tahercoolguy/diffutoon 📝🖼️ → 🖼️

▶️ 50 runs 📅 Aug 2024 ⚙️ Cog 0.9.12

About

This will convert any video to anime

Example Output

Prompt:

"best quality, perfect anime illustration"

Output

Performance Metrics

446.20s Prediction Time

628.24s Total Time

All Input Parameters

{
  "prompt": "best quality, perfect anime illustration",
  "prompt_2": "best quality, perfect anime illustration, light",
  "input_video": "https://replicate.delivery/pbxt/LWT4W9jAKsv5iAuHYe8jsfeb5t0Dze3Wgvs0FSSCfLkoWN1v/videoplayback%20%28online-video-cutter.com%29.mp4"
}

Input Parameters

prompt Type: stringDefault: best quality, perfect anime illustration, orange clothes, night, a girl is dancing, smile, solo, black silk stockings: Prompt for stage 1
prompt_2 Type: stringDefault: best quality, perfect anime illustration, light, a girl is dancing, smile, solo: Prompt for stage 2
input_video (required) Type: string: Input video

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Loading models from: models/stable_diffusion/aingdiffusion_v12.safetensors
model_name: sd_text_encoder model_class: SDTextEncoder
model_name: sd_unet model_class: SDUNet
model_name: sd_vae_decoder model_class: SDVAEDecoder
model_name: sd_vae_encoder model_class: SDVAEEncoder
The following models are loaded: ['sd_text_encoder', 'sd_unet', 'sd_vae_decoder', 'sd_vae_encoder'].
Loading models from: models/ControlNet/control_v11p_sd15_softedge.pth
model_name: sd_controlnet model_class: SDControlNet
    The following models are loaded: ['sd_controlnet'].
Loading models from: models/ControlNet/control_v11f1p_sd15_depth.pth
model_name: sd_controlnet model_class: SDControlNet
    The following models are loaded: ['sd_controlnet'].
Using sd_text_encoder from models/stable_diffusion/aingdiffusion_v12.safetensors.
Using sd_unet from models/stable_diffusion/aingdiffusion_v12.safetensors.
Using sd_vae_decoder from models/stable_diffusion/aingdiffusion_v12.safetensors.
Using sd_vae_encoder from models/stable_diffusion/aingdiffusion_v12.safetensors.
Using sd_controlnet from models/ControlNet/control_v11p_sd15_softedge.pth.
/root/.pyenv/versions/3.10.14/lib/python3.10/site-packages/timm/models/_factory.py:117: UserWarning: Mapping deprecated model name vit_base_resnet50_384 to current vit_base_r50_s16_384.orig_in21k_ft_in1k.
model = create_fn(
Using sd_controlnet from models/ControlNet/control_v11f1p_sd15_depth.pth.
No sd_ipadapter models available.
No sd_ipadapter_clip_image_encoder models available.
No sd_motion_modules models available.
Textual inversion verybadimagenegative_v1.3 is enabled.
  0%|          | 0/30 [00:00<?, ?it/s]
 13%|█▎        | 4/30 [00:00<00:00, 35.27it/s]
 33%|███▎      | 10/30 [00:00<00:00, 47.84it/s]
 53%|█████▎    | 16/30 [00:00<00:00, 52.49it/s]
