sambowenhughes/testing-sdx-demo-v2 🖼️🔢📝❓✓ → 🖼️

▶️ 408 runs 📅 Jan 2024 ⚙️ Cog v0.8.1+dev
image-inpainting image-to-image text-to-image

About

Example Output

Prompt:

"Create me Kanye west styled lego sets"

Output

Example outputExample outputExample output

Performance Metrics

58.93s Prediction Time
100.95s Total Time
All Input Parameters
{
  "width": 1024,
  "height": 1024,
  "prompt": "Create me Kanye west styled lego sets",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 4,
  "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
Output Schema

Output

Type: arrayItems Type: stringItems Format: uri

Example Execution Logs
Using seed: 1678
Ensuring enough disk space...
Free disk space: 1561028825088
Downloading weights: https://replicate.delivery/pbxt/a9Dwgke1cH37XasEzdPuNwdAP9oXcpAjtfImteV9MOQtw9fIB/trained_model.tar
2024-01-30T04:32:28Z | INFO  | [ Initiating ] dest=/src/weights-cache/67574d26c2eadf91 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/a9Dwgke1cH37XasEzdPuNwdAP9oXcpAjtfImteV9MOQtw9fIB/trained_model.tar
2024-01-30T04:32:28Z | INFO  | [ Complete ] dest=/src/weights-cache/67574d26c2eadf91 size="186 MB" total_elapsed=0.867s url=https://replicate.delivery/pbxt/a9Dwgke1cH37XasEzdPuNwdAP9oXcpAjtfImteV9MOQtw9fIB/trained_model.tar
b''
Downloaded weights in 1.0836598873138428 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: Create me Kanye west styled lego sets
txt2img mode
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:01<00:51,  1.04s/it]
  4%|▍         | 2/50 [00:02<00:49,  1.04s/it]
  6%|▌         | 3/50 [00:03<00:48,  1.04s/it]
  8%|▊         | 4/50 [00:04<00:47,  1.04s/it]
 10%|█         | 5/50 [00:05<00:46,  1.04s/it]
 12%|█▏        | 6/50 [00:06<00:45,  1.04s/it]
 14%|█▍        | 7/50 [00:07<00:44,  1.04s/it]
 16%|█▌        | 8/50 [00:08<00:43,  1.04s/it]
 18%|█▊        | 9/50 [00:09<00:42,  1.04s/it]
 20%|██        | 10/50 [00:10<00:41,  1.04s/it]
 22%|██▏       | 11/50 [00:11<00:40,  1.04s/it]
 24%|██▍       | 12/50 [00:12<00:39,  1.04s/it]
 26%|██▌       | 13/50 [00:13<00:38,  1.04s/it]
 28%|██▊       | 14/50 [00:14<00:37,  1.04s/it]
 30%|███       | 15/50 [00:15<00:36,  1.04s/it]
 32%|███▏      | 16/50 [00:16<00:35,  1.04s/it]
 34%|███▍      | 17/50 [00:17<00:34,  1.04s/it]
 36%|███▌      | 18/50 [00:18<00:33,  1.04s/it]
 38%|███▊      | 19/50 [00:19<00:32,  1.04s/it]
 40%|████      | 20/50 [00:20<00:31,  1.04s/it]
 42%|████▏     | 21/50 [00:21<00:30,  1.04s/it]
 44%|████▍     | 22/50 [00:22<00:29,  1.04s/it]
 46%|████▌     | 23/50 [00:23<00:28,  1.04s/it]
 48%|████▊     | 24/50 [00:25<00:27,  1.04s/it]
 50%|█████     | 25/50 [00:26<00:26,  1.04s/it]
 52%|█████▏    | 26/50 [00:27<00:25,  1.04s/it]
 54%|█████▍    | 27/50 [00:28<00:24,  1.04s/it]
 56%|█████▌    | 28/50 [00:29<00:22,  1.04s/it]
 58%|█████▊    | 29/50 [00:30<00:21,  1.04s/it]
 60%|██████    | 30/50 [00:31<00:20,  1.05s/it]
 62%|██████▏   | 31/50 [00:32<00:19,  1.04s/it]
 64%|██████▍   | 32/50 [00:33<00:18,  1.05s/it]
 66%|██████▌   | 33/50 [00:34<00:17,  1.05s/it]
 68%|██████▊   | 34/50 [00:35<00:16,  1.05s/it]
 70%|███████   | 35/50 [00:36<00:15,  1.05s/it]
 72%|███████▏  | 36/50 [00:37<00:14,  1.05s/it]
 74%|███████▍  | 37/50 [00:38<00:13,  1.04s/it]
 76%|███████▌  | 38/50 [00:39<00:12,  1.05s/it]
 78%|███████▊  | 39/50 [00:40<00:11,  1.05s/it]
 80%|████████  | 40/50 [00:41<00:10,  1.05s/it]
 82%|████████▏ | 41/50 [00:42<00:09,  1.05s/it]
 84%|████████▍ | 42/50 [00:43<00:08,  1.05s/it]
 86%|████████▌ | 43/50 [00:44<00:07,  1.05s/it]
 88%|████████▊ | 44/50 [00:45<00:06,  1.05s/it]
 90%|█████████ | 45/50 [00:46<00:05,  1.05s/it]
 92%|█████████▏| 46/50 [00:48<00:04,  1.05s/it]
 94%|█████████▍| 47/50 [00:49<00:03,  1.05s/it]
 96%|█████████▌| 48/50 [00:50<00:02,  1.05s/it]
 98%|█████████▊| 49/50 [00:51<00:01,  1.05s/it]
100%|██████████| 50/50 [00:52<00:00,  1.05s/it]
100%|██████████| 50/50 [00:52<00:00,  1.04s/it]
Potential NSFW content was detected in one or more images. A black image will be returned instead. Try again with a different prompt and/or seed.
NSFW content detected in image 2
Version Details
Version ID
6793d9587cd0e01368641706ff87a6b143c49d6f96654e3328dc3e5fe2ec0c2d
Version Created
February 9, 2024
Run on Replicate →