camenduru/story-diffusion 🔢📝❓🖼️ → 🖼️

▶️ 1.3K runs 📅 May 2024 ⚙️ Cog 0.9.5 🔗 GitHub 📄 Paper ⚖️ License

anime comic-creation image-generation style-transfer text-to-image visual-storytelling

About

StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation

Example Output

Output

Performance Metrics

56.06s Prediction Time

365.86s Total Time

All Input Parameters

{
  "sa32_": 0.5,
  "sa64_": 0.5,
  "seed_": 1,
  "style": "Japanese Anime",
  "G_width": 768,
  "sd_type": "Unstable",
  "G_height": 768,
  "num_steps": 50,
  "comic_type": "Classic Comic Style",
  "id_length_": 3,
  "model_type": "Using Ref Images",
  "input_image": "https://replicate.delivery/pbxt/KqySXsVmWku71q5LZeNjgasK4oVRILdFPt9dKKCEYG5ZFVko/1%20%281%29.jpeg",
  "prompt_array": "wake up in the bed\nhave breakfast\nis on the road, go to company\nwork in the company\nTake a walk next to the company at noon\nlying in bed at night",
  "general_prompt": "a woman img, wearing a white T-shirt, blue loose hair",
  "guidance_scale": 5,
  "negative_prompt": "bad anatomy, bad hands, missing fingers, extra fingers, three hands, three legs, bad arms, missing legs, missing arms, poorly drawn face, bad face, fused face, cloned face, three crus, fused feet, fused thigh, extra crus, ugly fingers, horn, cartoon, cg, 3d, unreal, animate, amputation, disconnected limbs",
  "Ip_Adapter_Strength": 0.5,
  "style_strength_ratio": 20
}

Input Parameters

sa32_ Type: numberDefault: 0.5: The degree of Paired Attention at 32 x 32 self-attention layers
sa64_ Type: numberDefault: 0.5: The degree of Paired Attention at 64 x 64 self-attention layers
seed_ Type: integerDefault: 1: Seed
style Type: stringDefault: Japanese Anime: Style template: '(No style)', 'Japanese Anime', 'Cinematic', 'Disney Character', 'Photographic', 'Comic book', 'Line art'
G_width Type: integerDefault: 768: Width
G_height Type: integerDefault: 768: Height
num_steps Type: integerDefault: 50: Number of sample steps
comic_type Default: Classic Comic Style: Typesetting Style
id_length_ Type: integerDefault: 3: Number of id images in total images
model_type Default: Using Ref Images: Control type of the Character
input_image (required) Type: string
prompt_array Type: stringDefault: wake up in the bed have breakfast is on the road, go to company work in the company Take a walk next to the company at noon lying in bed at night: Comic Description (each line corresponds to a frame).
general_prompt Type: stringDefault: a woman img, wearing a white T-shirt, blue loose hair: Textual Description for Character
guidance_scale Type: integerDefault: 5: Guidance scale
negative_prompt Type: stringDefault: bad anatomy, bad hands, missing fingers, extra fingers, three hands, three legs, bad arms, missing legs, missing arms, poorly drawn face, bad face, fused face, cloned face, three crus, fused feet, fused thigh, extra crus, ugly fingers, horn, cartoon, cg, 3d, unreal, animate, amputation, disconnected limbs: Negative Prompt
Ip_Adapter_Strength Type: numberDefault: 0.5: Ip Adapter Strength
style_strength_ratio Type: integerDefault: 20: Style strength of Ref Image (%)

