leonardoa2/cult-contemplazione 🖼️🔢❓📝✓ → 🖼️

▶️ 364 runs 📅 Mar 2025 ⚙️ Cog 0.13.7
image-inpainting image-to-image lora text-to-image

About

Example Output

Prompt:

"

"A raw, grainy 35mm film photograph, captured in near-total darkness—only a single, violent burst of flash reveals fragmented details, carving stark highlights into the void. The image, taken in secrecy, feels stolen, intrusive, imperfect—an unfiltered glimpse into something that was never meant to be seen. The oppressive darkness swallows everything beyond the immediate flash’s reach, making the moment feel isolated, disorienting, as if suspended in an abyss.

Two figures, cloaked in heavy, white robes adorned with cryptic, minimal embroidery, are caught in the frame, their forms barely materializing from the shadows. The flash scorches their fabric with overexposed highlights, while the deep grain and multiple exposure distortions cause their bodies to flicker in and out of focus—a ghostly, mechanical movement frozen mid-action.

One figure is in the process of forcefully placing a rigid, brutalist metal mask onto the other. The mask has a geometric, industrial design, tapering down into a sharp form with two large, circular eye holes that stare blankly. Its hard, metallic surface reflects the harsh flash, creating unnatural, jagged highlights that contrast sharply against the surrounding darkness. The figure receiving the mask remains tense, their hands twitching slightly, their form slightly distorted by the multi-exposure, giving the impression that they are flickering between submission and resistance.

The environment is raw, industrial, and brutalist—an empty, lifeless concrete space, its edges barely visible beyond the reach of the flash. There is no context, no escape—just an act frozen in time. The only details that emerge from the void are the stark textures of fabric, steel, and cold hands gripping the mask.

The imperfections of the film—harsh contrast, deep grain, erratic multi-exposure blur, and the aggressive flash—turn the image into something unsettling, documentary-like, yet unreal. It feels like an unrepeatable, haunted moment, a silent initiation or an act of transformation caught in secrecy. An industrial ritual, a brutalist offering, a ceremony where faith and machinery collide in the absolute void. use tokcontemplazione3

"

Output

Example output

Performance Metrics

7.80s Prediction Time
9.08s Total Time
All Input Parameters
{
  "model": "dev",
  "prompt": "\"A raw, grainy 35mm film photograph, captured in near-total darkness—only a single, violent burst of flash reveals fragmented details, carving stark highlights into the void. The image, taken in secrecy, feels stolen, intrusive, imperfect—an unfiltered glimpse into something that was never meant to be seen. The oppressive darkness swallows everything beyond the immediate flash’s reach, making the moment feel isolated, disorienting, as if suspended in an abyss.\n\nTwo figures, cloaked in heavy, white robes adorned with cryptic, minimal embroidery, are caught in the frame, their forms barely materializing from the shadows. The flash scorches their fabric with overexposed highlights, while the deep grain and multiple exposure distortions cause their bodies to flicker in and out of focus—a ghostly, mechanical movement frozen mid-action.\n\nOne figure is in the process of forcefully placing a rigid, brutalist metal mask onto the other. The mask has a geometric, industrial design, tapering down into a sharp form with two large, circular eye holes that stare blankly. Its hard, metallic surface reflects the harsh flash, creating unnatural, jagged highlights that contrast sharply against the surrounding darkness. The figure receiving the mask remains tense, their hands twitching slightly, their form slightly distorted by the multi-exposure, giving the impression that they are flickering between submission and resistance.\n\nThe environment is raw, industrial, and brutalist—an empty, lifeless concrete space, its edges barely visible beyond the reach of the flash. There is no context, no escape—just an act frozen in time. The only details that emerge from the void are the stark textures of fabric, steel, and cold hands gripping the mask.\n\nThe imperfections of the film—harsh contrast, deep grain, erratic multi-exposure blur, and the aggressive flash—turn the image into something unsettling, documentary-like, yet unreal. It feels like an unrepeatable, haunted moment, a silent initiation or an act of transformation caught in secrecy. An industrial ritual, a brutalist offering, a ceremony where faith and machinery collide in the absolute void. use tokcontemplazione3",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "16:9",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 100,
  "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: arrayItems Type: stringItems Format: uri

