exdatic/tortengenerator 🖼️🔢📝❓✓ → 🖼️

▶️ 83 runs 📅 Jun 2024 ⚙️ Cog 0.9.5

About

Example Output

Prompt:

"a TOK cake showing Dresden city"

Output

Performance Metrics

18.67s Prediction Time

20.97s Total Time

All Input Parameters

{
  "width": 1024,
  "height": 1024,
  "prompt": "a TOK cake showing Dresden city",
  "refine": "expert_ensemble_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "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](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: 30701
Ensuring enough disk space...
Free disk space: 1675342958592
Downloading weights: https://replicate.delivery/pbxt/gn3Qkbkzq45UD535KTILfGPtKOfvfNdMPgb1uTeTJPgR68BMB/trained_model.tar
2024-06-20T15:13:48Z | INFO  | [ Initiating ] chunk_size=150M dest=/src/weights-cache/edb882bcf98d56ad url=https://replicate.delivery/pbxt/gn3Qkbkzq45UD535KTILfGPtKOfvfNdMPgb1uTeTJPgR68BMB/trained_model.tar
2024-06-20T15:13:50Z | INFO  | [ Complete ] dest=/src/weights-cache/edb882bcf98d56ad size="186 MB" total_elapsed=1.818s url=https://replicate.delivery/pbxt/gn3Qkbkzq45UD535KTILfGPtKOfvfNdMPgb1uTeTJPgR68BMB/trained_model.tar
b''
Downloaded weights in 1.9627363681793213 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: a <s0><s1> cake showing Dresden city
txt2img mode
  0%|          | 0/40 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights`
deprecate(
  2%|▎         | 1/40 [00:00<00:09,  4.25it/s]
  5%|▌         | 2/40 [00:00<00:08,  4.24it/s]
  8%|▊         | 3/40 [00:00<00:08,  4.24it/s]
 10%|█         | 4/40 [00:00<00:08,  4.22it/s]
 12%|█▎        | 5/40 [00:01<00:08,  4.22it/s]
 15%|█▌        | 6/40 [00:01<00:08,  4.22it/s]
 18%|█▊        | 7/40 [00:01<00:07,  4.21it/s]
 20%|██        | 8/40 [00:01<00:07,  4.21it/s]
 22%|██▎       | 9/40 [00:02<00:07,  4.21it/s]
 25%|██▌       | 10/40 [00:02<00:07,  4.21it/s]
 28%|██▊       | 11/40 [00:02<00:06,  4.21it/s]
 30%|███       | 12/40 [00:02<00:06,  4.21it/s]
 32%|███▎      | 13/40 [00:03<00:06,  4.20it/s]
 35%|███▌      | 14/40 [00:03<00:06,  4.20it/s]
 38%|███▊      | 15/40 [00:03<00:05,  4.20it/s]
 40%|████      | 16/40 [00:03<00:05,  4.20it/s]
 42%|████▎     | 17/40 [00:04<00:05,  4.20it/s]
 45%|████▌     | 18/40 [00:04<00:05,  4.20it/s]
 48%|████▊     | 19/40 [00:04<00:05,  4.20it/s]
 50%|█████     | 20/40 [00:04<00:04,  4.20it/s]
 52%|█████▎    | 21/40 [00:04<00:04,  4.20it/s]
 55%|█████▌    | 22/40 [00:05<00:04,  4.20it/s]
 57%|█████▊    | 23/40 [00:05<00:04,  4.20it/s]
 60%|██████    | 24/40 [00:05<00:03,  4.20it/s]
 62%|██████▎   | 25/40 [00:05<00:03,  4.20it/s]
 65%|██████▌   | 26/40 [00:06<00:03,  4.20it/s]
 68%|██████▊   | 27/40 [00:06<00:03,  4.20it/s]
 70%|███████   | 28/40 [00:06<00:02,  4.20it/s]
 72%|███████▎  | 29/40 [00:06<00:02,  4.20it/s]
 75%|███████▌  | 30/40 [00:07<00:02,  4.20it/s]
 78%|███████▊  | 31/40 [00:07<00:02,  4.19it/s]
 80%|████████  | 32/40 [00:07<00:01,  4.19it/s]
 82%|████████▎ | 33/40 [00:07<00:01,  4.19it/s]
 85%|████████▌ | 34/40 [00:08<00:01,  4.20it/s]
 88%|████████▊ | 35/40 [00:08<00:01,  4.19it/s]
 90%|█████████ | 36/40 [00:08<00:00,  4.19it/s]
 92%|█████████▎| 37/40 [00:08<00:00,  4.19it/s]
 95%|█████████▌| 38/40 [00:09<00:00,  4.19it/s]
 98%|█████████▊| 39/40 [00:09<00:00,  4.19it/s]
100%|██████████| 40/40 [00:09<00:00,  4.19it/s]
100%|██████████| 40/40 [00:09<00:00,  4.20it/s]
  0%|          | 0/10 [00:00<?, ?it/s]
 10%|█         | 1/10 [00:00<00:02,  3.87it/s]
 20%|██        | 2/10 [00:00<00:01,  4.03it/s]
 30%|███       | 3/10 [00:00<00:01,  4.09it/s]
 40%|████      | 4/10 [00:00<00:01,  4.11it/s]
 50%|█████     | 5/10 [00:01<00:01,  4.13it/s]
 60%|██████    | 6/10 [00:01<00:00,  4.15it/s]
 70%|███████   | 7/10 [00:01<00:00,  4.15it/s]
 80%|████████  | 8/10 [00:01<00:00,  4.16it/s]
 90%|█████████ | 9/10 [00:02<00:00,  4.16it/s]
100%|██████████| 10/10 [00:02<00:00,  4.16it/s]
100%|██████████| 10/10 [00:02<00:00,  4.13it/s]

Version Details

Version ID: 8ed306f94a3b3cd77104de663a59fbd396c045cbcb93ef928679c2ca1859260f
Version Created: June 20, 2024

Run on Replicate →