fofr/sdxl-tng-interior 🖼️🔢📝❓✓ → 🖼️

▶️ 1.3K runs 📅 Aug 2023 ⚙️ Cog v0.8.1+dev
image-to-image interior-design text-to-image

About

SDXL fine-tune of Star Trek Next Generation interiors

Example Output

Prompt:

"A photo in the style of TOK, interior, house - sustainable, minimalist, organic, light-filled, dynamic, efficient, autonomous, connected, harmonious, innovative, detailed, 8k, high resolution, sharp focus"

Output

Example output

Performance Metrics

13.14s Prediction Time
13.15s Total Time
All Input Parameters
{
  "width": 1152,
  "height": 768,
  "prompt": "A photo in the style of TOK, interior, house - sustainable, minimalist, organic, light-filled, dynamic, efficient, autonomous, connected, harmonious, innovative, detailed, 8k, high resolution, sharp focus",
  "refine": "expert_ensemble_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.85,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.95,
  "negative_prompt": "low resolution, blurred, soft, jpeg artefacts, broken, distorted, ugly, disfigured",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}
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: An astronaut riding a rainbow unicorn
Input prompt
refine Default: no_refiner
Which refine style to use
scheduler Default: K_EULER
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.
refine_steps Type: integer
For base_image_refiner, the number of steps to refine, defaults to num_inference_steps
guidance_scale Type: numberDefault: 7.5Range: 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.
high_noise_frac Type: numberDefault: 0.8Range: 0 - 1
For expert_ensemble_refiner, the fraction of noise to use
negative_prompt Type: stringDefault:
Input Negative 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: 50Range: 1 - 500
Number of denoising steps
Output Schema

Output

Type: arrayItems Type: stringItems Format: uri

Example Execution Logs
Using seed: 14896
Prompt: A photo in the style of <s0><s1>, interior, house - sustainable, minimalist, organic, light-filled, dynamic, efficient, autonomous, connected, harmonious, innovative, detailed, 8k, high resolution, sharp focus
txt2img mode
  0%|          | 0/47 [00:00<?, ?it/s]
  2%|▏         | 1/47 [00:00<00:10,  4.35it/s]
  4%|▍         | 2/47 [00:00<00:10,  4.34it/s]
  6%|▋         | 3/47 [00:00<00:10,  4.34it/s]
  9%|▊         | 4/47 [00:00<00:09,  4.34it/s]
 11%|█         | 5/47 [00:01<00:09,  4.33it/s]
 13%|█▎        | 6/47 [00:01<00:09,  4.33it/s]
 15%|█▍        | 7/47 [00:01<00:09,  4.33it/s]
 17%|█▋        | 8/47 [00:01<00:09,  4.33it/s]
 19%|█▉        | 9/47 [00:02<00:08,  4.33it/s]
 21%|██▏       | 10/47 [00:02<00:08,  4.33it/s]
 23%|██▎       | 11/47 [00:02<00:08,  4.32it/s]
 26%|██▌       | 12/47 [00:02<00:08,  4.33it/s]
 28%|██▊       | 13/47 [00:03<00:07,  4.32it/s]
 30%|██▉       | 14/47 [00:03<00:07,  4.32it/s]
 32%|███▏      | 15/47 [00:03<00:07,  4.32it/s]
 34%|███▍      | 16/47 [00:03<00:07,  4.33it/s]
 36%|███▌      | 17/47 [00:03<00:06,  4.33it/s]
 38%|███▊      | 18/47 [00:04<00:06,  4.32it/s]
 40%|████      | 19/47 [00:04<00:06,  4.32it/s]
 43%|████▎     | 20/47 [00:04<00:06,  4.32it/s]
 45%|████▍     | 21/47 [00:04<00:06,  4.32it/s]
 47%|████▋     | 22/47 [00:05<00:05,  4.32it/s]
 49%|████▉     | 23/47 [00:05<00:05,  4.32it/s]
 51%|█████     | 24/47 [00:05<00:05,  4.32it/s]
 53%|█████▎    | 25/47 [00:05<00:05,  4.31it/s]
 55%|█████▌    | 26/47 [00:06<00:04,  4.32it/s]
 57%|█████▋    | 27/47 [00:06<00:04,  4.31it/s]
 60%|█████▉    | 28/47 [00:06<00:04,  4.31it/s]
 62%|██████▏   | 29/47 [00:06<00:04,  4.31it/s]
 64%|██████▍   | 30/47 [00:06<00:03,  4.31it/s]
 66%|██████▌   | 31/47 [00:07<00:03,  4.31it/s]
 68%|██████▊   | 32/47 [00:07<00:03,  4.31it/s]
 70%|███████   | 33/47 [00:07<00:03,  4.31it/s]
 72%|███████▏  | 34/47 [00:07<00:03,  4.31it/s]
 74%|███████▍  | 35/47 [00:08<00:02,  4.31it/s]
 77%|███████▋  | 36/47 [00:08<00:02,  4.31it/s]
 79%|███████▊  | 37/47 [00:08<00:02,  4.31it/s]
 81%|████████  | 38/47 [00:08<00:02,  4.31it/s]
 83%|████████▎ | 39/47 [00:09<00:01,  4.31it/s]
 85%|████████▌ | 40/47 [00:09<00:01,  4.31it/s]
 87%|████████▋ | 41/47 [00:09<00:01,  4.31it/s]
 89%|████████▉ | 42/47 [00:09<00:01,  4.30it/s]
 91%|█████████▏| 43/47 [00:09<00:00,  4.30it/s]
 94%|█████████▎| 44/47 [00:10<00:00,  4.30it/s]
 96%|█████████▌| 45/47 [00:10<00:00,  4.30it/s]
 98%|█████████▊| 46/47 [00:10<00:00,  4.30it/s]
100%|██████████| 47/47 [00:10<00:00,  4.30it/s]
100%|██████████| 47/47 [00:10<00:00,  4.32it/s]
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:00,  5.60it/s]
 67%|██████▋   | 2/3 [00:00<00:00,  5.56it/s]
100%|██████████| 3/3 [00:00<00:00,  5.56it/s]
100%|██████████| 3/3 [00:00<00:00,  5.56it/s]
Version Details
Version ID
45f1d0cf3445f54d4b19a2a03e53b15abd7237ea72e2fb4824b193ffa429e31f
Version Created
August 27, 2023
Run on Replicate →