pagebrain/cyberrealistic-v3-3 🖼️🔢❓📝✓ → 🖼️

▶️ 7.0K runs 📅 Sep 2023 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper ⚖️ License
hyperrealism image-generation img2img inpainting photorealism portrait-photography text-to-image

About

T4 GPU, negative embeddings, img2img, inpainting, safety checker, KarrasDPM, pruned fp16 safetensor

Example Output

Prompt:

"a portrait photo of a beautiful woman with curls and lots of freckles, (dirty blonde hair), (face portrait:1.5), dramatic light , Rembrandt lighting scheme, (hyperrealism:1.2), (photorealistic:1.2), shot with Canon EOS 5D Mark IV, detailed face, detailed hair"

Output

Example output

Performance Metrics

13.22s Prediction Time
13.20s Total Time
All Input Parameters
{
  "width": 512,
  "height": 512,
  "prompt": "a portrait photo of a beautiful woman with curls and lots of freckles, (dirty blonde hair), (face portrait:1.5), dramatic light , Rembrandt lighting scheme, (hyperrealism:1.2), (photorealistic:1.2), shot with Canon EOS 5D Mark IV, detailed face, detailed hair",
  "scheduler": "KarrasDPM",
  "num_outputs": 1,
  "guidance_scale": 5,
  "safety_checker": true,
  "negative_prompt": "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation",
  "prompt_strength": 0.8,
  "num_inference_steps": 60
}
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 Default: 512
Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
height Default: 512
Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
prompt Type: string
Input prompt
scheduler Default: K_EULER
scheduler
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of images to output.
guidance_scale Type: numberDefault: 7.5Range: 1 - 20
Scale for classifier-free guidance
safety_checker Type: booleanDefault: true
Safety checker. Disable to expose unfiltered results
negative_prompt Type: string
Specify things to not see in the output. Supported embeddings: realisticvision-negative-embedding, BadDream, EasyNegative, negative_hand-neg, ng_deepnegative_v1_75t, FastNegativeV2, UnrealisticDream
prompt_strength Type: numberDefault: 0.8
Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image
num_inference_steps Type: integerDefault: 50Range: 1 - 500
Number of denoising steps
Output Schema

Output

Type: arrayItems Type: stringItems Format: uri

Example Execution Logs
Using seed: 12889
Prompt: a portrait photo of a beautiful woman with curls and lots of freckles, (dirty blonde hair), (face portrait:1.5), dramatic light , Rembrandt lighting scheme, (hyperrealism:1.2), (photorealistic:1.2), shot with Canon EOS 5D Mark IV, detailed face, detailed hair
txt2img mode
  0%|          | 0/60 [00:00<?, ?it/s]
  2%|▏         | 1/60 [00:00<00:14,  4.08it/s]
  3%|▎         | 2/60 [00:00<00:12,  4.58it/s]
  5%|▌         | 3/60 [00:00<00:11,  4.82it/s]
  7%|▋         | 4/60 [00:00<00:11,  4.94it/s]
  8%|▊         | 5/60 [00:01<00:11,  4.86it/s]
 10%|█         | 6/60 [00:01<00:11,  4.77it/s]
 12%|█▏        | 7/60 [00:01<00:11,  4.81it/s]
 13%|█▎        | 8/60 [00:01<00:10,  4.88it/s]
 15%|█▌        | 9/60 [00:01<00:10,  4.92it/s]
 17%|█▋        | 10/60 [00:02<00:10,  4.82it/s]
 18%|█▊        | 11/60 [00:02<00:10,  4.83it/s]
 20%|██        | 12/60 [00:02<00:09,  4.84it/s]
 22%|██▏       | 13/60 [00:02<00:09,  4.88it/s]
 23%|██▎       | 14/60 [00:02<00:09,  4.87it/s]
 25%|██▌       | 15/60 [00:03<00:09,  4.82it/s]
 27%|██▋       | 16/60 [00:03<00:09,  4.87it/s]
 28%|██▊       | 17/60 [00:03<00:08,  4.91it/s]
 30%|███       | 18/60 [00:03<00:08,  4.94it/s]
 32%|███▏      | 19/60 [00:03<00:08,  4.94it/s]
 33%|███▎      | 20/60 [00:04<00:08,  4.91it/s]
 35%|███▌      | 21/60 [00:04<00:07,  4.93it/s]
 37%|███▋      | 22/60 [00:04<00:07,  4.93it/s]
 38%|███▊      | 23/60 [00:04<00:07,  4.97it/s]
 40%|████      | 24/60 [00:04<00:07,  4.94it/s]
 42%|████▏     | 25/60 [00:05<00:07,  4.93it/s]
 43%|████▎     | 26/60 [00:05<00:06,  4.95it/s]
 45%|████▌     | 27/60 [00:05<00:06,  4.95it/s]
 47%|████▋     | 28/60 [00:05<00:06,  4.96it/s]
 48%|████▊     | 29/60 [00:05<00:06,  4.95it/s]
 50%|█████     | 30/60 [00:06<00:06,  4.92it/s]
 52%|█████▏    | 31/60 [00:06<00:05,  4.94it/s]
 53%|█████▎    | 32/60 [00:06<00:05,  4.94it/s]
 55%|█████▌    | 33/60 [00:06<00:05,  4.96it/s]
 57%|█████▋    | 34/60 [00:06<00:05,  4.94it/s]
 58%|█████▊    | 35/60 [00:07<00:05,  4.93it/s]
 60%|██████    | 36/60 [00:07<00:04,  4.96it/s]
 62%|██████▏   | 37/60 [00:07<00:04,  4.95it/s]
 63%|██████▎   | 38/60 [00:07<00:04,  4.96it/s]
 65%|██████▌   | 39/60 [00:07<00:04,  4.95it/s]
 67%|██████▋   | 40/60 [00:08<00:04,  4.93it/s]
 68%|██████▊   | 41/60 [00:08<00:03,  4.94it/s]
 70%|███████   | 42/60 [00:08<00:03,  4.94it/s]
 72%|███████▏  | 43/60 [00:08<00:03,  4.96it/s]
 73%|███████▎  | 44/60 [00:08<00:03,  4.94it/s]
 75%|███████▌  | 45/60 [00:09<00:03,  4.94it/s]
 77%|███████▋  | 46/60 [00:09<00:02,  4.95it/s]
 78%|███████▊  | 47/60 [00:09<00:02,  4.96it/s]
 80%|████████  | 48/60 [00:09<00:02,  4.96it/s]
 82%|████████▏ | 49/60 [00:09<00:02,  4.93it/s]
 83%|████████▎ | 50/60 [00:10<00:02,  4.94it/s]
 85%|████████▌ | 51/60 [00:10<00:01,  4.93it/s]
 87%|████████▋ | 52/60 [00:10<00:01,  4.94it/s]
 88%|████████▊ | 53/60 [00:10<00:01,  4.96it/s]
 90%|█████████ | 54/60 [00:10<00:01,  4.94it/s]
 92%|█████████▏| 55/60 [00:11<00:01,  4.94it/s]
 93%|█████████▎| 56/60 [00:11<00:00,  4.93it/s]
 95%|█████████▌| 57/60 [00:11<00:00,  4.90it/s]
 97%|█████████▋| 58/60 [00:11<00:00,  4.86it/s]
 98%|█████████▊| 59/60 [00:12<00:00,  4.86it/s]
98%|█████████▊| 59/60 [00:12<00:00,  4.91it/s]
Version Details
Version ID
02d575aeefff93cc32262e65c2784e00bf1af37071a6b6202adf62285c71f559
Version Created
September 10, 2023
Run on Replicate →