aicomfy/vivian 🖼️🔢❓📝✓ → 🖼️

▶️ 27 runs 📅 Aug 2025 ⚙️ Cog 0.15.3
image-inpainting image-to-image lora lora-person text-to-image

About

Example Output

Prompt:

"An off-guard shot of a tall, skinny, almond-skinned 22-year-old woman with toned arms and legs, wearing a tailored black blazer dress and stiletto heels backstage at fashion week, holding a coffee cup, minimal makeup, hair tied sleekly back, amateur flash lighting, cluttered background, spontaneous vibe"

Output

Example output

Performance Metrics

10.93s Prediction Time
11.11s Total Time
All Input Parameters 
{
  "model": "dev",
  "prompt": "An off-guard shot of a tall, skinny, almond-skinned 22-year-old woman with toned arms and legs, wearing a tailored black blazer dress and stiletto heels backstage at fashion week, holding a coffee cup, minimal makeup, hair tied sleekly back, amateur flash lighting, cluttered background, spontaneous vibe\n",
  "go_fast": false,
  "extra_lora": "huggingface.co/OthmaneNAHYL/FLUX-Amateur-Photography-LoRA",
  "lora_scale": 0.88,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 2.72,
  "output_quality": 100,
  "prompt_strength": 0.8,
  "extra_lora_scale": 0.53,
  "num_inference_steps": 28
}
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=26886180691968
Downloading weights
2025-08-05T19:57:36Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpod2_i_3h/weights url=https://replicate.delivery/xezq/pZIQe8CE3FwBBqEPze8IWNpWWjQx3Gg4C6KW5HqArBSLHBIVA/trained_model.tar
2025-08-05T19:57:36Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-08-05T19:57:36Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/pZIQe8CE3FwBBqEPze8IWNpWWjQx3Gg4C6KW5HqArBSLHBIVA/trained_model.tar url=https://replicate.delivery/xezq/pZIQe8CE3FwBBqEPze8IWNpWWjQx3Gg4C6KW5HqArBSLHBIVA/trained_model.tar
2025-08-05T19:57:36Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/1c7aef52544cb187c7752fd765bd7bd8c7b3cabbd415ad317e1c6af36bfda275?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250805%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250805T195736Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=3d304d2b6aa080a84967863c7a2d4b9983b574ef4beea46fc1365ffcaa0cec47 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/pZIQe8CE3FwBBqEPze8IWNpWWjQx3Gg4C6KW5HqArBSLHBIVA/trained_model.tar
2025-08-05T19:57:36Z | INFO  | [ Complete ] dest=/tmp/tmpod2_i_3h/weights size="172 MB" total_elapsed=0.269s url=https://replicate.delivery/xezq/pZIQe8CE3FwBBqEPze8IWNpWWjQx3Gg4C6KW5HqArBSLHBIVA/trained_model.tar
Downloaded weights in 0.33s
free=26886008016896
Downloading weights
2025-08-05T19:57:37Z | INFO  | [ Initiating ] chunk_size=150M dest=/src/weights-cache/ad4532bc9b095492 url=https://huggingface.co/OthmaneNAHYL/FLUX-Amateur-Photography-LoRA/resolve/main/amateurphoto-v6-forcu.safetensors
2025-08-05T19:57:37Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-08-05T19:57:37Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/huggingface.co/OthmaneNAHYL/FLUX-Amateur-Photography-LoRA/resolve/main/amateurphoto-v6-forcu.safetensors url=https://huggingface.co/OthmaneNAHYL/FLUX-Amateur-Photography-LoRA/resolve/main/amateurphoto-v6-forcu.safetensors
2025-08-05T19:57:37Z | INFO  | [ Redirect ] redirect_url=http://r8-huggingface-ric1.cwlota.com/e78253a8727015393767c23b915fa35ec16346b0956d0bae4f21e5cf11a060db?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250805%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250805T195737Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=dc62f36f1bfe81de288a56054834525e12fd343814b4ea3a7c328fe89ce5aecc url=http://hermes.services.svc.cluster.local/huggingface.co/OthmaneNAHYL/FLUX-Amateur-Photography-LoRA/resolve/main/amateurphoto-v6-forcu.safetensors
2025-08-05T19:57:37Z | INFO  | [ Complete ] dest=/src/weights-cache/ad4532bc9b095492 size="306 MB" total_elapsed=0.424s url=https://huggingface.co/OthmaneNAHYL/FLUX-Amateur-Photography-LoRA/resolve/main/amateurphoto-v6-forcu.safetensors
Downloaded weights in 0.49s
Loaded LoRAs in 2.19s
Using seed: 64723
Prompt: An off-guard shot of a tall, skinny, almond-skinned 22-year-old woman with toned arms and legs, wearing a tailored black blazer dress and stiletto heels backstage at fashion week, holding a coffee cup, minimal makeup, hair tied sleekly back, amateur flash lighting, cluttered background, spontaneous vibe
[!] txt2img mode
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:08,  3.36it/s]
  7%|▋         | 2/28 [00:00<00:07,  3.69it/s]
 11%|█         | 3/28 [00:00<00:07,  3.55it/s]
 14%|█▍        | 4/28 [00:01<00:06,  3.48it/s]
 18%|█▊        | 5/28 [00:01<00:06,  3.45it/s]
 21%|██▏       | 6/28 [00:01<00:06,  3.42it/s]
 25%|██▌       | 7/28 [00:02<00:06,  3.41it/s]
 29%|██▊       | 8/28 [00:02<00:05,  3.40it/s]
 32%|███▏      | 9/28 [00:02<00:05,  3.40it/s]
 36%|███▌      | 10/28 [00:02<00:05,  3.39it/s]
 39%|███▉      | 11/28 [00:03<00:05,  3.39it/s]
 43%|████▎     | 12/28 [00:03<00:04,  3.39it/s]
 46%|████▋     | 13/28 [00:03<00:04,  3.39it/s]
 50%|█████     | 14/28 [00:04<00:04,  3.39it/s]
 54%|█████▎    | 15/28 [00:04<00:03,  3.39it/s]
 57%|█████▋    | 16/28 [00:04<00:03,  3.39it/s]
 61%|██████    | 17/28 [00:04<00:03,  3.39it/s]
 64%|██████▍   | 18/28 [00:05<00:02,  3.38it/s]
 68%|██████▊   | 19/28 [00:05<00:02,  3.38it/s]
 71%|███████▏  | 20/28 [00:05<00:02,  3.38it/s]
 75%|███████▌  | 21/28 [00:06<00:02,  3.38it/s]
 79%|███████▊  | 22/28 [00:06<00:01,  3.38it/s]
 82%|████████▏ | 23/28 [00:06<00:01,  3.38it/s]
 86%|████████▌ | 24/28 [00:07<00:01,  3.38it/s]
 89%|████████▉ | 25/28 [00:07<00:00,  3.38it/s]
 93%|█████████▎| 26/28 [00:07<00:00,  3.38it/s]
 96%|█████████▋| 27/28 [00:07<00:00,  3.38it/s]
100%|██████████| 28/28 [00:08<00:00,  3.38it/s]
100%|██████████| 28/28 [00:08<00:00,  3.40it/s]
Total safe images: 1 out of 1
Version Details
Version ID
67b357029871153800da9eac857f651ef986414e78598ac656f8cb1572130367
Version Created
August 5, 2025
Run on Replicate →