leonardoa2/masc 🖼️🔢❓📝✓ → 🖼️

▶️ 443 runs 📅 Mar 2025 ⚙️ Cog 0.13.7
image-inpainting image-to-image lora text-to-image

About

Example Output

Prompt:

"

A cinematic, intimate moment captured with a flash-lit aesthetic, evoking the raw, voyeuristic energy of documentary photography. The composition is close-up and personal, with subjects deeply engaged in their environments—whether embracing, conversing, or in contemplative solitude.

The lighting is dramatic and varied: direct flash for harsh, high-contrast club or nightlife scenes with deep shadows and saturated colors, or soft, warm golden-hour light for outdoor portraits, creating a dewy, glowing filter effect on the skin. This glow gives a dreamlike quality, enhancing the subjects’ natural textures, from sweat and water droplets on skin to soft reflections on fabric.

The color palette is rich, moody, and nostalgic, with warm hues of amber, deep reds, and inky blues in nighttime and indoor settings, contrasting with cooler pastel tones and soft greens in outdoor sunlit moments. Film-like grain and subtle halation effects emphasize the analog aesthetic, making each image feel tangible and raw.

The subjects exude a mix of confidence and vulnerability. Their expressions feel unguarded, spontaneous, and deeply personal. They are often immersed in fleeting moments of passion, reflection, or deep conversation. Some subjects gaze directly at the camera with an intense, almost cinematic stare, while others are lost in thought, looking away.

The environments range from dimly lit, cluttered interiors filled with personal objects—creating an intimate, lived-in feel—to open, sun-drenched natural settings, like rocky beaches with shimmering blue water and soft, overexposed skies. Spaces feel immersive and tactile, filled with everyday textures like peeling walls, patterned fabrics, and handwritten notes.

Technical details:

35mm film-like texture, with subtle grain and a hint of motion blur
A mix of sharp focus on the subject with soft, blurred backgrounds to create depth
Flash photography for high-contrast nightlife moments, capturing skin highlights
Sun-dappled, golden-hour glow for dreamy, ethereal softness
Compositions with slightly off-kilter framing, mimicking the spontaneity of candid shots
Color grading reminiscent of classic fashion and documentary photographers from the 1980s-2000s
The overall mood is nostalgic, intimate, and cinematic—blending elements of youth culture, queer joy, fleeting human connections, and the quiet poetry of daily life. The images feel like found moments, fragments of a story untold. all this in the style of TOKMASC NO WOMEN

"

Output

Example output

Performance Metrics

9.80s Prediction Time
9.91s Total Time
All Input Parameters
{
  "model": "dev",
  "prompt": "A cinematic, intimate moment captured with a flash-lit aesthetic, evoking the raw, voyeuristic energy of documentary photography. The composition is close-up and personal, with subjects deeply engaged in their environments—whether embracing, conversing, or in contemplative solitude.\n\nThe lighting is dramatic and varied: direct flash for harsh, high-contrast club or nightlife scenes with deep shadows and saturated colors, or soft, warm golden-hour light for outdoor portraits, creating a dewy, glowing filter effect on the skin. This glow gives a dreamlike quality, enhancing the subjects’ natural textures, from sweat and water droplets on skin to soft reflections on fabric.\n\nThe color palette is rich, moody, and nostalgic, with warm hues of amber, deep reds, and inky blues in nighttime and indoor settings, contrasting with cooler pastel tones and soft greens in outdoor sunlit moments. Film-like grain and subtle halation effects emphasize the analog aesthetic, making each image feel tangible and raw.\n\nThe subjects exude a mix of confidence and vulnerability. Their expressions feel unguarded, spontaneous, and deeply personal. They are often immersed in fleeting moments of passion, reflection, or deep conversation. Some subjects gaze directly at the camera with an intense, almost cinematic stare, while others are lost in thought, looking away.\n\nThe environments range from dimly lit, cluttered interiors filled with personal objects—creating an intimate, lived-in feel—to open, sun-drenched natural settings, like rocky beaches with shimmering blue water and soft, overexposed skies. Spaces feel immersive and tactile, filled with everyday textures like peeling walls, patterned fabrics, and handwritten notes.\n\nTechnical details:\n\n35mm film-like texture, with subtle grain and a hint of motion blur\nA mix of sharp focus on the subject with soft, blurred backgrounds to create depth\nFlash photography for high-contrast nightlife moments, capturing skin highlights\nSun-dappled, golden-hour glow for dreamy, ethereal softness\nCompositions with slightly off-kilter framing, mimicking the spontaneity of candid shots\nColor grading reminiscent of classic fashion and documentary photographers from the 1980s-2000s\nThe overall mood is nostalgic, intimate, and cinematic—blending elements of youth culture, queer joy, fleeting human connections, and the quiet poetry of daily life. The images feel like found moments, fragments of a story untold. all this in the style of TOKMASC NO WOMEN",
  "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: arrayItems Type: stringItems Format: uri