Output Schema

Output

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

Example Execution Logs

successsfully load paired self-attention
number of the processor : 36
/content/StoryDiffusion-hf/examples/taylor/1.jpeg
start_merge_step:10
['a woman img, wearing a white T-shirt, blue loose hair,wake up in the bed', 'a woman img, wearing a white T-shirt, blue loose hair,have breakfast', 'a woman img, wearing a white T-shirt, blue loose hair,is on the road, go to company', 'a woman img, wearing a white T-shirt, blue loose hair,work in the company', 'a woman img, wearing a white T-shirt, blue loose hair,Take a walk next to the company at noon', 'a woman img, wearing a white T-shirt, blue loose hair,lying in bed at night']
anime artwork illustrating a woman, wearing a white t - shirt, blue loose hair, wake up in the bed. created by japanese anime studio. highly emotional. best quality, high resolution
anime artwork illustrating a woman, wearing a white t - shirt, blue loose hair, have breakfast. created by japanese anime studio. highly emotional. best quality, high resolution
anime artwork illustrating a woman, wearing a white t - shirt, blue loose hair, is on the road, go to company. created by japanese anime studio. highly emotional. best quality, high resolution
torch.Size([3, 77, 2048])
torch.Size([3, 77, 2048])
torch.Size([3, 77, 2048])
torch.Size([3, 1280])
torch.Size([3, 1280])
torch.Size([3, 1280])
torch.Size([3, 4, 96, 96])
torch.Size([6, 6])
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:32,  1.51it/s]
  4%|▍         | 2/50 [00:00<00:22,  2.17it/s]
  6%|▌         | 3/50 [00:01<00:18,  2.48it/s]
  8%|▊         | 4/50 [00:01<00:17,  2.58it/s]
 10%|█         | 5/50 [00:02<00:17,  2.65it/s]
 12%|█▏        | 6/50 [00:02<00:16,  2.70it/s]
 14%|█▍        | 7/50 [00:02<00:15,  2.74it/s]
 16%|█▌        | 8/50 [00:03<00:15,  2.73it/s]
 18%|█▊        | 9/50 [00:03<00:14,  2.77it/s]
 20%|██        | 10/50 [00:03<00:14,  2.79it/s]
 22%|██▏       | 11/50 [00:04<00:13,  2.82it/s]
 24%|██▍       | 12/50 [00:04<00:13,  2.82it/s]
 26%|██▌       | 13/50 [00:04<00:13,  2.81it/s]
 28%|██▊       | 14/50 [00:05<00:12,  2.79it/s]
 30%|███       | 15/50 [00:05<00:12,  2.82it/s]
 32%|███▏      | 16/50 [00:05<00:12,  2.79it/s]
 34%|███▍      | 17/50 [00:06<00:11,  2.76it/s]
 36%|███▌      | 18/50 [00:06<00:11,  2.73it/s]
 38%|███▊      | 19/50 [00:07<00:11,  2.75it/s]
 40%|████      | 20/50 [00:07<00:10,  2.76it/s]
 42%|████▏     | 21/50 [00:07<00:10,  2.76it/s]
 44%|████▍     | 22/50 [00:08<00:10,  2.74it/s]
 46%|████▌     | 23/50 [00:08<00:09,  2.72it/s]
 48%|████▊     | 24/50 [00:08<00:09,  2.71it/s]
 50%|█████     | 25/50 [00:09<00:09,  2.72it/s]
 52%|█████▏    | 26/50 [00:09<00:08,  2.72it/s]
 54%|█████▍    | 27/50 [00:10<00:08,  2.70it/s]
 56%|█████▌    | 28/50 [00:10<00:08,  2.70it/s]
 58%|█████▊    | 29/50 [00:10<00:07,  2.69it/s]
 60%|██████    | 30/50 [00:11<00:07,  2.68it/s]
 62%|██████▏   | 31/50 [00:11<00:07,  2.68it/s]
 64%|██████▍   | 32/50 [00:11<00:06,  2.68it/s]
