aicapcut/blue-pencil-v600-optimized 🖼️🔢📝❓ → 🖼️

▶️ 248 runs 📅 May 2024 ⚙️ Cog 0.9.6

About

Optimized model

Example Output

Prompt:

"urban, evening, streetlights, bustling, emotional reunion, youth, nostalgia, tension, affection, subtle romance, warm lighting, intimate moments, unspoken feelings, dynamic characters, soft shadows, city street, sunset, traffic lights, luggage, smoking, exhaustion, casual encounter, childhood friends, emotional distance, awkwardness, snack bag, college atmosphere, text messages, concern, protective gesture, two young man"

Output

Performance Metrics

20.63s Prediction Time

180.14s Total Time

All Input Parameters

{
  "seed": 51036,
  "width": 1280,
  "height": 720,
  "prompt": "urban, evening, streetlights, bustling, emotional reunion, youth, nostalgia, tension, affection, subtle romance, warm lighting, intimate moments, unspoken feelings, dynamic characters, soft shadows, city street, sunset, traffic lights, luggage, smoking, exhaustion, casual encounter, childhood friends, emotional distance, awkwardness, snack bag, college atmosphere, text messages, concern, protective gesture, two young man",
  "strength": 0.7,
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 4,
  "guidance_scale": 6,
  "negative_prompt": "text",
  "num_inference_steps": 40
}

Input Parameters

mask Type: string: Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.
seed Type: integer: Random seed. Leave blank to randomize the seed
image Type: string: Input image for img2img or inpaint mode
width Type: integerDefault: 1024: Width of output image
height Type: integerDefault: 1024: Height of output image
prompt Type: stringDefault: abstract beauty, centered, looking at the camera, approaching perfection, dynamic, moonlight, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, art by Carne Griffiths and Wadim Kashin: Input prompt
strength Type: numberDefault: 0.8Range: 0 - 1: Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image
scheduler Default: K_EULER_ANCESTRAL: scheduler
lora_scale Type: numberDefault: 0.6Range: 0 - 1: LoRA additive scale. Only applicable on trained models.
num_outputs Type: integerDefault: 1Range: 1 - 4: Number of images to output.
lora_weights Type: string: Replicate LoRA weights to use. Leave blank to use the default weights.
guidance_scale Type: numberDefault: 7Range: 1 - 50: Scale for classifier-free guidance
negative_prompt Type: stringDefault: (worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4), (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name:1.2), (blur, blurry, grainy), morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur:1.3), (3D ,3D Game, 3D Game Scene, 3D Character:1.1), (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities:1.3): Negative Input prompt
num_inference_steps Type: integerDefault: 40Range: 1 - 500: Number of denoising steps

Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs

Using seed: 51036
Prompt: urban, evening, streetlights, bustling, emotional reunion, youth, nostalgia, tension, affection, subtle romance, warm lighting, intimate moments, unspoken feelings, dynamic characters, soft shadows, city street, sunset, traffic lights, luggage, smoking, exhaustion, casual encounter, childhood friends, emotional distance, awkwardness, snack bag, college atmosphere, text messages, concern, protective gesture, two young man
txt2img mode
interval 3 bid 5
Token indices sequence length is longer than the specified maximum sequence length for this model (85 > 77). Running this sequence through the model will result in indexing errors
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['concern, protective gesture, two young man', 'concern, protective gesture, two young man', 'concern, protective gesture, two young man', 'concern, protective gesture, two young man']
Token indices sequence length is longer than the specified maximum sequence length for this model (85 > 77). Running this sequence through the model will result in indexing errors
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['concern, protective gesture, two young man', 'concern, protective gesture, two young man', 'concern, protective gesture, two young man', 'concern, protective gesture, two young man']
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:00<00:34,  1.14it/s]
  5%|▌         | 2/40 [00:01<00:18,  2.06it/s]
  8%|▊         | 3/40 [00:01<00:13,  2.78it/s]
 10%|█         | 4/40 [00:01<00:16,  2.13it/s]
 12%|█▎        | 5/40 [00:02<00:13,  2.66it/s]
 15%|█▌        | 6/40 [00:02<00:10,  3.12it/s]
 18%|█▊        | 7/40 [00:02<00:14,  2.36it/s]
 20%|██        | 8/40 [00:03<00:11,  2.80it/s]
 22%|██▎       | 9/40 [00:03<00:09,  3.21it/s]
 25%|██▌       | 10/40 [00:04<00:12,  2.42it/s]
 28%|██▊       | 11/40 [00:04<00:10,  2.85it/s]
 30%|███       | 12/40 [00:04<00:08,  3.24it/s]
 32%|███▎      | 13/40 [00:05<00:11,  2.44it/s]
 35%|███▌      | 14/40 [00:05<00:09,  2.86it/s]
 38%|███▊      | 15/40 [00:05<00:07,  3.24it/s]
 40%|████      | 16/40 [00:06<00:09,  2.45it/s]
 42%|████▎     | 17/40 [00:06<00:08,  2.86it/s]
 45%|████▌     | 18/40 [00:06<00:06,  3.24it/s]
 48%|████▊     | 19/40 [00:07<00:08,  2.44it/s]
 50%|█████     | 20/40 [00:07<00:07,  2.85it/s]
 52%|█████▎    | 21/40 [00:07<00:05,  3.23it/s]
 55%|█████▌    | 22/40 [00:08<00:07,  2.44it/s]
 57%|█████▊    | 23/40 [00:08<00:05,  2.85it/s]
 60%|██████    | 24/40 [00:08<00:04,  3.23it/s]
 62%|██████▎   | 25/40 [00:09<00:06,  2.44it/s]
 65%|██████▌   | 26/40 [00:09<00:04,  2.85it/s]
 68%|██████▊   | 27/40 [00:09<00:04,  3.23it/s]
 70%|███████   | 28/40 [00:10<00:04,  2.44it/s]
 72%|███████▎  | 29/40 [00:10<00:03,  2.85it/s]
 75%|███████▌  | 30/40 [00:10<00:03,  3.23it/s]
 78%|███████▊  | 31/40 [00:11<00:03,  2.44it/s]
 80%|████████  | 32/40 [00:11<00:02,  2.84it/s]
 82%|████████▎ | 33/40 [00:11<00:02,  3.22it/s]
 85%|████████▌ | 34/40 [00:12<00:02,  2.43it/s]
 88%|████████▊ | 35/40 [00:12<00:01,  2.84it/s]
 90%|█████████ | 36/40 [00:13<00:01,  3.22it/s]
 92%|█████████▎| 37/40 [00:13<00:01,  2.44it/s]
 95%|█████████▌| 38/40 [00:13<00:00,  2.85it/s]
 98%|█████████▊| 39/40 [00:14<00:00,  3.23it/s]
100%|██████████| 40/40 [00:14<00:00,  2.45it/s]
100%|██████████| 40/40 [00:14<00:00,  2.71it/s]

Version Details

Version ID: fe75e8edeb469432311cb9854b82b66f9e57fb167586fa3c5a137766fbc87cad
Version Created: May 3, 2024

Run on Replicate →