fofr/sdxl-vision-pro 🖼️🔢📝❓✓ → 🖼️

▶️ 5.4K runs 📅 Aug 2023 ⚙️ Cog 0.8.2

About

An SDXL fine-tune on Apple Vision Pro

Example Output

Prompt:

"A photo of gandalf wearing a TOK VR headset, faces visible"

Output

Performance Metrics

15.49s Prediction Time

15.48s Total Time

All Input Parameters

{
  "width": 1024,
  "height": 1024,
  "prompt": "A photo of gandalf wearing a TOK VR headset, faces visible",
  "refine": "expert_ensemble_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.95,
  "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: array • Items Type: string • Items Format: uri

Example Execution Logs

Using seed: 16149
Prompt: A photo of gandalf wearing a <s0><s1> VR headset, faces visible
txt2img mode
  0%|          | 0/47 [00:00<?, ?it/s]
  2%|▏         | 1/47 [00:00<00:12,  3.66it/s]
  4%|▍         | 2/47 [00:00<00:12,  3.67it/s]
  6%|▋         | 3/47 [00:00<00:11,  3.67it/s]
  9%|▊         | 4/47 [00:01<00:11,  3.67it/s]
 11%|█         | 5/47 [00:01<00:11,  3.66it/s]
 13%|█▎        | 6/47 [00:01<00:11,  3.66it/s]
 15%|█▍        | 7/47 [00:01<00:10,  3.67it/s]
 17%|█▋        | 8/47 [00:02<00:10,  3.66it/s]
 19%|█▉        | 9/47 [00:02<00:10,  3.66it/s]
 21%|██▏       | 10/47 [00:02<00:10,  3.66it/s]
 23%|██▎       | 11/47 [00:03<00:09,  3.65it/s]
 26%|██▌       | 12/47 [00:03<00:09,  3.66it/s]
 28%|██▊       | 13/47 [00:03<00:09,  3.65it/s]
 30%|██▉       | 14/47 [00:03<00:09,  3.65it/s]
 32%|███▏      | 15/47 [00:04<00:08,  3.65it/s]
 34%|███▍      | 16/47 [00:04<00:08,  3.65it/s]
 36%|███▌      | 17/47 [00:04<00:08,  3.65it/s]
 38%|███▊      | 18/47 [00:04<00:07,  3.65it/s]
 40%|████      | 19/47 [00:05<00:07,  3.65it/s]
 43%|████▎     | 20/47 [00:05<00:07,  3.65it/s]
 45%|████▍     | 21/47 [00:05<00:07,  3.65it/s]
 47%|████▋     | 22/47 [00:06<00:06,  3.65it/s]
 49%|████▉     | 23/47 [00:06<00:06,  3.65it/s]
 51%|█████     | 24/47 [00:06<00:06,  3.65it/s]
 53%|█████▎    | 25/47 [00:06<00:06,  3.65it/s]
 55%|█████▌    | 26/47 [00:07<00:05,  3.65it/s]
 57%|█████▋    | 27/47 [00:07<00:05,  3.65it/s]
 60%|█████▉    | 28/47 [00:07<00:05,  3.65it/s]
 62%|██████▏   | 29/47 [00:07<00:04,  3.65it/s]
 64%|██████▍   | 30/47 [00:08<00:04,  3.65it/s]
 66%|██████▌   | 31/47 [00:08<00:04,  3.64it/s]
 68%|██████▊   | 32/47 [00:08<00:04,  3.64it/s]
 70%|███████   | 33/47 [00:09<00:03,  3.64it/s]
 72%|███████▏  | 34/47 [00:09<00:03,  3.64it/s]
 74%|███████▍  | 35/47 [00:09<00:03,  3.64it/s]
 77%|███████▋  | 36/47 [00:09<00:03,  3.64it/s]
 79%|███████▊  | 37/47 [00:10<00:02,  3.64it/s]
 81%|████████  | 38/47 [00:10<00:02,  3.64it/s]
 83%|████████▎ | 39/47 [00:10<00:02,  3.64it/s]
 85%|████████▌ | 40/47 [00:10<00:01,  3.64it/s]
 87%|████████▋ | 41/47 [00:11<00:01,  3.64it/s]
 89%|████████▉ | 42/47 [00:11<00:01,  3.64it/s]
 91%|█████████▏| 43/47 [00:11<00:01,  3.64it/s]
 94%|█████████▎| 44/47 [00:12<00:00,  3.64it/s]
 96%|█████████▌| 45/47 [00:12<00:00,  3.64it/s]
 98%|█████████▊| 46/47 [00:12<00:00,  3.64it/s]
100%|██████████| 47/47 [00:12<00:00,  3.63it/s]
100%|██████████| 47/47 [00:12<00:00,  3.65it/s]
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:00,  4.31it/s]
 67%|██████▋   | 2/3 [00:00<00:00,  4.28it/s]
100%|██████████| 3/3 [00:00<00:00,  4.28it/s]
100%|██████████| 3/3 [00:00<00:00,  4.28it/s]

Version Details

Version ID: 858d66f10a520248ae48fd5c6661578fef8982ffd1a272f58c2a16ef803dd744
Version Created: August 10, 2023

Run on Replicate →