 66%|██████▌   | 33/50 [00:12<00:06,  2.68it/s]
 68%|██████▊   | 34/50 [00:12<00:05,  2.69it/s]
 70%|███████   | 35/50 [00:12<00:05,  2.68it/s]
 72%|███████▏  | 36/50 [00:13<00:05,  2.69it/s]
 74%|███████▍  | 37/50 [00:13<00:04,  2.69it/s]
 76%|███████▌  | 38/50 [00:14<00:04,  2.69it/s]
 78%|███████▊  | 39/50 [00:14<00:04,  2.69it/s]
 80%|████████  | 40/50 [00:14<00:03,  2.69it/s]
 82%|████████▏ | 41/50 [00:15<00:03,  2.70it/s]
 84%|████████▍ | 42/50 [00:15<00:02,  2.70it/s]
 86%|████████▌ | 43/50 [00:15<00:02,  2.69it/s]
 88%|████████▊ | 44/50 [00:16<00:02,  2.70it/s]
 90%|█████████ | 45/50 [00:16<00:01,  2.72it/s]
 92%|█████████▏| 46/50 [00:17<00:01,  2.71it/s]
 94%|█████████▍| 47/50 [00:17<00:01,  2.72it/s]
 96%|█████████▌| 48/50 [00:17<00:00,  2.73it/s]
 98%|█████████▊| 49/50 [00:18<00:00,  2.76it/s]
100%|██████████| 50/50 [00:18<00:00,  2.74it/s]
100%|██████████| 50/50 [00:18<00:00,  2.70it/s]
anime artwork illustrating a woman, wearing a white t - shirt, blue loose hair, work in the company. created by japanese anime studio. highly emotional. best quality, high resolution
torch.Size([1, 77, 2048])
torch.Size([1, 77, 2048])
torch.Size([1, 77, 2048])
torch.Size([1, 1280])
torch.Size([1, 1280])
torch.Size([1, 1280])
torch.Size([1, 4, 96, 96])
torch.Size([2, 6])
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:09,  5.08it/s]
  4%|▍         | 2/50 [00:00<00:07,  6.27it/s]
  6%|▌         | 3/50 [00:00<00:07,  6.49it/s]
  8%|▊         | 4/50 [00:00<00:07,  6.35it/s]
 10%|█         | 5/50 [00:00<00:07,  6.28it/s]
 12%|█▏        | 6/50 [00:00<00:06,  6.33it/s]
 14%|█▍        | 7/50 [00:01<00:06,  6.34it/s]
 16%|█▌        | 8/50 [00:01<00:06,  6.28it/s]
 18%|█▊        | 9/50 [00:01<00:06,  6.31it/s]
 20%|██        | 10/50 [00:01<00:06,  6.37it/s]
 22%|██▏       | 11/50 [00:01<00:06,  6.41it/s]
 24%|██▍       | 12/50 [00:01<00:05,  6.39it/s]
 26%|██▌       | 13/50 [00:02<00:05,  6.35it/s]
 28%|██▊       | 14/50 [00:02<00:05,  6.30it/s]
 30%|███       | 15/50 [00:02<00:05,  6.38it/s]
 32%|███▏      | 16/50 [00:02<00:05,  6.31it/s]
 34%|███▍      | 17/50 [00:02<00:05,  6.21it/s]
 36%|███▌      | 18/50 [00:02<00:05,  6.14it/s]
 38%|███▊      | 19/50 [00:03<00:04,  6.21it/s]
 40%|████      | 20/50 [00:03<00:04,  6.25it/s]
 42%|████▏     | 21/50 [00:03<00:04,  6.23it/s]
 44%|████▍     | 22/50 [00:03<00:04,  6.17it/s]
 46%|████▌     | 23/50 [00:03<00:04,  6.13it/s]
 48%|████▊     | 24/50 [00:03<00:04,  6.11it/s]
 50%|█████     | 25/50 [00:04<00:04,  6.10it/s]
 52%|█████▏    | 26/50 [00:04<00:03,  6.10it/s]
 54%|█████▍    | 27/50 [00:04<00:03,  6.05it/s]
 56%|█████▌    | 28/50 [00:04<00:03,  6.04it/s]
 58%|█████▊    | 29/50 [00:04<00:03,  6.01it/s]
 60%|██████    | 30/50 [00:04<00:03,  5.97it/s]
 62%|██████▏   | 31/50 [00:05<00:03,  5.95it/s]
 64%|██████▍   | 32/50 [00:05<00:03,  5.97it/s]
 66%|██████▌   | 33/50 [00:05<00:02,  5.99it/s]
 68%|██████▊   | 34/50 [00:05<00:02,  5.97it/s]
 70%|███████   | 35/50 [00:05<00:02,  5.98it/s]
 72%|███████▏  | 36/50 [00:05<00:02,  5.99it/s]
