cjwbw/textdiffuser 🔢📝❓ → 🖼️

▶️ 2.0K runs 📅 Jun 2023 ⚙️ Cog 0.7.2 🔗 GitHub 📄 Paper ⚖️ License
text-in-image text-rendering text-to-image

About

Diffusion Models as Text Painters

Example Output

Prompt:

"A sign that says 'Hello'"

Output

Example output

Performance Metrics

32.61s Prediction Time
454.69s Total Time
All Input Parameters
{
  "prompt": "A sign that says 'Hello'",
  "sample_num": 1,
  "guidance_scale": 7.5,
  "num_inference_steps": 50
}
Input Parameters
seed Type: integer
Random seed. Leave blank to randomize the seed
prompt Type: stringDefault: A sign that says 'Hello'
Input prompt
sample_num Default: 1
Number of output images
guidance_scale Type: numberDefault: 7.5Range: 1 - 20
Scale for classifier-free guidance
num_inference_steps Type: integerDefault: 50Range: 1 - 500
Number of denoising steps
Output Schema

Output

Type: arrayItems Type: stringItems Format: uri

Example Execution Logs
Using seed: 19585
encoder_hidden_states: torch.Size([1, 77, 768]).
encoder_hidden_states_nocond: torch.Size([1, 77, 768]).
[!] Detected keywords: ['Hello'] from prompt A sign that says 'Hello'
index	keyword	x_min	y_min	x_max	y_max
0	Hello	83	140	416	311
[√] Layout is successfully generated
character-level segmentation_mask: torch.Size([1, 256, 256]).
feature_mask: torch.Size([1, 1, 64, 64]).
masked_feature: torch.Size([1, 4, 64, 64]).
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:28,  1.69it/s]
  4%|▍         | 2/50 [00:01<00:27,  1.73it/s]
  6%|▌         | 3/50 [00:01<00:27,  1.74it/s]
  8%|▊         | 4/50 [00:02<00:26,  1.76it/s]
 10%|█         | 5/50 [00:02<00:25,  1.77it/s]
 12%|█▏        | 6/50 [00:03<00:24,  1.77it/s]
 14%|█▍        | 7/50 [00:03<00:24,  1.77it/s]
 16%|█▌        | 8/50 [00:04<00:23,  1.77it/s]
 18%|█▊        | 9/50 [00:05<00:23,  1.77it/s]
 20%|██        | 10/50 [00:05<00:22,  1.77it/s]
 22%|██▏       | 11/50 [00:06<00:21,  1.77it/s]
 24%|██▍       | 12/50 [00:06<00:21,  1.78it/s]
 26%|██▌       | 13/50 [00:07<00:20,  1.78it/s]
 28%|██▊       | 14/50 [00:07<00:20,  1.77it/s]
 30%|███       | 15/50 [00:08<00:19,  1.77it/s]
 32%|███▏      | 16/50 [00:09<00:19,  1.77it/s]
 34%|███▍      | 17/50 [00:09<00:18,  1.77it/s]
 36%|███▌      | 18/50 [00:10<00:18,  1.77it/s]
 38%|███▊      | 19/50 [00:10<00:17,  1.77it/s]
 40%|████      | 20/50 [00:11<00:17,  1.76it/s]
 42%|████▏     | 21/50 [00:11<00:16,  1.76it/s]
 44%|████▍     | 22/50 [00:12<00:15,  1.76it/s]
 46%|████▌     | 23/50 [00:13<00:15,  1.76it/s]
 48%|████▊     | 24/50 [00:13<00:14,  1.76it/s]
 50%|█████     | 25/50 [00:14<00:14,  1.76it/s]
 52%|█████▏    | 26/50 [00:14<00:13,  1.75it/s]
 54%|█████▍    | 27/50 [00:15<00:13,  1.75it/s]
 56%|█████▌    | 28/50 [00:15<00:12,  1.75it/s]
 58%|█████▊    | 29/50 [00:16<00:12,  1.74it/s]
 60%|██████    | 30/50 [00:17<00:11,  1.74it/s]
 62%|██████▏   | 31/50 [00:17<00:10,  1.74it/s]
 64%|██████▍   | 32/50 [00:18<00:10,  1.75it/s]
 66%|██████▌   | 33/50 [00:18<00:09,  1.73it/s]
 68%|██████▊   | 34/50 [00:19<00:09,  1.73it/s]
 70%|███████   | 35/50 [00:19<00:08,  1.72it/s]
 72%|███████▏  | 36/50 [00:20<00:08,  1.72it/s]
 74%|███████▍  | 37/50 [00:21<00:07,  1.72it/s]
 76%|███████▌  | 38/50 [00:21<00:06,  1.72it/s]
 78%|███████▊  | 39/50 [00:22<00:06,  1.72it/s]
 80%|████████  | 40/50 [00:22<00:05,  1.72it/s]
 82%|████████▏ | 41/50 [00:23<00:05,  1.71it/s]
 84%|████████▍ | 42/50 [00:24<00:04,  1.71it/s]
 86%|████████▌ | 43/50 [00:24<00:04,  1.71it/s]
 88%|████████▊ | 44/50 [00:25<00:03,  1.71it/s]
 90%|█████████ | 45/50 [00:25<00:02,  1.70it/s]
 92%|█████████▏| 46/50 [00:26<00:02,  1.70it/s]
 94%|█████████▍| 47/50 [00:26<00:01,  1.70it/s]
 96%|█████████▌| 48/50 [00:27<00:01,  1.70it/s]
 98%|█████████▊| 49/50 [00:28<00:00,  1.69it/s]
100%|██████████| 50/50 [00:28<00:00,  1.69it/s]
100%|██████████| 50/50 [00:28<00:00,  1.74it/s]
Version Details
Version ID
7d7fdc0954e65ee53d61dde9bc342865e0fe1e45c6f491c10e05975439c6858c
Version Created
June 4, 2023
Run on Replicate →