lucataco/realvisxl-v2.0 🖼️🔢📝❓✓ → 🖼️

▶️ 288.8K runs 📅 Nov 2023 ⚙️ Cog 0.8.5 🔗 GitHub ⚖️ License
image-inpainting image-to-image text-to-image

About

Implementation of SDXL RealVisXL_V2.0

Example Output

Prompt:

"dark shot, front shot, closeup photo of a 25 y.o latino man, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot"

Output

Example output

Performance Metrics

10.66s Prediction Time
84.76s Total Time
All Input Parameters 
{
  "seed": 1111316861,
  "width": 1024,
  "height": 1024,
  "prompt": "dark shot, front shot, closeup photo of a 25 y.o latino man, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot",
  "scheduler": "DPMSolverMultistep",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "guidance_scale": 7,
  "apply_watermark": true,
  "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth",
  "prompt_strength": 0.8,
  "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: dark shot, front shot, closeup photo of a 25 y.o latino man, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot
Input prompt
scheduler Default: DPMSolverMultistep
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
apply_watermark Type: booleanDefault: true
Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.
negative_prompt Type: stringDefault: (worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth
Negative Input prompt
prompt_strength Type: numberDefault: 0.8Range: 0 - 1
Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image
num_inference_steps Type: integerDefault: 40Range: 1 - 500
Number of denoising steps
disable_safety_checker Type: booleanDefault: false
Disable safety checker for generated images. This feature is only available through the API. See https://replicate.com/docs/how-does-replicate-work#safety
Output Schema

Output

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

Example Execution Logs 
Using seed: 1111316861
Prompt: dark shot, front shot, closeup photo of a 25 y.o latino man, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot
txt2img mode
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:00<00:30,  1.29it/s]
  5%|▌         | 2/40 [00:00<00:16,  2.29it/s]
  8%|▊         | 3/40 [00:01<00:12,  3.04it/s]
 10%|█         | 4/40 [00:01<00:10,  3.60it/s]
 12%|█▎        | 5/40 [00:01<00:08,  3.98it/s]
 15%|█▌        | 6/40 [00:01<00:07,  4.27it/s]
 18%|█▊        | 7/40 [00:01<00:07,  4.48it/s]
 20%|██        | 8/40 [00:02<00:06,  4.62it/s]
 22%|██▎       | 9/40 [00:02<00:06,  4.73it/s]
 25%|██▌       | 10/40 [00:02<00:06,  4.79it/s]
 28%|██▊       | 11/40 [00:02<00:05,  4.83it/s]
 30%|███       | 12/40 [00:02<00:05,  4.87it/s]
 32%|███▎      | 13/40 [00:03<00:05,  4.89it/s]
 35%|███▌      | 14/40 [00:03<00:05,  4.91it/s]
 38%|███▊      | 15/40 [00:03<00:05,  4.92it/s]
 40%|████      | 16/40 [00:03<00:04,  4.93it/s]
 42%|████▎     | 17/40 [00:04<00:04,  4.93it/s]
 45%|████▌     | 18/40 [00:04<00:04,  4.93it/s]
 48%|████▊     | 19/40 [00:04<00:04,  4.93it/s]
 50%|█████     | 20/40 [00:04<00:04,  4.94it/s]
 52%|█████▎    | 21/40 [00:04<00:03,  4.94it/s]
 55%|█████▌    | 22/40 [00:05<00:03,  4.94it/s]
 57%|█████▊    | 23/40 [00:05<00:03,  4.93it/s]
 60%|██████    | 24/40 [00:05<00:03,  4.94it/s]
 62%|██████▎   | 25/40 [00:05<00:03,  4.94it/s]
 65%|██████▌   | 26/40 [00:05<00:02,  4.93it/s]
 68%|██████▊   | 27/40 [00:06<00:02,  4.93it/s]
 70%|███████   | 28/40 [00:06<00:02,  4.93it/s]
 72%|███████▎  | 29/40 [00:06<00:02,  4.93it/s]
 75%|███████▌  | 30/40 [00:06<00:02,  4.93it/s]
 78%|███████▊  | 31/40 [00:06<00:01,  4.93it/s]
 80%|████████  | 32/40 [00:07<00:01,  4.93it/s]
 82%|████████▎ | 33/40 [00:07<00:01,  4.92it/s]
 85%|████████▌ | 34/40 [00:07<00:01,  4.92it/s]
 88%|████████▊ | 35/40 [00:07<00:01,  4.92it/s]
 90%|█████████ | 36/40 [00:07<00:00,  4.92it/s]
 92%|█████████▎| 37/40 [00:08<00:00,  4.92it/s]
 95%|█████████▌| 38/40 [00:08<00:00,  4.93it/s]
 98%|█████████▊| 39/40 [00:08<00:00,  4.92it/s]
100%|██████████| 40/40 [00:08<00:00,  4.93it/s]
100%|██████████| 40/40 [00:08<00:00,  4.61it/s]
Version Details
Version ID
7d6a2f9c4754477b12c14ed2a58f89bb85128edcdd581d24ce58b6926029de08
Version Created
November 9, 2023
Run on Replicate →