 73%|███████▎  | 22/30 [00:00<00:00, 54.72it/s]
 93%|█████████▎| 28/30 [00:00<00:00, 55.80it/s]
100%|██████████| 30/30 [00:00<00:00, 53.08it/s]
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:03,  8.06it/s]
 13%|█▎        | 4/30 [00:00<00:01, 18.45it/s]
 23%|██▎       | 7/30 [00:00<00:01, 22.11it/s]
 33%|███▎      | 10/30 [00:00<00:00, 23.87it/s]
 43%|████▎     | 13/30 [00:00<00:00, 24.80it/s]
 53%|█████▎    | 16/30 [00:00<00:00, 25.32it/s]
 63%|██████▎   | 19/30 [00:00<00:00, 25.66it/s]
 73%|███████▎  | 22/30 [00:00<00:00, 25.92it/s]
 83%|████████▎ | 25/30 [00:01<00:00, 26.07it/s]
 93%|█████████▎| 28/30 [00:01<00:00, 26.11it/s]
100%|██████████| 30/30 [00:01<00:00, 24.57it/s]
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:06<02:09,  6.80s/it]
 10%|█         | 2/20 [00:13<02:00,  6.70s/it]
 15%|█▌        | 3/20 [00:20<01:53,  6.67s/it]
 20%|██        | 4/20 [00:26<01:46,  6.66s/it]
 25%|██▌       | 5/20 [00:33<01:39,  6.66s/it]
 30%|███       | 6/20 [00:40<01:33,  6.66s/it]
 35%|███▌      | 7/20 [00:46<01:26,  6.68s/it]
 40%|████      | 8/20 [00:53<01:20,  6.67s/it]
 45%|████▌     | 9/20 [01:00<01:13,  6.67s/it]
 50%|█████     | 10/20 [01:06<01:06,  6.68s/it]
 55%|█████▌    | 11/20 [01:13<01:00,  6.67s/it]
 60%|██████    | 12/20 [01:20<00:53,  6.68s/it]
 65%|██████▌   | 13/20 [01:26<00:46,  6.69s/it]
 70%|███████   | 14/20 [01:33<00:40,  6.69s/it]
 75%|███████▌  | 15/20 [01:40<00:33,  6.69s/it]
 80%|████████  | 16/20 [01:46<00:26,  6.69s/it]
 85%|████████▌ | 17/20 [01:53<00:20,  6.69s/it]
 90%|█████████ | 18/20 [02:00<00:13,  6.69s/it]
 95%|█████████▌| 19/20 [02:07<00:06,  6.69s/it]
100%|██████████| 20/20 [02:13<00:00,  6.69s/it]
100%|██████████| 20/20 [02:13<00:00,  6.69s/it]
Fast Mode Step 1/4:   0%|          | 0/7 [00:00<?, ?it/s]
Fast Mode Step 1/4:  14%|█▍        | 1/7 [00:09<00:57,  9.57s/it]
Fast Mode Step 1/4:  29%|██▊       | 2/7 [00:10<00:21,  4.25s/it]
Fast Mode Step 1/4:  43%|████▎     | 3/7 [00:10<00:10,  2.55s/it]
Fast Mode Step 1/4:  57%|█████▋    | 4/7 [00:11<00:05,  1.75s/it]
Fast Mode Step 1/4:  71%|███████▏  | 5/7 [00:11<00:02,  1.30s/it]
Fast Mode Step 1/4:  86%|████████▌ | 6/7 [00:12<00:01,  1.04s/it]
Fast Mode Step 1/4: 100%|██████████| 7/7 [00:12<00:00,  1.07it/s]
Fast Mode Step 1/4: 100%|██████████| 7/7 [00:12<00:00,  1.84s/it]
Fast Mode Step 2/4:   0%|          | 0/6 [00:00<?, ?it/s]
Fast Mode Step 2/4:  17%|█▋        | 1/6 [00:00<00:02,  1.91it/s]
Fast Mode Step 2/4:  33%|███▎      | 2/6 [00:01<00:02,  1.92it/s]
Fast Mode Step 2/4:  50%|█████     | 3/6 [00:01<00:01,  1.92it/s]
Fast Mode Step 2/4:  67%|██████▋   | 4/6 [00:02<00:01,  1.39it/s]
Fast Mode Step 2/4:  83%|████████▎ | 5/6 [00:03<00:00,  1.55it/s]