Example Execution Logs
Loaded LoRAs in 0.56s
Using seed: 42020
Prompt: "A raw, grainy 35mm film photograph, captured in near-total darkness—only a single, violent burst of flash reveals fragmented details, carving stark highlights into the void. The image, taken in secrecy, feels stolen, intrusive, imperfect—an unfiltered glimpse into something that was never meant to be seen. The oppressive darkness swallows everything beyond the immediate flash’s reach, making the moment feel isolated, disorienting, as if suspended in an abyss.
Two figures, cloaked in heavy, white robes adorned with cryptic, minimal embroidery, are caught in the frame, their forms barely materializing from the shadows. The flash scorches their fabric with overexposed highlights, while the deep grain and multiple exposure distortions cause their bodies to flicker in and out of focus—a ghostly, mechanical movement frozen mid-action.
One figure is in the process of forcefully placing a rigid, brutalist metal mask onto the other. The mask has a geometric, industrial design, tapering down into a sharp form with two large, circular eye holes that stare blankly. Its hard, metallic surface reflects the harsh flash, creating unnatural, jagged highlights that contrast sharply against the surrounding darkness. The figure receiving the mask remains tense, their hands twitching slightly, their form slightly distorted by the multi-exposure, giving the impression that they are flickering between submission and resistance.
The environment is raw, industrial, and brutalist—an empty, lifeless concrete space, its edges barely visible beyond the reach of the flash. There is no context, no escape—just an act frozen in time. The only details that emerge from the void are the stark textures of fabric, steel, and cold hands gripping the mask.
The imperfections of the film—harsh contrast, deep grain, erratic multi-exposure blur, and the aggressive flash—turn the image into something unsettling, documentary-like, yet unreal. It feels like an unrepeatable, haunted moment, a silent initiation or an act of transformation caught in secrecy. An industrial ritual, a brutalist offering, a ceremony where faith and machinery collide in the absolute void. use tokcontemplazione3
[!] txt2img mode
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:06,  4.01it/s]
  7%|▋         | 2/28 [00:00<00:05,  4.53it/s]
 11%|█         | 3/28 [00:00<00:05,  4.29it/s]
 14%|█▍        | 4/28 [00:00<00:05,  4.18it/s]
 18%|█▊        | 5/28 [00:01<00:05,  4.12it/s]
 21%|██▏       | 6/28 [00:01<00:05,  4.09it/s]
 25%|██▌       | 7/28 [00:01<00:05,  4.07it/s]
 29%|██▊       | 8/28 [00:01<00:04,  4.05it/s]
 32%|███▏      | 9/28 [00:02<00:04,  4.04it/s]
 36%|███▌      | 10/28 [00:02<00:04,  4.03it/s]
 39%|███▉      | 11/28 [00:02<00:04,  4.03it/s]
 43%|████▎     | 12/28 [00:02<00:03,  4.03it/s]
 46%|████▋     | 13/28 [00:03<00:03,  4.02it/s]
 50%|█████     | 14/28 [00:03<00:03,  4.02it/s]
 54%|█████▎    | 15/28 [00:03<00:03,  4.03it/s]
 57%|█████▋    | 16/28 [00:03<00:02,  4.02it/s]
 61%|██████    | 17/28 [00:04<00:02,  4.01it/s]
 64%|██████▍   | 18/28 [00:04<00:02,  4.02it/s]
 68%|██████▊   | 19/28 [00:04<00:02,  4.01it/s]
 71%|███████▏  | 20/28 [00:04<00:01,  4.02it/s]
 75%|███████▌  | 21/28 [00:05<00:01,  4.02it/s]
 79%|███████▊  | 22/28 [00:05<00:01,  4.01it/s]
 82%|████████▏ | 23/28 [00:05<00:01,  4.01it/s]
 86%|████████▌ | 24/28 [00:05<00:00,  4.02it/s]
 89%|████████▉ | 25/28 [00:06<00:00,  4.02it/s]
 93%|█████████▎| 26/28 [00:06<00:00,  4.02it/s]
 96%|█████████▋| 27/28 [00:06<00:00,  4.02it/s]
100%|██████████| 28/28 [00:06<00:00,  4.02it/s]
100%|██████████| 28/28 [00:06<00:00,  4.05it/s]
Total safe images: 1 out of 1
Version Details
Version ID
50f1ed1a0d2dd6b4cbf4fe5e15ef0bdb9f8e04ab753c016bc8ce78144546f2ea
Version Created
March 10, 2025
Run on Replicate →