 74%|███████▍  | 37/50 [00:06<00:02,  5.97it/s]
 76%|███████▌  | 38/50 [00:06<00:02,  5.95it/s]
 78%|███████▊  | 39/50 [00:06<00:01,  5.99it/s]
 80%|████████  | 40/50 [00:06<00:01,  5.99it/s]
 82%|████████▏ | 41/50 [00:06<00:01,  6.03it/s]
 84%|████████▍ | 42/50 [00:06<00:01,  6.02it/s]
 86%|████████▌ | 43/50 [00:07<00:01,  6.01it/s]
 88%|████████▊ | 44/50 [00:07<00:00,  6.05it/s]
 90%|█████████ | 45/50 [00:07<00:00,  6.11it/s]
 92%|█████████▏| 46/50 [00:07<00:00,  6.08it/s]
 94%|█████████▍| 47/50 [00:07<00:00,  6.07it/s]
 96%|█████████▌| 48/50 [00:07<00:00,  6.10it/s]
 98%|█████████▊| 49/50 [00:07<00:00,  6.18it/s]
100%|██████████| 50/50 [00:08<00:00,  6.15it/s]
100%|██████████| 50/50 [00:08<00:00,  6.13it/s]
anime artwork illustrating a woman, wearing a white t - shirt, blue loose hair, take a walk next to the company at noon. created by japanese anime studio. highly emotional. best quality, high resolution
torch.Size([1, 77, 2048])
torch.Size([1, 77, 2048])
torch.Size([1, 77, 2048])
torch.Size([1, 1280])
torch.Size([1, 1280])
torch.Size([1, 1280])
torch.Size([1, 4, 96, 96])
torch.Size([2, 6])
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:06,  7.32it/s]
  4%|▍         | 2/50 [00:00<00:06,  7.42it/s]
  6%|▌         | 3/50 [00:00<00:06,  7.11it/s]
  8%|▊         | 4/50 [00:00<00:06,  6.69it/s]
 10%|█         | 5/50 [00:00<00:06,  6.50it/s]
 12%|█▏        | 6/50 [00:00<00:06,  6.49it/s]
 14%|█▍        | 7/50 [00:01<00:06,  6.45it/s]
 16%|█▌        | 8/50 [00:01<00:06,  6.35it/s]
 18%|█▊        | 9/50 [00:01<00:06,  6.38it/s]
 20%|██        | 10/50 [00:01<00:06,  6.42it/s]
 22%|██▏       | 11/50 [00:01<00:06,  6.44it/s]
 24%|██▍       | 12/50 [00:01<00:05,  6.42it/s]
 26%|██▌       | 13/50 [00:01<00:05,  6.38it/s]
 28%|██▊       | 14/50 [00:02<00:05,  6.32it/s]
 30%|███       | 15/50 [00:02<00:05,  6.40it/s]
 32%|███▏      | 16/50 [00:02<00:05,  6.33it/s]
 34%|███▍      | 17/50 [00:02<00:05,  6.24it/s]
 36%|███▌      | 18/50 [00:02<00:05,  6.17it/s]
 38%|███▊      | 19/50 [00:02<00:04,  6.21it/s]
 40%|████      | 20/50 [00:03<00:04,  6.25it/s]
 42%|████▏     | 21/50 [00:03<00:04,  6.23it/s]
 44%|████▍     | 22/50 [00:03<00:04,  6.14it/s]
 46%|████▌     | 23/50 [00:03<00:04,  6.09it/s]
 48%|████▊     | 24/50 [00:03<00:04,  6.09it/s]
 50%|█████     | 25/50 [00:03<00:04,  6.08it/s]
 52%|█████▏    | 26/50 [00:04<00:03,  6.08it/s]
 54%|█████▍    | 27/50 [00:04<00:03,  6.04it/s]
 56%|█████▌    | 28/50 [00:04<00:03,  6.01it/s]
 58%|█████▊    | 29/50 [00:04<00:03,  5.99it/s]
 60%|██████    | 30/50 [00:04<00:03,  5.98it/s]
 62%|██████▏   | 31/50 [00:04<00:03,  5.96it/s]
 64%|██████▍   | 32/50 [00:05<00:03,  6.00it/s]
 66%|██████▌   | 33/50 [00:05<00:02,  6.01it/s]
 68%|██████▊   | 34/50 [00:05<00:02,  5.99it/s]
 70%|███████   | 35/50 [00:05<00:02,  5.98it/s]
 72%|███████▏  | 36/50 [00:05<00:02,  6.01it/s]
 74%|███████▍  | 37/50 [00:05<00:02,  6.00it/s]
 76%|███████▌  | 38/50 [00:06<00:02,  5.98it/s]
 78%|███████▊  | 39/50 [00:06<00:01,  6.00it/s]