Fast Mode Step 2/4: 100%|██████████| 6/6 [00:03<00:00,  1.76it/s]
Fast Mode Step 2/4: 100%|██████████| 6/6 [00:03<00:00,  1.70it/s]
Fast Mode Step 3/4:   0%|          | 0/7 [00:00<?, ?it/s]
Fast Mode Step 3/4:  14%|█▍        | 1/7 [00:00<00:03,  1.92it/s]
Fast Mode Step 3/4:  29%|██▊       | 2/7 [00:01<00:02,  1.94it/s]
Fast Mode Step 3/4:  43%|████▎     | 3/7 [00:01<00:02,  1.95it/s]
Fast Mode Step 3/4:  57%|█████▋    | 4/7 [00:02<00:01,  1.95it/s]
Fast Mode Step 3/4:  71%|███████▏  | 5/7 [00:02<00:01,  1.95it/s]
Fast Mode Step 3/4:  86%|████████▌ | 6/7 [00:03<00:00,  1.93it/s]
Fast Mode Step 3/4: 100%|██████████| 7/7 [00:03<00:00,  2.31it/s]
Fast Mode Step 3/4: 100%|██████████| 7/7 [00:03<00:00,  2.09it/s]
Fast Mode Step 4/4:   0%|          | 0/6 [00:00<?, ?it/s]
Fast Mode Step 4/4:  17%|█▋        | 1/6 [00:00<00:02,  1.91it/s]
Fast Mode Step 4/4:  33%|███▎      | 2/6 [00:01<00:02,  1.93it/s]
Fast Mode Step 4/4:  50%|█████     | 3/6 [00:01<00:01,  1.92it/s]
Fast Mode Step 4/4:  67%|██████▋   | 4/6 [00:02<00:01,  1.93it/s]
Fast Mode Step 4/4:  83%|████████▎ | 5/6 [00:02<00:00,  1.92it/s]
Fast Mode Step 4/4: 100%|██████████| 6/6 [00:03<00:00,  2.08it/s]
Fast Mode Step 4/4: 100%|██████████| 6/6 [00:03<00:00,  2.00it/s]
Saving images:   0%|          | 0/30 [00:00<?, ?it/s]
Saving images:   7%|▋         | 2/30 [00:00<00:02, 12.21it/s]
Saving images:  13%|█▎        | 4/30 [00:00<00:02, 12.41it/s]
Saving images:  20%|██        | 6/30 [00:00<00:01, 12.55it/s]
Saving images:  27%|██▋       | 8/30 [00:00<00:01, 12.62it/s]
Saving images:  33%|███▎      | 10/30 [00:00<00:01, 12.67it/s]
Saving images:  40%|████      | 12/30 [00:00<00:01, 12.66it/s]
Saving images:  47%|████▋     | 14/30 [00:01<00:01, 12.65it/s]
Saving images:  53%|█████▎    | 16/30 [00:01<00:01, 12.60it/s]
Saving images:  60%|██████    | 18/30 [00:01<00:00, 12.61it/s]
Saving images:  67%|██████▋   | 20/30 [00:01<00:00, 12.61it/s]
Saving images:  73%|███████▎  | 22/30 [00:01<00:00, 12.59it/s]
Saving images:  80%|████████  | 24/30 [00:01<00:00, 12.57it/s]
Saving images:  87%|████████▋ | 26/30 [00:02<00:00, 12.56it/s]
Saving images:  93%|█████████▎| 28/30 [00:02<00:00, 12.56it/s]
Saving images: 100%|██████████| 30/30 [00:02<00:00, 12.55it/s]
Saving images: 100%|██████████| 30/30 [00:02<00:00, 12.58it/s]
Saving video:   0%|          | 0/30 [00:00<?, ?it/s]
Saving video:   3%|▎         | 1/30 [00:00<00:06,  4.52it/s]
Saving video: 100%|██████████| 30/30 [00:00<00:00, 112.54it/s]
Loading models from: models/stable_diffusion/aingdiffusion_v12.safetensors
model_name: sd_text_encoder model_class: SDTextEncoder
model_name: sd_unet model_class: SDUNet
model_name: sd_vae_decoder model_class: SDVAEDecoder
model_name: sd_vae_encoder model_class: SDVAEEncoder
