biguloff/vin-diesel 🖼️🔢❓📝✓ → 🖼️

▶️ 10 runs 📅 Nov 2024 ⚙️ Cog 0.11.1

About

Example Output

Prompt:

Vin Diesel, with a powerful, bodybuilder physique, stands confidently in the middle of the AMRT sports nutrition store, wearing a fitted white t-shirt that accentuates his muscular build. His face is lit up with a genuine, happy smile, adding a warm and approachable vibe to his otherwise strong and intense presence. His arms and shoulders appear exceptionally defined under the t-shirt, showcasing his athletic form in ultra-realistic detail. The soft, professional lighting highlights his skin tone and the contours of his muscles, enhancing the realism of his appearance. VDSL

The AMRT store background is sharp and fully in focus, displaying neatly organized shelves filled with sports supplements, protein powders, and energy drinks, each item clearly labeled and arranged to reflect a professional environment. The vivid colors and textures of the products add depth to the scene, contrasting with Diesel’s white t-shirt. The details, from the fabric of his shirt to the items on the shelves, are captured in extreme clarity, rendered in a high-resolution, lifelike quality. The scene has the feel of a cinematic still shot taken with a Canon EOS or an iPhone Pro in cinematic mode, blending elements of editorial magazine cover style with a friendly, approachable energy. The overall composition highlights Vin Diesel’s strength and charisma, making him the focus within the vibrant, professional setting of the AMRT store.

Output

Performance Metrics

13.64s Prediction Time

13.94s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "Vin Diesel, with a powerful, bodybuilder physique, stands confidently in the middle of the AMRT sports nutrition store, wearing a fitted white t-shirt that accentuates his muscular build. His face is lit up with a genuine, happy smile, adding a warm and approachable vibe to his otherwise strong and intense presence. His arms and shoulders appear exceptionally defined under the t-shirt, showcasing his athletic form in ultra-realistic detail. The soft, professional lighting highlights his skin tone and the contours of his muscles, enhancing the realism of his appearance. VDSL\n\nThe AMRT store background is sharp and fully in focus, displaying neatly organized shelves filled with sports supplements, protein powders, and energy drinks, each item clearly labeled and arranged to reflect a professional environment. The vivid colors and textures of the products add depth to the scene, contrasting with Diesel’s white t-shirt. The details, from the fabric of his shirt to the items on the shelves, are captured in extreme clarity, rendered in a high-resolution, lifelike quality. The scene has the feel of a cinematic still shot taken with a Canon EOS or an iPhone Pro in cinematic mode, blending elements of editorial magazine cover style with a friendly, approachable energy. The overall composition highlights Vin Diesel’s strength and charisma, making him the focus within the vibrant, professional setting of the AMRT store.",
  "lora_scale": 1,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 90,
  "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

Using seed: 791
Prompt: Vin Diesel, with a powerful, bodybuilder physique, stands confidently in the middle of the AMRT sports nutrition store, wearing a fitted white t-shirt that accentuates his muscular build. His face is lit up with a genuine, happy smile, adding a warm and approachable vibe to his otherwise strong and intense presence. His arms and shoulders appear exceptionally defined under the t-shirt, showcasing his athletic form in ultra-realistic detail. The soft, professional lighting highlights his skin tone and the contours of his muscles, enhancing the realism of his appearance. VDSL
The AMRT store background is sharp and fully in focus, displaying neatly organized shelves filled with sports supplements, protein powders, and energy drinks, each item clearly labeled and arranged to reflect a professional environment. The vivid colors and textures of the products add depth to the scene, contrasting with Diesel’s white t-shirt. The details, from the fabric of his shirt to the items on the shelves, are captured in extreme clarity, rendered in a high-resolution, lifelike quality. The scene has the feel of a cinematic still shot taken with a Canon EOS or an iPhone Pro in cinematic mode, blending elements of editorial magazine cover style with a friendly, approachable energy. The overall composition highlights Vin Diesel’s strength and charisma, making him the focus within the vibrant, professional setting of the AMRT store.
[!] txt2img mode
Using dev model
free=6505625649152
Downloading weights
2024-11-11T10:44:27Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmph3ww9vbh/weights url=https://replicate.delivery/xezq/unLAkb62Gt5QKlwsBfo23EraoqqnsIskUvkFkxikErZPh83JA/trained_model.tar
2024-11-11T10:44:31Z | INFO  | [ Complete ] dest=/tmp/tmph3ww9vbh/weights size="344 MB" total_elapsed=3.765s url=https://replicate.delivery/xezq/unLAkb62Gt5QKlwsBfo23EraoqqnsIskUvkFkxikErZPh83JA/trained_model.tar
Downloaded weights in 3.80s
Loaded LoRAs in 4.28s
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:08,  3.07it/s]
  7%|▋         | 2/28 [00:00<00:07,  3.43it/s]
 11%|█         | 3/28 [00:00<00:07,  3.26it/s]
 14%|█▍        | 4/28 [00:01<00:07,  3.18it/s]
 18%|█▊        | 5/28 [00:01<00:07,  3.14it/s]
 21%|██▏       | 6/28 [00:01<00:07,  3.12it/s]
 25%|██▌       | 7/28 [00:02<00:06,  3.10it/s]
 29%|██▊       | 8/28 [00:02<00:06,  3.09it/s]
 32%|███▏      | 9/28 [00:02<00:06,  3.08it/s]
 36%|███▌      | 10/28 [00:03<00:05,  3.08it/s]
 39%|███▉      | 11/28 [00:03<00:05,  3.08it/s]
 43%|████▎     | 12/28 [00:03<00:05,  3.08it/s]
 46%|████▋     | 13/28 [00:04<00:04,  3.07it/s]
 50%|█████     | 14/28 [00:04<00:04,  3.07it/s]
 54%|█████▎    | 15/28 [00:04<00:04,  3.07it/s]
 57%|█████▋    | 16/28 [00:05<00:03,  3.07it/s]
 61%|██████    | 17/28 [00:05<00:03,  3.07it/s]
 64%|██████▍   | 18/28 [00:05<00:03,  3.07it/s]
 68%|██████▊   | 19/28 [00:06<00:02,  3.07it/s]
 71%|███████▏  | 20/28 [00:06<00:02,  3.07it/s]
 75%|███████▌  | 21/28 [00:06<00:02,  3.07it/s]
 79%|███████▊  | 22/28 [00:07<00:01,  3.07it/s]
 82%|████████▏ | 23/28 [00:07<00:01,  3.07it/s]
 86%|████████▌ | 24/28 [00:07<00:01,  3.07it/s]
 89%|████████▉ | 25/28 [00:08<00:00,  3.07it/s]
 93%|█████████▎| 26/28 [00:08<00:00,  3.07it/s]
 96%|█████████▋| 27/28 [00:08<00:00,  3.07it/s]
100%|██████████| 28/28 [00:09<00:00,  3.07it/s]
100%|██████████| 28/28 [00:09<00:00,  3.09it/s]

Version Details

Version ID: f50356c018c253a06d57f1f4b18cb1b47af893ac48d13c7367aaac68fa0310b9
Version Created: November 11, 2024

Run on Replicate →