marcobitboss274/mace27 🖼️🔢❓📝✓ → 🖼️

▶️ 17 runs 📅 Oct 2025 ⚙️ Cog 0.13.6
image-inpainting image-to-image lora text-to-image toktok-style

About

Example Output

Prompt:

"

High-resolution digital engraving-style reproduction, monochromatic black ink on a pure white background, characterized by a fluid and dynamic geometry. The drawing is an ornamental composition in a Rococo-Baroque style, composed solely and exclusively of jewels arranged in sinuous and calligraphic lines. Elegant scrolls and spirals evoke the golden ratio, ending in harmonious curves and sophisticated volutes. At the center appear small oval medallions with classical sculpted profiles, while on both the upper and lower sides there are often winged putti holding decorative elements such as pendants and fine draped chains.

From the structure branch out pendants, beads, gemstones, and slender jewels and necklaces forming elegant curves and arches, accentuating the symmetry and refinement of the composition. The style is light, harmonious, and reminiscent of 18th-century French jewelry design.

The drawing develops primarily in a vertical direction but is skillfully balanced by horizontal elements and connecting curves that create a harmonious interlace and a sense of stability. The overall forms are an intricate weave of elongated ellipses, soft S- and C-shaped curves, and small stylized droplet-like elements, richly detailed.

The composition alternates richly detailed areas with open white spaces and presents strong chiaroscuro and volumetric effects achieved through precise and refined cross-hatching and shading. The border consists of overlapping intricate volutes and delicate floral elements.

Must be in TOKTOK style.

"