The following models are loaded: ['sd_text_encoder', 'sd_unet', 'sd_vae_decoder', 'sd_vae_encoder'].
Loading models from: models/AnimateDiff/mm_sd_v15_v2.ckpt
model_name: sd_motion_modules model_class: SDMotionModel
    The following models are loaded: ['sd_motion_modules'].
Loading models from: models/ControlNet/control_v11f1e_sd15_tile.pth
model_name: sd_controlnet model_class: SDControlNet
    The following models are loaded: ['sd_controlnet'].
Loading models from: models/ControlNet/control_v11p_sd15_lineart.pth
model_name: sd_controlnet model_class: SDControlNet
    The following models are loaded: ['sd_controlnet'].
Using sd_text_encoder from models/stable_diffusion/aingdiffusion_v12.safetensors.
Using sd_unet from models/stable_diffusion/aingdiffusion_v12.safetensors.
Using sd_vae_decoder from models/stable_diffusion/aingdiffusion_v12.safetensors.
Using sd_vae_encoder from models/stable_diffusion/aingdiffusion_v12.safetensors.
Using sd_controlnet from models/ControlNet/control_v11f1e_sd15_tile.pth.
Using sd_controlnet from models/ControlNet/control_v11p_sd15_lineart.pth.
No sd_ipadapter models available.
No sd_ipadapter_clip_image_encoder models available.
Using sd_motion_modules from models/AnimateDiff/mm_sd_v15_v2.ckpt.
Textual inversion verybadimagenegative_v1.3 is enabled.
  0%|          | 0/30 [00:00<?, ?it/s]
 57%|█████▋    | 17/30 [00:00<00:00, 166.58it/s]
100%|██████████| 30/30 [00:00<00:00, 180.05it/s]
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:03<01:42,  3.52s/it]
 10%|█         | 3/30 [00:03<00:25,  1.05it/s]
 17%|█▋        | 5/30 [00:03<00:12,  2.03it/s]
 23%|██▎       | 7/30 [00:03<00:07,  3.24it/s]
 30%|███       | 9/30 [00:03<00:04,  4.67it/s]
 37%|███▋      | 11/30 [00:04<00:03,  6.20it/s]
 43%|████▎     | 13/30 [00:04<00:02,  7.82it/s]
 50%|█████     | 15/30 [00:04<00:01,  9.38it/s]
 57%|█████▋    | 17/30 [00:04<00:01, 10.84it/s]
 63%|██████▎   | 19/30 [00:04<00:00, 12.27it/s]
 70%|███████   | 21/30 [00:04<00:00, 13.54it/s]
 77%|███████▋  | 23/30 [00:04<00:00, 14.57it/s]
 83%|████████▎ | 25/30 [00:04<00:00, 15.42it/s]
 90%|█████████ | 27/30 [00:05<00:00, 15.95it/s]
 97%|█████████▋| 29/30 [00:05<00:00, 16.42it/s]
100%|██████████| 30/30 [00:05<00:00,  5.75it/s]
  0%|          | 0/10 [00:00<?, ?it/s]
 10%|█         | 1/10 [00:21<03:15, 21.68s/it]
 20%|██        | 2/10 [00:42<02:51, 21.39s/it]
 30%|███       | 3/10 [01:04<02:29, 21.31s/it]
 40%|████      | 4/10 [01:25<02:07, 21.27s/it]
 50%|█████     | 5/10 [01:46<01:46, 21.31s/it]
 60%|██████    | 6/10 [02:07<01:25, 21.31s/it]
 70%|███████   | 7/10 [02:29<01:03, 21.30s/it]
 80%|████████  | 8/10 [02:50<00:42, 21.31s/it]
 90%|█████████ | 9/10 [03:11<00:21, 21.30s/it]
100%|██████████| 10/10 [03:33<00:00, 21.30s/it]
