pwntus/sdxl-gta-v 🖼️🔢📝❓✓ → 🖼️

▶️ 64.6K runs 📅 Aug 2023 ⚙️ Cog 0.8.2
image-inpainting image-to-image text-to-image

About

A fine-tuned SDXL based on GTA V art

Example Output

Prompt:

"video game art, in the style of TOK, one man in a suit, on a luxury yacht"

Output

Example output

Performance Metrics

10.62s Prediction Time
10.62s Total Time
All Input Parameters 
{
  "width": 1024,
  "height": 1024,
  "prompt": "video game art, in the style of TOK, one man in a suit, on a luxury yacht",
  "refine": "no_refiner",
  "scheduler": "K_EULER_ANCESTRAL",
  "lora_scale": 0.8,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "guns",
  "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 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: array • Items Type: string • Items Format: uri

Example Execution Logs 
Using seed: 56434
Prompt: video game art, in the style of <s0><s1>, one man in a suit, on a luxury yacht
txt2img mode
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:07,  3.67it/s]
  7%|▋         | 2/30 [00:00<00:07,  3.66it/s]
 10%|█         | 3/30 [00:00<00:07,  3.66it/s]
 13%|█▎        | 4/30 [00:01<00:07,  3.66it/s]
 17%|█▋        | 5/30 [00:01<00:06,  3.66it/s]
 20%|██        | 6/30 [00:01<00:06,  3.66it/s]
 23%|██▎       | 7/30 [00:01<00:06,  3.66it/s]
 27%|██▋       | 8/30 [00:02<00:06,  3.66it/s]
 30%|███       | 9/30 [00:02<00:05,  3.66it/s]
 33%|███▎      | 10/30 [00:02<00:05,  3.66it/s]
 37%|███▋      | 11/30 [00:03<00:05,  3.66it/s]
 40%|████      | 12/30 [00:03<00:04,  3.66it/s]
 43%|████▎     | 13/30 [00:03<00:04,  3.66it/s]
 47%|████▋     | 14/30 [00:03<00:04,  3.66it/s]
 50%|█████     | 15/30 [00:04<00:04,  3.66it/s]
 53%|█████▎    | 16/30 [00:04<00:03,  3.66it/s]
 57%|█████▋    | 17/30 [00:04<00:03,  3.66it/s]
 60%|██████    | 18/30 [00:04<00:03,  3.66it/s]
 63%|██████▎   | 19/30 [00:05<00:03,  3.66it/s]
 67%|██████▋   | 20/30 [00:05<00:02,  3.66it/s]
 70%|███████   | 21/30 [00:05<00:02,  3.66it/s]
 73%|███████▎  | 22/30 [00:06<00:02,  3.66it/s]
 77%|███████▋  | 23/30 [00:06<00:01,  3.65it/s]
 80%|████████  | 24/30 [00:06<00:01,  3.65it/s]
 83%|████████▎ | 25/30 [00:06<00:01,  3.65it/s]
 87%|████████▋ | 26/30 [00:07<00:01,  3.65it/s]
 90%|█████████ | 27/30 [00:07<00:00,  3.65it/s]
 93%|█████████▎| 28/30 [00:07<00:00,  3.65it/s]
 97%|█████████▋| 29/30 [00:07<00:00,  3.65it/s]
100%|██████████| 30/30 [00:08<00:00,  3.65it/s]
100%|██████████| 30/30 [00:08<00:00,  3.66it/s]
Version Details
Version ID
326cf15ffffc4e2b157d0a1974891cd7893f4542b508be349f3c115412506c5e
Version Created
December 7, 2023
Run on Replicate →