Output

Example output

Performance Metrics

9.55s Prediction Time
9.58s Total Time
All Input Parameters 
{
  "image": "https://replicate.delivery/pbxt/NvfUWMbykNzOkdAluBckBDtzxTKMRyTySBaSsWaMQfuwgLtf/Screenshot%202025-10-21%20at%2011.42.45.png",
  "model": "dev",
  "prompt": "High-resolution digital engraving-style reproduction, monochromatic black ink on a pure white background, characterized by a fluid and dynamic geometry. The drawing is an ornamental composition in a Rococo-Baroque style, composed solely and exclusively of jewels arranged in sinuous and calligraphic lines. Elegant scrolls and spirals evoke the golden ratio, ending in harmonious curves and sophisticated volutes. At the center appear small oval medallions with classical sculpted profiles, while on both the upper and lower sides there are often winged putti holding decorative elements such as pendants and fine draped chains.\n\nFrom the structure branch out pendants, beads, gemstones, and slender jewels and necklaces forming elegant curves and arches, accentuating the symmetry and refinement of the composition. The style is light, harmonious, and reminiscent of 18th-century French jewelry design.\n\nThe drawing develops primarily in a vertical direction but is skillfully balanced by horizontal elements and connecting curves that create a harmonious interlace and a sense of stability. The overall forms are an intricate weave of elongated ellipses, soft S- and C-shaped curves, and small stylized droplet-like elements, richly detailed.\n\nThe composition alternates richly detailed areas with open white spaces and presents strong chiaroscuro and volumetric effects achieved through precise and refined cross-hatching and shading. The border consists of overlapping intricate volutes and delicate floral elements.\n\nMust be in TOKTOK style.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "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=25811572899840
Downloading weights
2025-10-22T13:37:52Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmplu1nddu4/weights url=https://replicate.delivery/xezq/gEIcRsMzc5b8DB9Aehfg9qWVNr7RJD7janvQqyATklozfRDrA/flux-lora.tar
2025-10-22T13:37:52Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-10-22T13:37:52Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/gEIcRsMzc5b8DB9Aehfg9qWVNr7RJD7janvQqyATklozfRDrA/flux-lora.tar url=https://replicate.delivery/xezq/gEIcRsMzc5b8DB9Aehfg9qWVNr7RJD7janvQqyATklozfRDrA/flux-lora.tar
2025-10-22T13:37:52Z | INFO  | [ Redirect ] redirect_url=https://replicate.delivery/xezq/gEIcRsMzc5b8DB9Aehfg9qWVNr7RJD7janvQqyATklozfRDrA/flux-lora.tar url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/gEIcRsMzc5b8DB9Aehfg9qWVNr7RJD7janvQqyATklozfRDrA/flux-lora.tar
2025-10-22T13:37:55Z | INFO  | [ Complete ] dest=/tmp/tmplu1nddu4/weights size="172 MB" total_elapsed=2.757s url=https://replicate.delivery/xezq/gEIcRsMzc5b8DB9Aehfg9qWVNr7RJD7janvQqyATklozfRDrA/flux-lora.tar
Downloaded weights in 2.84s
Loaded LoRAs in 3.37s
Using seed: 38631
Prompt: High-resolution digital engraving-style reproduction, monochromatic black ink on a pure white background, characterized by a fluid and dynamic geometry. The drawing is an ornamental composition in a Rococo-Baroque style, composed solely and exclusively of jewels arranged in sinuous and calligraphic lines. Elegant scrolls and spirals evoke the golden ratio, ending in harmonious curves and sophisticated volutes. At the center appear small oval medallions with classical sculpted profiles, while on both the upper and lower sides there are often winged putti holding decorative elements such as pendants and fine draped chains.
From the structure branch out pendants, beads, gemstones, and slender jewels and necklaces forming elegant curves and arches, accentuating the symmetry and refinement of the composition. The style is light, harmonious, and reminiscent of 18th-century French jewelry design.
The drawing develops primarily in a vertical direction but is skillfully balanced by horizontal elements and connecting curves that create a harmonious interlace and a sense of stability. The overall forms are an intricate weave of elongated ellipses, soft S- and C-shaped curves, and small stylized droplet-like elements, richly detailed.
The composition alternates richly detailed areas with open white spaces and presents strong chiaroscuro and volumetric effects achieved through precise and refined cross-hatching and shading. The border consists of overlapping intricate volutes and delicate floral elements.
Must be in TOKTOK style.
Input image size: 862x1862
[!] Resizing input image from 862x1862 to 672x1440
[!] img2img mode
  0%|          | 0/23 [00:00<?, ?it/s]
  4%|▍         | 1/23 [00:00<00:04,  5.08it/s]
  9%|▊         | 2/23 [00:00<00:04,  4.43it/s]
 13%|█▎        | 3/23 [00:00<00:04,  4.25it/s]
 17%|█▋        | 4/23 [00:00<00:04,  4.17it/s]
 22%|██▏       | 5/23 [00:01<00:04,  4.13it/s]
 26%|██▌       | 6/23 [00:01<00:04,  4.11it/s]
 30%|███       | 7/23 [00:01<00:03,  4.09it/s]
 35%|███▍      | 8/23 [00:01<00:03,  4.07it/s]
 39%|███▉      | 9/23 [00:02<00:03,  4.07it/s]
 43%|████▎     | 10/23 [00:02<00:03,  4.06it/s]
 48%|████▊     | 11/23 [00:02<00:02,  4.06it/s]
 52%|█████▏    | 12/23 [00:02<00:02,  4.06it/s]
 57%|█████▋    | 13/23 [00:03<00:02,  4.05it/s]
 61%|██████    | 14/23 [00:03<00:02,  4.05it/s]
 65%|██████▌   | 15/23 [00:03<00:01,  4.05it/s]
 70%|██████▉   | 16/23 [00:03<00:01,  4.05it/s]
 74%|███████▍  | 17/23 [00:04<00:01,  4.05it/s]
 78%|███████▊  | 18/23 [00:04<00:01,  4.05it/s]
 83%|████████▎ | 19/23 [00:04<00:00,  4.05it/s]
 87%|████████▋ | 20/23 [00:04<00:00,  4.05it/s]
 91%|█████████▏| 21/23 [00:05<00:00,  4.05it/s]
 96%|█████████▌| 22/23 [00:05<00:00,  4.05it/s]
100%|██████████| 23/23 [00:05<00:00,  4.05it/s]
100%|██████████| 23/23 [00:05<00:00,  4.09it/s]
Total safe images: 1 out of 1
Version Details
Version ID
f2a4ef407f53a90e7eee353651f49799406eef8f05e4e25c886002821d5910a2
Version Created
October 22, 2025
Run on Replicate →