100%|██████████| 10/10 [03:33<00:00, 21.32s/it]
Saving images:   0%|          | 0/30 [00:00<?, ?it/s]
Saving images:   3%|▎         | 1/30 [00:00<00:13,  2.21it/s]
Saving images:   7%|▋         | 2/30 [00:00<00:13,  2.12it/s]
Saving images:  10%|█         | 3/30 [00:01<00:12,  2.17it/s]
Saving images:  13%|█▎        | 4/30 [00:01<00:11,  2.19it/s]
Saving images:  17%|█▋        | 5/30 [00:02<00:11,  2.21it/s]
Saving images:  20%|██        | 6/30 [00:02<00:10,  2.22it/s]
Saving images:  23%|██▎       | 7/30 [00:03<00:10,  2.23it/s]
Saving images:  27%|██▋       | 8/30 [00:03<00:09,  2.24it/s]
Saving images:  30%|███       | 9/30 [00:04<00:09,  2.24it/s]
Saving images:  33%|███▎      | 10/30 [00:04<00:08,  2.25it/s]
Saving images:  37%|███▋      | 11/30 [00:04<00:08,  2.25it/s]
Saving images:  40%|████      | 12/30 [00:05<00:07,  2.26it/s]
Saving images:  43%|████▎     | 13/30 [00:05<00:07,  2.26it/s]
Saving images:  47%|████▋     | 14/30 [00:06<00:07,  2.28it/s]
Saving images:  50%|█████     | 15/30 [00:06<00:06,  2.30it/s]
Saving images:  53%|█████▎    | 16/30 [00:07<00:06,  2.31it/s]
Saving images:  57%|█████▋    | 17/30 [00:07<00:05,  2.33it/s]
Saving images:  60%|██████    | 18/30 [00:07<00:05,  2.35it/s]
Saving images:  63%|██████▎   | 19/30 [00:08<00:04,  2.36it/s]
Saving images:  67%|██████▋   | 20/30 [00:08<00:04,  2.37it/s]
Saving images:  70%|███████   | 21/30 [00:09<00:03,  2.37it/s]
Saving images:  73%|███████▎  | 22/30 [00:09<00:03,  2.38it/s]
Saving images:  77%|███████▋  | 23/30 [00:10<00:02,  2.39it/s]
Saving images:  80%|████████  | 24/30 [00:10<00:02,  2.39it/s]
Saving images:  83%|████████▎ | 25/30 [00:10<00:02,  2.40it/s]
Saving images:  87%|████████▋ | 26/30 [00:11<00:01,  2.41it/s]
Saving images:  90%|█████████ | 27/30 [00:11<00:01,  2.41it/s]
Saving images:  93%|█████████▎| 28/30 [00:12<00:00,  2.42it/s]
Saving images:  97%|█████████▋| 29/30 [00:12<00:00,  2.43it/s]
Saving images: 100%|██████████| 30/30 [00:12<00:00,  2.43it/s]
Saving images: 100%|██████████| 30/30 [00:12<00:00,  2.32it/s]
Saving video:   0%|          | 0/30 [00:00<?, ?it/s]
Saving video:   3%|▎         | 1/30 [00:00<00:10,  2.82it/s]
Saving video:   7%|▋         | 2/30 [00:00<00:06,  4.10it/s]
Saving video:  27%|██▋       | 8/30 [00:00<00:01, 18.10it/s]
Saving video:  53%|█████▎    | 16/30 [00:00<00:00, 33.81it/s]
Saving video:  70%|███████   | 21/30 [00:01<00:00, 18.86it/s]
Saving video:  83%|████████▎ | 25/30 [00:01<00:00, 17.70it/s]
Saving video:  93%|█████████▎| 28/30 [00:01<00:00, 14.59it/s]
Saving video: 100%|██████████| 30/30 [00:01<00:00, 16.47it/s]

Version Details

Version ID: f30bf4a6704cba69771c4476c419c5ee6ce9650d584b5c0c84deda6d9142461e
Version Created: August 28, 2024

Run on Replicate →