Example Execution Logs
Loaded LoRAs in 2.55s
Using seed: 29645
Prompt: A cinematic, intimate moment captured with a flash-lit aesthetic, evoking the raw, voyeuristic energy of documentary photography. The composition is close-up and personal, with subjects deeply engaged in their environments—whether embracing, conversing, or in contemplative solitude.
The lighting is dramatic and varied: direct flash for harsh, high-contrast club or nightlife scenes with deep shadows and saturated colors, or soft, warm golden-hour light for outdoor portraits, creating a dewy, glowing filter effect on the skin. This glow gives a dreamlike quality, enhancing the subjects’ natural textures, from sweat and water droplets on skin to soft reflections on fabric.
The color palette is rich, moody, and nostalgic, with warm hues of amber, deep reds, and inky blues in nighttime and indoor settings, contrasting with cooler pastel tones and soft greens in outdoor sunlit moments. Film-like grain and subtle halation effects emphasize the analog aesthetic, making each image feel tangible and raw.
The subjects exude a mix of confidence and vulnerability. Their expressions feel unguarded, spontaneous, and deeply personal. They are often immersed in fleeting moments of passion, reflection, or deep conversation. Some subjects gaze directly at the camera with an intense, almost cinematic stare, while others are lost in thought, looking away.
The environments range from dimly lit, cluttered interiors filled with personal objects—creating an intimate, lived-in feel—to open, sun-drenched natural settings, like rocky beaches with shimmering blue water and soft, overexposed skies. Spaces feel immersive and tactile, filled with everyday textures like peeling walls, patterned fabrics, and handwritten notes.
Technical details:
35mm film-like texture, with subtle grain and a hint of motion blur
A mix of sharp focus on the subject with soft, blurred backgrounds to create depth
Flash photography for high-contrast nightlife moments, capturing skin highlights
Sun-dappled, golden-hour glow for dreamy, ethereal softness
Compositions with slightly off-kilter framing, mimicking the spontaneity of candid shots
Color grading reminiscent of classic fashion and documentary photographers from the 1980s-2000s
The overall mood is nostalgic, intimate, and cinematic—blending elements of youth culture, queer joy, fleeting human connections, and the quiet poetry of daily life. The images feel like found moments, fragments of a story untold. all this in the style of TOKMASC NO WOMEN
[!] txt2img mode
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:06,  4.05it/s]
  7%|▋         | 2/28 [00:00<00:05,  4.56it/s]
 11%|█         | 3/28 [00:00<00:05,  4.30it/s]
 14%|█▍        | 4/28 [00:00<00:05,  4.20it/s]
 18%|█▊        | 5/28 [00:01<00:05,  4.15it/s]
 21%|██▏       | 6/28 [00:01<00:05,  4.10it/s]
 25%|██▌       | 7/28 [00:01<00:05,  4.08it/s]
 29%|██▊       | 8/28 [00:01<00:04,  4.06it/s]
 32%|███▏      | 9/28 [00:02<00:04,  4.06it/s]
 36%|███▌      | 10/28 [00:02<00:04,  4.05it/s]
 39%|███▉      | 11/28 [00:02<00:04,  4.05it/s]
 43%|████▎     | 12/28 [00:02<00:03,  4.04it/s]
 46%|████▋     | 13/28 [00:03<00:03,  4.05it/s]
 50%|█████     | 14/28 [00:03<00:03,  4.04it/s]
 54%|█████▎    | 15/28 [00:03<00:03,  4.04it/s]
 57%|█████▋    | 16/28 [00:03<00:02,  4.03it/s]
 61%|██████    | 17/28 [00:04<00:02,  4.02it/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,  4.03it/s]
 82%|████████▏ | 23/28 [00:05<00:01,  4.02it/s]
 86%|████████▌ | 24/28 [00:05<00:00,  4.02it/s]
 89%|████████▉ | 25/28 [00:06<00:00,  4.01it/s]
 93%|█████████▎| 26/28 [00:06<00:00,  4.02it/s]
 96%|█████████▋| 27/28 [00:06<00:00,  4.01it/s]
100%|██████████| 28/28 [00:06<00:00,  4.02it/s]
100%|██████████| 28/28 [00:06<00:00,  4.06it/s]
Total safe images: 1 out of 1
Version Details
Version ID
3ddc091226a6d82d8eceaba6e104c6020dd9c836188b98088571daef77d6c082
Version Created
March 7, 2025
Run on Replicate →