 80%|████████  | 40/50 [00:06<00:01,  5.96it/s]
 82%|████████▏ | 41/50 [00:06<00:01,  5.99it/s]
 84%|████████▍ | 42/50 [00:06<00:01,  5.98it/s]
 86%|████████▌ | 43/50 [00:06<00:01,  5.97it/s]
 88%|████████▊ | 44/50 [00:07<00:01,  5.96it/s]
 90%|█████████ | 45/50 [00:07<00:00,  6.04it/s]
 92%|█████████▏| 46/50 [00:07<00:00,  5.99it/s]
 94%|█████████▍| 47/50 [00:07<00:00,  6.01it/s]
 96%|█████████▌| 48/50 [00:07<00:00,  6.05it/s]
 98%|█████████▊| 49/50 [00:07<00:00,  6.13it/s]
100%|██████████| 50/50 [00:08<00:00,  6.07it/s]
100%|██████████| 50/50 [00:08<00:00,  6.17it/s]
anime artwork illustrating a woman, wearing a white t - shirt, blue loose hair, lying in bed at night. created by japanese anime studio. highly emotional. best quality, high resolution
torch.Size([1, 77, 2048])
torch.Size([1, 77, 2048])
torch.Size([1, 77, 2048])
torch.Size([1, 1280])
torch.Size([1, 1280])
torch.Size([1, 1280])
torch.Size([1, 4, 96, 96])
torch.Size([2, 6])
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:06,  7.37it/s]
  4%|▍         | 2/50 [00:00<00:06,  7.43it/s]
  6%|▌         | 3/50 [00:00<00:06,  7.08it/s]
  8%|▊         | 4/50 [00:00<00:07,  6.56it/s]
 10%|█         | 5/50 [00:00<00:07,  6.36it/s]
 12%|█▏        | 6/50 [00:00<00:06,  6.37it/s]
 14%|█▍        | 7/50 [00:01<00:06,  6.34it/s]
 16%|█▌        | 8/50 [00:01<00:06,  6.24it/s]
 18%|█▊        | 9/50 [00:01<00:06,  6.29it/s]
 20%|██        | 10/50 [00:01<00:06,  6.34it/s]
 22%|██▏       | 11/50 [00:01<00:06,  6.38it/s]
 24%|██▍       | 12/50 [00:01<00:05,  6.36it/s]
 26%|██▌       | 13/50 [00:02<00:05,  6.32it/s]
 28%|██▊       | 14/50 [00:02<00:05,  6.27it/s]
 30%|███       | 15/50 [00:02<00:05,  6.35it/s]
 32%|███▏      | 16/50 [00:02<00:05,  6.31it/s]
 34%|███▍      | 17/50 [00:02<00:05,  6.22it/s]
 36%|███▌      | 18/50 [00:02<00:05,  6.14it/s]
 38%|███▊      | 19/50 [00:02<00:05,  6.20it/s]
 40%|████      | 20/50 [00:03<00:04,  6.23it/s]
 42%|████▏     | 21/50 [00:03<00:04,  6.19it/s]
 44%|████▍     | 22/50 [00:03<00:04,  6.13it/s]
 46%|████▌     | 23/50 [00:03<00:04,  6.10it/s]
 48%|████▊     | 24/50 [00:03<00:04,  6.07it/s]
 50%|█████     | 25/50 [00:03<00:04,  6.07it/s]
 52%|█████▏    | 26/50 [00:04<00:03,  6.06it/s]
 54%|█████▍    | 27/50 [00:04<00:03,  5.99it/s]
 56%|█████▌    | 28/50 [00:04<00:03,  5.99it/s]
 58%|█████▊    | 29/50 [00:04<00:03,  5.98it/s]
 60%|██████    | 30/50 [00:04<00:03,  5.95it/s]
 62%|██████▏   | 31/50 [00:04<00:03,  5.94it/s]
 64%|██████▍   | 32/50 [00:05<00:03,  5.97it/s]
 66%|██████▌   | 33/50 [00:05<00:02,  5.97it/s]
 68%|██████▊   | 34/50 [00:05<00:02,  5.98it/s]
 70%|███████   | 35/50 [00:05<00:02,  5.97it/s]
 72%|███████▏  | 36/50 [00:05<00:02,  5.99it/s]
 74%|███████▍  | 37/50 [00:05<00:02,  5.98it/s]
 76%|███████▌  | 38/50 [00:06<00:02,  5.95it/s]
 78%|███████▊  | 39/50 [00:06<00:01,  5.96it/s]
 80%|████████  | 40/50 [00:06<00:01,  5.93it/s]
 82%|████████▏ | 41/50 [00:06<00:01,  5.97it/s]
 84%|████████▍ | 42/50 [00:06<00:01,  5.94it/s]
 86%|████████▌ | 43/50 [00:07<00:01,  5.88it/s]
