krisdoan/odcn2 🖼️🔢❓📝✓ → 🖼️

▶️ 23 runs 📅 Aug 2025 ⚙️ Cog 0.13.6

About

Example Output

Prompt:

"a pair of ODCN2 eyeglasses is worn by a young Japanese man, he is looking to the left, realistic, cinematic, studio style"

Output

Performance Metrics

13.90s Prediction Time

13.90s Total Time

All Input Parameters

{
  "model": "dev",
  "width": 1440,
  "height": 1440,
  "prompt": "a pair of ODCN2 eyeglasses is worn by a young Japanese man, he is looking to the left, realistic, cinematic, studio style",
  "go_fast": false,
  "extra_lora": "https://huggingface.co/PlayDustinDB/FLUX.1-Krea-dev-LoRA/resolve/main/flux1-krea-dev_rank_128-bf16.safetensors",
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "9:16",
  "output_format": "png",
  "guidance_scale": 2.5,
  "output_quality": 100,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 45
}

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 0.04s
Using seed: 56469
Prompt: a pair of ODCN2 eyeglasses is worn by a young Japanese man, he is looking to the left, realistic, cinematic, studio style
[!] txt2img mode
  0%|          | 0/45 [00:00<?, ?it/s]
  2%|▏         | 1/45 [00:00<00:13,  3.37it/s]
  4%|▍         | 2/45 [00:00<00:11,  3.70it/s]
  7%|▋         | 3/45 [00:00<00:11,  3.55it/s]
  9%|▉         | 4/45 [00:01<00:11,  3.48it/s]
 11%|█         | 5/45 [00:01<00:11,  3.45it/s]
 13%|█▎        | 6/45 [00:01<00:11,  3.43it/s]
 16%|█▌        | 7/45 [00:02<00:11,  3.41it/s]
 18%|█▊        | 8/45 [00:02<00:10,  3.40it/s]
 20%|██        | 9/45 [00:02<00:10,  3.39it/s]
 22%|██▏       | 10/45 [00:02<00:10,  3.39it/s]
 24%|██▍       | 11/45 [00:03<00:10,  3.39it/s]
 27%|██▋       | 12/45 [00:03<00:09,  3.39it/s]
 29%|██▉       | 13/45 [00:03<00:09,  3.38it/s]
 31%|███       | 14/45 [00:04<00:09,  3.38it/s]
 33%|███▎      | 15/45 [00:04<00:08,  3.38it/s]
 36%|███▌      | 16/45 [00:04<00:08,  3.38it/s]
 38%|███▊      | 17/45 [00:04<00:08,  3.38it/s]
 40%|████      | 18/45 [00:05<00:07,  3.38it/s]
 42%|████▏     | 19/45 [00:05<00:07,  3.38it/s]
 44%|████▍     | 20/45 [00:05<00:07,  3.38it/s]
 47%|████▋     | 21/45 [00:06<00:07,  3.38it/s]
 49%|████▉     | 22/45 [00:06<00:06,  3.38it/s]
 51%|█████     | 23/45 [00:06<00:06,  3.38it/s]
 53%|█████▎    | 24/45 [00:07<00:06,  3.38it/s]
 56%|█████▌    | 25/45 [00:07<00:05,  3.38it/s]
 58%|█████▊    | 26/45 [00:07<00:05,  3.38it/s]
 60%|██████    | 27/45 [00:07<00:05,  3.38it/s]
 62%|██████▏   | 28/45 [00:08<00:05,  3.38it/s]
 64%|██████▍   | 29/45 [00:08<00:04,  3.38it/s]
 67%|██████▋   | 30/45 [00:08<00:04,  3.38it/s]
 69%|██████▉   | 31/45 [00:09<00:04,  3.38it/s]
 71%|███████   | 32/45 [00:09<00:03,  3.38it/s]
 73%|███████▎  | 33/45 [00:09<00:03,  3.38it/s]
 76%|███████▌  | 34/45 [00:10<00:03,  3.38it/s]
 78%|███████▊  | 35/45 [00:10<00:02,  3.38it/s]
 80%|████████  | 36/45 [00:10<00:02,  3.38it/s]
 82%|████████▏ | 37/45 [00:10<00:02,  3.38it/s]
 84%|████████▍ | 38/45 [00:11<00:02,  3.38it/s]
 87%|████████▋ | 39/45 [00:11<00:01,  3.38it/s]
 89%|████████▉ | 40/45 [00:11<00:01,  3.38it/s]
 91%|█████████ | 41/45 [00:12<00:01,  3.38it/s]
 93%|█████████▎| 42/45 [00:12<00:00,  3.38it/s]
 96%|█████████▌| 43/45 [00:12<00:00,  3.38it/s]
 98%|█████████▊| 44/45 [00:12<00:00,  3.38it/s]
100%|██████████| 45/45 [00:13<00:00,  3.38it/s]
100%|██████████| 45/45 [00:13<00:00,  3.39it/s]
Total safe images: 1 out of 1

Version Details

Version ID: dadcba170774d1edfefe6c43b3b14dccbd9a0a856ce7fb3d8e481418aecf6667
Version Created: August 14, 2025

Run on Replicate →