leonardoa2/cult6-mask 🖼️🔢❓📝✓ → 🖼️

▶️ 98 runs 📅 Mar 2025 ⚙️ Cog 0.13.7

About

Example Output

Prompt:

A raw, grainy 35mm film photograph, capturing an intense, unfiltered moment under the harsh glare of a direct flash. The extreme overexposure from the flash creates stark, blown-out highlights and deep, crushing shadows, stripping away any sense of depth and immersing the scene in a visceral, almost oppressive atmosphere. The image feels stolen—documentary in nature, as if revealing something that was never meant to be seen.

At the center, a close-up of an animal’s thick, coarse fur, its texture violently illuminated by the flash, causing an almost ethereal glow against the void-like darkness of the background. The contrast is brutal—bright, blinding whites of the fur against the cold, reflective surface of a heavy, industrial metal collar strapped tightly around its neck. The metallic surface of the collar flares under the intense light, revealing deep scratches, dents, and signs of oxidation, making it feel aged, functional, and almost ritualistic. the image is fractured by layered motion blur, a stroboscopic effect distorting the body into overlapping gestures, as if caught in a looped ritual. The flickering traces of movement create an eerie sense of repetition, like a sequence of sacred motions being performed again and again.

Jagged, irregular metal spikes protrude aggressively from the collar, their harsh edges catching the flash and scattering fragmented reflections. The spikes appear carelessly welded, twisted, and brutalist in design, reinforcing the object’s utilitarian, almost cruel purpose. Rusted wire coils around sections of the collar, some strands unraveling chaotically, adding to the sense of raw, industrial brutality.

The ground is damp, textured with patches of wild grass and disturbed soil, barely visible in the darkness beyond the flash’s reach. The trees and distant structures dissolve into the void, making the setting feel isolated, liminal, and ominous. The colors are desaturated, washed in deep blues, pale greens, and the stark white of the flash, enhancing the industrial, brutalist aesthetic of the scene.

The motion blur, harsh light, and deep shadows make the image feel alive, as if capturing a moment in an unknown ritual, a mechanical invocation, or an experimental ceremony where faith and technology collide.

The image is relentless in its stark, high-contrast brutality, where the harsh flash transforms an ordinary subject into something alien, uncomfortably intimate, and strikingly raw. use tokpotere

Output

Performance Metrics

9.86s Prediction Time

9.91s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "A raw, grainy 35mm film photograph, capturing an intense, unfiltered moment under the harsh glare of a direct flash. The extreme overexposure from the flash creates stark, blown-out highlights and deep, crushing shadows, stripping away any sense of depth and immersing the scene in a visceral, almost oppressive atmosphere. The image feels stolen—documentary in nature, as if revealing something that was never meant to be seen.\n\nAt the center, a close-up of an animal’s thick, coarse fur, its texture violently illuminated by the flash, causing an almost ethereal glow against the void-like darkness of the background. The contrast is brutal—bright, blinding whites of the fur against the cold, reflective surface of a heavy, industrial metal collar strapped tightly around its neck. The metallic surface of the collar flares under the intense light, revealing deep scratches, dents, and signs of oxidation, making it feel aged, functional, and almost ritualistic.  the image is fractured by layered motion blur, a stroboscopic effect distorting the body into overlapping gestures, as if caught in a looped ritual. The flickering traces of movement create an eerie sense of repetition, like a sequence of sacred motions being performed again and again.\n\nJagged, irregular metal spikes protrude aggressively from the collar, their harsh edges catching the flash and scattering fragmented reflections. The spikes appear carelessly welded, twisted, and brutalist in design, reinforcing the object’s utilitarian, almost cruel purpose. Rusted wire coils around sections of the collar, some strands unraveling chaotically, adding to the sense of raw, industrial brutality.\n\nThe ground is damp, textured with patches of wild grass and disturbed soil, barely visible in the darkness beyond the flash’s reach. The trees and distant structures dissolve into the void, making the setting feel isolated, liminal, and ominous. The colors are desaturated, washed in deep blues, pale greens, and the stark white of the flash, enhancing the industrial, brutalist aesthetic of the scene.\n\nThe motion blur, harsh light, and deep shadows make the image feel alive, as if capturing a moment in an unknown ritual, a mechanical invocation, or an experimental ceremony where faith and technology collide.\n\nThe image is relentless in its stark, high-contrast brutality, where the harsh flash transforms an ordinary subject into something alien, uncomfortably intimate, and strikingly raw. use tokpotere",
  "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: array • Items Type: string • Items Format: uri

