lovewraps/annie_vixen 🖼️🔢❓📝✓ → 🖼️

▶️ 7 runs 📅 Jun 2025 ⚙️ Cog 0.13.6
lora lora-person nsfw text-to-image

About

online_vixen (realistic)

Example Output

Prompt:

"

Create image of annie based on the following:

  • Woman with long, wavy bright red hair
  • Wearing black fishnet/mesh long-sleeved top with "badmood" text in orange/red gothic lettering across the chest
  • Black fishnet stockings/tights with garter belt straps and metal ring details
  • Arms raised above head in a posed position
  • Extensive tattoo coverage visible on arms and torso
  • Red lipstick, dramatic eye makeup with long eyelashes
  • Standing against plain white/light gray background

Consistent elements to include image generation:

  • Professional studio lighting
  • Clean, minimalist background
  • High contrast, vibrant color saturation
  • Fashion/lifestyle photography style
  • Identical hair color, length, and styling
  • Same facial features and makeup application
  • Extensive black tattoo work on both arms and visible body areas
"

Output

Example output

Performance Metrics

33.12s Prediction Time
35.54s Total Time
All Input Parameters 
{
  "model": "dev",
  "prompt": "Create image of annie based on the following:\n- Woman with long, wavy bright red hair\n- Wearing black fishnet/mesh long-sleeved top with \"badmood\" text in orange/red gothic lettering across the chest\n- Black fishnet stockings/tights with garter belt straps and metal ring details\n- Arms raised above head in a posed position\n- Extensive tattoo coverage visible on arms and torso\n- Red lipstick, dramatic eye makeup with long eyelashes\n- Standing against plain white/light gray background\n\nConsistent elements to include image generation:\n- Professional studio lighting\n- Clean, minimalist background\n- High contrast, vibrant color saturation\n- Fashion/lifestyle photography style\n- Identical hair color, length, and styling\n- Same facial features and makeup application\n- Extensive black tattoo work on both arms and visible body areas",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 3,
  "aspect_ratio": "9:16",
  "output_format": "png",
  "guidance_scale": 2,
  "output_quality": 100,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 40
}
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=26894439661568
Downloading weights
2025-06-30T06:59:37Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpnyo82gl5/weights url=https://replicate.delivery/xezq/j6T9Hj45IWqhGtGnG4KZtAQUefNM9VAwVrnj3pWQY3UJg67UA/flux-lora.tar
2025-06-30T06:59:37Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-06-30T06:59:37Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/j6T9Hj45IWqhGtGnG4KZtAQUefNM9VAwVrnj3pWQY3UJg67UA/flux-lora.tar url=https://replicate.delivery/xezq/j6T9Hj45IWqhGtGnG4KZtAQUefNM9VAwVrnj3pWQY3UJg67UA/flux-lora.tar
2025-06-30T06:59:38Z | INFO  | [ Redirect ] redirect_url=https://replicate.delivery/xezq/j6T9Hj45IWqhGtGnG4KZtAQUefNM9VAwVrnj3pWQY3UJg67UA/flux-lora.tar url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/j6T9Hj45IWqhGtGnG4KZtAQUefNM9VAwVrnj3pWQY3UJg67UA/flux-lora.tar
2025-06-30T06:59:40Z | INFO  | [ Complete ] dest=/tmp/tmpnyo82gl5/weights size="172 MB" total_elapsed=2.600s url=https://replicate.delivery/xezq/j6T9Hj45IWqhGtGnG4KZtAQUefNM9VAwVrnj3pWQY3UJg67UA/flux-lora.tar
