pagebrain/lyriel-v1-6 🖼️🔢❓📝✓ → 🖼️

▶️ 1.5K runs 📅 Sep 2023 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper ⚖️ License

image-generation img2img inpainting negative-embeddings realistic-images text-to-image

About

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

Example Output

Prompt:

"8k beautiful girl avatar, 1girl, intricate, elegant, highly detailed, detail face, blonde, symetrical, majestic, 35mm, digital photography, fashion photography, (masterpiece, sidelighting), (soft light, sharp:1.1), (hyperdetailed), hdr, blurry, blurry_background, blurry_foreground, scottish highlands, winter, snow falling"

Output

Performance Metrics

6.74s Prediction Time

6.67s Total Time

All Input Parameters

{
  "width": "512",
  "height": "512",
  "prompt": "8k beautiful girl avatar, 1girl, intricate, elegant, highly detailed, detail face, blonde, symetrical, majestic, 35mm, digital photography, fashion photography, (masterpiece, sidelighting), (soft light, sharp:1.1), (hyperdetailed), hdr, blurry, blurry_background, blurry_foreground, scottish highlands, winter, snow falling",
  "scheduler": "KarrasDPM",
  "num_outputs": 1,
  "guidance_scale": 3,
  "safety_checker": false,
  "negative_prompt": "realisticvision-negative-embedding, EasyNegative, negative_hand-neg, ng_deepnegative_v1_75t, FastNegativeV2",
  "prompt_strength": 0.8,
  "num_inference_steps": 30
}

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

Example Execution Logs

Using seed: 23482
Prompt: 8k beautiful girl avatar, 1girl, intricate, elegant, highly detailed, detail face, blonde, symetrical, majestic, 35mm, digital photography, fashion photography, (masterpiece, sidelighting), (soft light, sharp:1.1), (hyperdetailed), hdr, blurry, blurry_background, blurry_foreground, scottish highlands, winter, snow falling
txt2img mode
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['falling']
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:07,  3.75it/s]
  7%|▋         | 2/30 [00:00<00:06,  4.61it/s]
 10%|█         | 3/30 [00:00<00:05,  4.99it/s]
 13%|█▎        | 4/30 [00:00<00:05,  5.20it/s]
 17%|█▋        | 5/30 [00:00<00:04,  5.32it/s]
 20%|██        | 6/30 [00:01<00:04,  5.38it/s]
 23%|██▎       | 7/30 [00:01<00:04,  5.35it/s]
 27%|██▋       | 8/30 [00:01<00:04,  5.41it/s]
 30%|███       | 9/30 [00:01<00:03,  5.45it/s]
 33%|███▎      | 10/30 [00:01<00:03,  5.47it/s]
 37%|███▋      | 11/30 [00:02<00:03,  5.50it/s]
 40%|████      | 12/30 [00:02<00:03,  5.46it/s]
 43%|████▎     | 13/30 [00:02<00:03,  5.44it/s]
 47%|████▋     | 14/30 [00:02<00:02,  5.47it/s]
 50%|█████     | 15/30 [00:02<00:02,  5.48it/s]
 53%|█████▎    | 16/30 [00:02<00:02,  5.50it/s]
 57%|█████▋    | 17/30 [00:03<00:02,  5.50it/s]
 60%|██████    | 18/30 [00:03<00:02,  5.45it/s]
 63%|██████▎   | 19/30 [00:03<00:02,  5.48it/s]
 67%|██████▋   | 20/30 [00:03<00:01,  5.49it/s]
 70%|███████   | 21/30 [00:03<00:01,  5.51it/s]
 73%|███████▎  | 22/30 [00:04<00:01,  5.50it/s]
 77%|███████▋  | 23/30 [00:04<00:01,  5.47it/s]
 80%|████████  | 24/30 [00:04<00:01,  5.48it/s]
 83%|████████▎ | 25/30 [00:04<00:00,  5.48it/s]
 87%|████████▋ | 26/30 [00:04<00:00,  5.48it/s]
 90%|█████████ | 27/30 [00:05<00:00,  5.50it/s]
 93%|█████████▎| 28/30 [00:05<00:00,  5.49it/s]
 97%|█████████▋| 29/30 [00:05<00:00,  5.46it/s]
100%|██████████| 30/30 [00:05<00:00,  5.47it/s]
100%|██████████| 30/30 [00:05<00:00,  5.40it/s]

Version Details

Version ID: 8b3faef2fd1d441f6d3e0cdf9364f1610b4fe08e2c5f96c8732d0309e0123a49
Version Created: September 10, 2023

Run on Replicate →