will-hoppe/corbu 🖼️🔢📝❓✓ → 🖼️

▶️ 89 runs 📅 Feb 2024 ⚙️ Cog 0.8.6

About

Stable Diffusion XL fine-tuned to create images based on Le Corbusier's architectural style.

Example Output

Prompt:

"a photo of a uniquely shaped house on a hill"

Output

Performance Metrics

17.17s Prediction Time

23.16s Total Time

All Input Parameters

{
  "width": 512,
  "height": 512,
  "prompt": "a photo of a uniquely shaped house on a hill",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.8,
  "num_outputs": 4,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "",
  "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
replicate_weights Type: string: Replicate LoRA weights to use. Leave blank to use the default weights.
num_inference_steps Type: integerDefault: 50Range: 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: 58556
Ensuring enough disk space...
Free disk space: 2400375980032
Downloading weights: https://replicate.delivery/pbxt/mezfsCWHHMg3kUkWow82ng4TyEHVa83obFpqceQj5qkJ2pukA/trained_model.tar
2024-02-16T17:39:58Z | INFO  | [ Initiating ] dest=/src/weights-cache/8dff8925588bf9c3 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/mezfsCWHHMg3kUkWow82ng4TyEHVa83obFpqceQj5qkJ2pukA/trained_model.tar
2024-02-16T17:39:59Z | INFO  | [ Complete ] dest=/src/weights-cache/8dff8925588bf9c3 size="186 MB" total_elapsed=0.649s url=https://replicate.delivery/pbxt/mezfsCWHHMg3kUkWow82ng4TyEHVa83obFpqceQj5qkJ2pukA/trained_model.tar
b''
Downloaded weights in 0.8100481033325195 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: a photo of a uniquely shaped house on a hill
txt2img mode
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:13,  3.74it/s]
  4%|▍         | 2/50 [00:00<00:12,  3.86it/s]
  6%|▌         | 3/50 [00:00<00:12,  3.90it/s]
  8%|▊         | 4/50 [00:01<00:11,  3.91it/s]
 10%|█         | 5/50 [00:01<00:11,  3.92it/s]
 12%|█▏        | 6/50 [00:01<00:11,  3.93it/s]
 14%|█▍        | 7/50 [00:01<00:10,  3.93it/s]
 16%|█▌        | 8/50 [00:02<00:10,  3.93it/s]
 18%|█▊        | 9/50 [00:02<00:10,  3.93it/s]
 20%|██        | 10/50 [00:02<00:10,  3.93it/s]
 22%|██▏       | 11/50 [00:02<00:09,  3.93it/s]
 24%|██▍       | 12/50 [00:03<00:09,  3.93it/s]
 26%|██▌       | 13/50 [00:03<00:09,  3.93it/s]
 28%|██▊       | 14/50 [00:03<00:09,  3.92it/s]
 30%|███       | 15/50 [00:03<00:08,  3.92it/s]
 32%|███▏      | 16/50 [00:04<00:08,  3.92it/s]
 34%|███▍      | 17/50 [00:04<00:08,  3.92it/s]
 36%|███▌      | 18/50 [00:04<00:08,  3.92it/s]
 38%|███▊      | 19/50 [00:04<00:07,  3.92it/s]
 40%|████      | 20/50 [00:05<00:07,  3.92it/s]
 42%|████▏     | 21/50 [00:05<00:07,  3.92it/s]
 44%|████▍     | 22/50 [00:05<00:07,  3.92it/s]
 46%|████▌     | 23/50 [00:05<00:06,  3.92it/s]
 48%|████▊     | 24/50 [00:06<00:06,  3.92it/s]
 50%|█████     | 25/50 [00:06<00:06,  3.92it/s]
 52%|█████▏    | 26/50 [00:06<00:06,  3.92it/s]
 54%|█████▍    | 27/50 [00:06<00:05,  3.92it/s]
 56%|█████▌    | 28/50 [00:07<00:05,  3.91it/s]
 58%|█████▊    | 29/50 [00:07<00:05,  3.91it/s]
 60%|██████    | 30/50 [00:07<00:05,  3.91it/s]
 62%|██████▏   | 31/50 [00:07<00:04,  3.91it/s]
 64%|██████▍   | 32/50 [00:08<00:04,  3.91it/s]
 66%|██████▌   | 33/50 [00:08<00:04,  3.91it/s]
 68%|██████▊   | 34/50 [00:08<00:04,  3.91it/s]
 70%|███████   | 35/50 [00:08<00:03,  3.87it/s]
 72%|███████▏  | 36/50 [00:09<00:03,  3.88it/s]
 74%|███████▍  | 37/50 [00:09<00:03,  3.89it/s]
 76%|███████▌  | 38/50 [00:09<00:03,  3.90it/s]
 78%|███████▊  | 39/50 [00:09<00:02,  3.90it/s]
 80%|████████  | 40/50 [00:10<00:02,  3.90it/s]
 82%|████████▏ | 41/50 [00:10<00:02,  3.90it/s]
 84%|████████▍ | 42/50 [00:10<00:02,  3.90it/s]
 86%|████████▌ | 43/50 [00:10<00:01,  3.90it/s]
 88%|████████▊ | 44/50 [00:11<00:01,  3.91it/s]
 90%|█████████ | 45/50 [00:11<00:01,  3.91it/s]
 92%|█████████▏| 46/50 [00:11<00:01,  3.91it/s]
 94%|█████████▍| 47/50 [00:12<00:00,  3.91it/s]
 96%|█████████▌| 48/50 [00:12<00:00,  3.90it/s]
 98%|█████████▊| 49/50 [00:12<00:00,  3.90it/s]
100%|██████████| 50/50 [00:12<00:00,  3.90it/s]
100%|██████████| 50/50 [00:12<00:00,  3.91it/s]

Version Details

Version ID: 173125079537df21d084306fa18a35a05f42f8becca225e2f7a7ef65356d6bdc
Version Created: February 16, 2024

Run on Replicate →