Example Execution Logs

free=27444175384576
Downloading weights
2025-03-11T11:24:26Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmptxdt1ud4/weights url=https://replicate.delivery/xezq/K7E7vjeVB0SMTiFRDteiDwTj4m7b6pLUt4BwRcqfhO7GexdRB/trained_model.tar
2025-03-11T11:24:28Z | INFO  | [ Complete ] dest=/tmp/tmptxdt1ud4/weights size="172 MB" total_elapsed=1.632s url=https://replicate.delivery/xezq/K7E7vjeVB0SMTiFRDteiDwTj4m7b6pLUt4BwRcqfhO7GexdRB/trained_model.tar
Downloaded weights in 1.66s
Loaded LoRAs in 2.23s
Using seed: 2885
Prompt: A raw, grainy 35mm film photograph, capturing an intense, unfiltered moment under the harsh glare of a direct flash. The extreme overexposure from the flash creates stark, blown-out highlights and deep, crushing shadows, stripping away any sense of depth and immersing the scene in a visceral, almost oppressive atmosphere. The image feels stolen—documentary in nature, as if revealing something that was never meant to be seen.
At the center, a close-up of an animal’s thick, coarse fur, its texture violently illuminated by the flash, causing an almost ethereal glow against the void-like darkness of the background. The contrast is brutal—bright, blinding whites of the fur against the cold, reflective surface of a heavy, industrial metal collar strapped tightly around its neck. The metallic surface of the collar flares under the intense light, revealing deep scratches, dents, and signs of oxidation, making it feel aged, functional, and almost ritualistic.  the image is fractured by layered motion blur, a stroboscopic effect distorting the body into overlapping gestures, as if caught in a looped ritual. The flickering traces of movement create an eerie sense of repetition, like a sequence of sacred motions being performed again and again.
Jagged, irregular metal spikes protrude aggressively from the collar, their harsh edges catching the flash and scattering fragmented reflections. The spikes appear carelessly welded, twisted, and brutalist in design, reinforcing the object’s utilitarian, almost cruel purpose. Rusted wire coils around sections of the collar, some strands unraveling chaotically, adding to the sense of raw, industrial brutality.
The ground is damp, textured with patches of wild grass and disturbed soil, barely visible in the darkness beyond the flash’s reach. The trees and distant structures dissolve into the void, making the setting feel isolated, liminal, and ominous. The colors are desaturated, washed in deep blues, pale greens, and the stark white of the flash, enhancing the industrial, brutalist aesthetic of the scene.
The motion blur, harsh light, and deep shadows make the image feel alive, as if capturing a moment in an unknown ritual, a mechanical invocation, or an experimental ceremony where faith and technology collide.
The image is relentless in its stark, high-contrast brutality, where the harsh flash transforms an ordinary subject into something alien, uncomfortably intimate, and strikingly raw. use tokpotere
[!] txt2img mode
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:15,  1.70it/s]
  7%|▋         | 2/28 [00:00<00:09,  2.78it/s]
 11%|█         | 3/28 [00:01<00:07,  3.25it/s]
 14%|█▍        | 4/28 [00:01<00:06,  3.52it/s]
 18%|█▊        | 5/28 [00:01<00:06,  3.69it/s]
 21%|██▏       | 6/28 [00:01<00:05,  3.80it/s]
 25%|██▌       | 7/28 [00:02<00:05,  3.86it/s]
 29%|██▊       | 8/28 [00:02<00:05,  3.90it/s]
 32%|███▏      | 9/28 [00:02<00:04,  3.93it/s]
 36%|███▌      | 10/28 [00:02<00:04,  3.95it/s]
 39%|███▉      | 11/28 [00:03<00:04,  3.97it/s]
 43%|████▎     | 12/28 [00:03<00:04,  3.99it/s]
 46%|████▋     | 13/28 [00:03<00:03,  4.00it/s]
 50%|█████     | 14/28 [00:03<00:03,  4.00it/s]
 54%|█████▎    | 15/28 [00:04<00:03,  4.00it/s]
 57%|█████▋    | 16/28 [00:04<00:02,  4.01it/s]
 61%|██████    | 17/28 [00:04<00:02,  4.00it/s]
 64%|██████▍   | 18/28 [00:04<00:02,  4.00it/s]
 68%|██████▊   | 19/28 [00:05<00:02,  4.01it/s]
 71%|███████▏  | 20/28 [00:05<00:01,  4.00it/s]
 75%|███████▌  | 21/28 [00:05<00:01,  4.01it/s]
 79%|███████▊  | 22/28 [00:05<00:01,  4.01it/s]
 82%|████████▏ | 23/28 [00:06<00:01,  4.01it/s]
 86%|████████▌ | 24/28 [00:06<00:00,  4.01it/s]
 89%|████████▉ | 25/28 [00:06<00:00,  4.01it/s]
 93%|█████████▎| 26/28 [00:06<00:00,  4.01it/s]
 96%|█████████▋| 27/28 [00:07<00:00,  3.99it/s]
100%|██████████| 28/28 [00:07<00:00,  3.99it/s]
100%|██████████| 28/28 [00:07<00:00,  3.85it/s]
Total safe images: 1 out of 1

Version Details

Version ID: d5f81830ff577ae97b9923fe0783cdfeda758ce97cb01cd8314e65435ecb340a
Version Created: March 11, 2025

Run on Replicate →