Downloaded weights in 2.66s
Loaded LoRAs in 3.18s
Using seed: 65297
Prompt: Create image of annie based on the following:
- Woman with long, wavy bright red hair
- Wearing black fishnet/mesh long-sleeved top with "badmood" text in orange/red gothic lettering across the chest
- Black fishnet stockings/tights with garter belt straps and metal ring details
- Arms raised above head in a posed position
- Extensive tattoo coverage visible on arms and torso
- Red lipstick, dramatic eye makeup with long eyelashes
- Standing against plain white/light gray background
Consistent elements to include image generation:
- Professional studio lighting
- Clean, minimalist background
- High contrast, vibrant color saturation
- Fashion/lifestyle photography style
- Identical hair color, length, and styling
- Same facial features and makeup application
- Extensive black tattoo work on both arms and visible body areas
[!] txt2img mode
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:00<00:28,  1.39it/s]
  5%|▌         | 2/40 [00:01<00:24,  1.56it/s]
  8%|▊         | 3/40 [00:02<00:25,  1.47it/s]
 10%|█         | 4/40 [00:02<00:25,  1.43it/s]
 12%|█▎        | 5/40 [00:03<00:24,  1.41it/s]
 15%|█▌        | 6/40 [00:04<00:24,  1.40it/s]
 18%|█▊        | 7/40 [00:04<00:23,  1.39it/s]
 20%|██        | 8/40 [00:05<00:23,  1.39it/s]
 22%|██▎       | 9/40 [00:06<00:22,  1.38it/s]
 25%|██▌       | 10/40 [00:07<00:21,  1.38it/s]
 28%|██▊       | 11/40 [00:07<00:20,  1.38it/s]
 30%|███       | 12/40 [00:08<00:20,  1.38it/s]
 32%|███▎      | 13/40 [00:09<00:19,  1.38it/s]
 35%|███▌      | 14/40 [00:10<00:18,  1.38it/s]
 38%|███▊      | 15/40 [00:10<00:18,  1.38it/s]
 40%|████      | 16/40 [00:11<00:17,  1.38it/s]
 42%|████▎     | 17/40 [00:12<00:16,  1.38it/s]
 45%|████▌     | 18/40 [00:12<00:16,  1.37it/s]
 48%|████▊     | 19/40 [00:13<00:15,  1.37it/s]
 50%|█████     | 20/40 [00:14<00:14,  1.37it/s]
 52%|█████▎    | 21/40 [00:15<00:13,  1.37it/s]
 55%|█████▌    | 22/40 [00:15<00:13,  1.37it/s]
 57%|█████▊    | 23/40 [00:16<00:12,  1.38it/s]
 60%|██████    | 24/40 [00:17<00:11,  1.38it/s]
 62%|██████▎   | 25/40 [00:18<00:10,  1.38it/s]
 65%|██████▌   | 26/40 [00:18<00:10,  1.38it/s]
 68%|██████▊   | 27/40 [00:19<00:09,  1.37it/s]
 70%|███████   | 28/40 [00:20<00:08,  1.37it/s]
 72%|███████▎  | 29/40 [00:20<00:07,  1.38it/s]
 75%|███████▌  | 30/40 [00:21<00:07,  1.38it/s]
 78%|███████▊  | 31/40 [00:22<00:06,  1.37it/s]
 80%|████████  | 32/40 [00:23<00:05,  1.37it/s]
 82%|████████▎ | 33/40 [00:23<00:05,  1.37it/s]
 85%|████████▌ | 34/40 [00:24<00:04,  1.37it/s]
 88%|████████▊ | 35/40 [00:25<00:03,  1.38it/s]
 90%|█████████ | 36/40 [00:26<00:02,  1.37it/s]
 92%|█████████▎| 37/40 [00:26<00:02,  1.37it/s]
 95%|█████████▌| 38/40 [00:27<00:01,  1.37it/s]
 98%|█████████▊| 39/40 [00:28<00:00,  1.38it/s]
100%|██████████| 40/40 [00:28<00:00,  1.37it/s]
100%|██████████| 40/40 [00:28<00:00,  1.38it/s]
NSFW content detected in image 0
NSFW content detected in image 1
Total safe images: 1 out of 3
Version Details
Version ID
0295e691f46f18e2bc73dd0e7ce24b00c4d9177b739c240ecccaa359b903c9eb
Version Created
June 30, 2025
Run on Replicate →