jyoung105/auraflow-v2 🔢📝 → 🖼️

▶️ 31 runs 📅 Nov 2024 ⚙️ Cog 0.13.2 🔗 GitHub

flow-matching text-to-image

About

AuraFlow: Fully open-sourced flow-based text-to-image generation model

Example Output

Prompt:

"A man with hoodie on, illustration"

Output

Performance Metrics

55.12s Prediction Time

208.99s Total Time

All Input Parameters

{
  "steps": 50,
  "width": 1024,
  "height": 1024,
  "prompt": "A man with hoodie on, illustration",
  "num_images": 1,
  "guidance_scale": 3.5
}

Input Parameters

seed Type: integer: Random seed. Leave blank to randomize the seed.
steps Type: integerDefault: 50Range: 1 - 50: Number of denoising steps.
width Type: integerDefault: 1024Range: 1 - 2048: Width of the output image.
height Type: integerDefault: 1024Range: 1 - 2048: Height of the output image.
prompt Type: string: Input prompt, text of what you want to generate.
num_images Type: integerDefault: 1Range: 1 - 4: Number of output images.
guidance_scale Type: numberDefault: 3.5Range: 0 - 20: Scale for classifier-free guidance.

Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs

DEVICE: cuda
DTYPE: torch.float16
Using seed: 13500
Finish setup in 0.0001323223114013672 secs.
[Debug] Prompt: A man with hoodie on, illustration, best quality, high detail, sharp focus
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:01<00:51,  1.05s/it]
  4%|▍         | 2/50 [00:01<00:30,  1.57it/s]
  6%|▌         | 3/50 [00:02<00:38,  1.22it/s]
  8%|▊         | 4/50 [00:03<00:41,  1.10it/s]
 10%|█         | 5/50 [00:04<00:43,  1.05it/s]
 12%|█▏        | 6/50 [00:05<00:43,  1.02it/s]
 14%|█▍        | 7/50 [00:06<00:43,  1.00s/it]
 16%|█▌        | 8/50 [00:07<00:42,  1.02s/it]
 18%|█▊        | 9/50 [00:08<00:42,  1.03s/it]
 20%|██        | 10/50 [00:09<00:41,  1.03s/it]
 22%|██▏       | 11/50 [00:10<00:40,  1.04s/it]
 24%|██▍       | 12/50 [00:11<00:39,  1.04s/it]
 26%|██▌       | 13/50 [00:12<00:38,  1.04s/it]
 28%|██▊       | 14/50 [00:13<00:37,  1.04s/it]
 30%|███       | 15/50 [00:14<00:36,  1.05s/it]
 32%|███▏      | 16/50 [00:16<00:35,  1.05s/it]
 34%|███▍      | 17/50 [00:17<00:34,  1.05s/it]
 36%|███▌      | 18/50 [00:18<00:33,  1.05s/it]
 38%|███▊      | 19/50 [00:19<00:32,  1.05s/it]
 40%|████      | 20/50 [00:20<00:31,  1.05s/it]
 42%|████▏     | 21/50 [00:21<00:30,  1.05s/it]
 44%|████▍     | 22/50 [00:22<00:29,  1.05s/it]
 46%|████▌     | 23/50 [00:23<00:28,  1.05s/it]
 48%|████▊     | 24/50 [00:24<00:27,  1.05s/it]
 50%|█████     | 25/50 [00:25<00:26,  1.05s/it]
 52%|█████▏    | 26/50 [00:26<00:25,  1.05s/it]
 54%|█████▍    | 27/50 [00:27<00:24,  1.05s/it]
 56%|█████▌    | 28/50 [00:28<00:23,  1.06s/it]
 58%|█████▊    | 29/50 [00:29<00:22,  1.06s/it]
 60%|██████    | 30/50 [00:30<00:21,  1.06s/it]
 62%|██████▏   | 31/50 [00:31<00:20,  1.06s/it]
 64%|██████▍   | 32/50 [00:32<00:19,  1.06s/it]
 66%|██████▌   | 33/50 [00:33<00:18,  1.06s/it]
 68%|██████▊   | 34/50 [00:35<00:16,  1.06s/it]
 70%|███████   | 35/50 [00:36<00:15,  1.06s/it]
 72%|███████▏  | 36/50 [00:37<00:14,  1.06s/it]
 74%|███████▍  | 37/50 [00:38<00:13,  1.05s/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 [00:47<00:04,  1.05s/it]
 94%|█████████▍| 47/50 [00:48<00:03,  1.05s/it]
 96%|█████████▌| 48/50 [00:49<00:02,  1.05s/it]
 98%|█████████▊| 49/50 [00:50<00:01,  1.05s/it]
100%|██████████| 50/50 [00:51<00:00,  1.05s/it]
100%|██████████| 50/50 [00:51<00:00,  1.04s/it]
Finish generation in 53.424176931381226 secs.

Version Details

Version ID: 6811b3086c178b9bd4bbedd4e4137734c153264ea0b6aa25f84c1d23954ab1b2
Version Created: November 22, 2024

Run on Replicate →