00:02,  3.94it/s]
 78%|███████▊  | 29/37 [00:07<00:02,  3.94it/s]
 81%|████████  | 30/37 [00:07<00:01,  3.94it/s]
 84%|████████▍ | 31/37 [00:07<00:01,  3.94it/s]
 86%|████████▋ | 32/37 [00:08<00:01,  3.94it/s]
 89%|████████▉ | 33/37 [00:08<00:01,  3.94it/s]
 92%|█████████▏| 34/37 [00:08<00:00,  3.94it/s]
 95%|█████████▍| 35/37 [00:08<00:00,  3.94it/s]
 97%|█████████▋| 36/37 [00:09<00:00,  3.94it/s]
100%|██████████| 37/37 [00:09<00:00,  3.95it/s]
100%|██████████| 37/37 [00:09<00:00,  3.96it/s]
Total safe images: 1 out of 1

Version Details

Version ID: b38961eaba1c28482bb9affa7c24e1faebd00021e306e5e941bbf916cc99e92c
Version Created: May 2, 2025

Run on Replicate →