 88%|████████▊ | 44/50 [00:07<00:01,  5.92it/s]
 90%|█████████ | 45/50 [00:07<00:00,  5.99it/s]
 92%|█████████▏| 46/50 [00:07<00:00,  5.97it/s]
 94%|█████████▍| 47/50 [00:07<00:00,  6.00it/s]
 96%|█████████▌| 48/50 [00:07<00:00,  6.03it/s]
 98%|█████████▊| 49/50 [00:07<00:00,  6.10it/s]
100%|██████████| 50/50 [00:08<00:00,  6.07it/s]
100%|██████████| 50/50 [00:08<00:00,  6.13it/s]
2 [[<PIL.Image.Image image mode=RGB size=788x788 at 0x7F59B44CAB60>, <PIL.Image.Image image mode=RGB size=788x788 at 0x7F59B44CAF50>, <PIL.Image.Image image mode=RGB size=788x788 at 0x7F59B44CAA70>, <PIL.Image.Image image mode=RGB size=788x788 at 0x7F59B44CBC40>]]
-2 [[<PIL.Image.Image image mode=RGB size=788x788 at 0x7F59B44CAB60>, <PIL.Image.Image image mode=RGB size=788x788 at 0x7F59B44CAF50>, <PIL.Image.Image image mode=RGB size=788x788 at 0x7F59B44CAA70>, <PIL.Image.Image image mode=RGB size=788x788 at 0x7F59B44CBC40>], [<PIL.Image.Image image mode=RGB size=788x788 at 0x7F59B44CACE0>, <PIL.Image.Image image mode=RGB size=788x788 at 0x7F59B44CAD10>]]
[[<PIL.Image.Image image mode=RGB size=788x788 at 0x7F59B44CAB60>, <PIL.Image.Image image mode=RGB size=788x788 at 0x7F59B44CAF50>, <PIL.Image.Image image mode=RGB size=788x788 at 0x7F59B44CAA70>, <PIL.Image.Image image mode=RGB size=788x788 at 0x7F59B44CBC40>], [<PIL.Image.Image image mode=RGB size=788x788 at 0x7F59B44CACE0>, <PIL.Image.Image image mode=RGB size=788x788 at 0x7F59B44CAD10>, <PIL.Image.Image image mode=RGBA size=788x788 at 0x7F59B44CAC50>, <PIL.Image.Image image mode=RGBA size=788x788 at 0x7F59B44CAC50>]]
0 (214, 718)
0 (201, 717)
0 (1, 717)
Pipelines loaded with `dtype=torch.float16` cannot run with `cpu` device. It is not recommended to move them to `cpu` as running them will fail. Please make sure to use an accelerator to run the pipeline in inference, due to the lack of support for`float16` operations on this device in PyTorch. Please, remove the `torch_dtype=torch.float16` argument, or use another device for inference.
Pipelines loaded with `dtype=torch.float16` cannot run with `cpu` device. It is not recommended to move them to `cpu` as running them will fail. Please make sure to use an accelerator to run the pipeline in inference, due to the lack of support for`float16` operations on this device in PyTorch. Please, remove the `torch_dtype=torch.float16` argument, or use another device for inference.
Pipelines loaded with `dtype=torch.float16` cannot run with `cpu` device. It is not recommended to move them to `cpu` as running them will fail. Please make sure to use an accelerator to run the pipeline in inference, due to the lack of support for`float16` operations on this device in PyTorch. Please, remove the `torch_dtype=torch.float16` argument, or use another device for inference.
successsfully load paired self-attention
number of the processor : 36

Version Details

Version ID: a43c7e0e4bce75ee98445b20b244240d1109e30a46bf7719958fd0a69ab29e8e
Version Created: May 3, 2024

Run on Replicate →