mchong6
/
gans-n-roses
Convert image or video of your face to anime
Prediction
mchong6/gans-n-roses:3184865fIDinrqympobrfq3l565ecynkhy6qStatusSucceededSourceWebHardware–Total durationCreatedInput
{ "inpath": "https://replicate.delivery/mgxm/7a6a089b-1505-4eb6-ab6d-987843b62b4c/robbie.jpeg" }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run mchong6/gans-n-roses using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "mchong6/gans-n-roses:3184865fe046280b9b202f9639a1198545677530678e86a75124aa6e0c3dc65b", { input: { inpath: "https://replicate.delivery/mgxm/7a6a089b-1505-4eb6-ab6d-987843b62b4c/robbie.jpeg" } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run mchong6/gans-n-roses using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "mchong6/gans-n-roses:3184865fe046280b9b202f9639a1198545677530678e86a75124aa6e0c3dc65b", input={ "inpath": "https://replicate.delivery/mgxm/7a6a089b-1505-4eb6-ab6d-987843b62b4c/robbie.jpeg" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run mchong6/gans-n-roses using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "3184865fe046280b9b202f9639a1198545677530678e86a75124aa6e0c3dc65b", "input": { "inpath": "https://replicate.delivery/mgxm/7a6a089b-1505-4eb6-ab6d-987843b62b4c/robbie.jpeg" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cog
If you don’t have Homebrew, there are other installation options available.
Pull and run mchong6/gans-n-roses using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/mchong6/gans-n-roses@sha256:3184865fe046280b9b202f9639a1198545677530678e86a75124aa6e0c3dc65b \ -i 'inpath="https://replicate.delivery/mgxm/7a6a089b-1505-4eb6-ab6d-987843b62b4c/robbie.jpeg"'
To learn more, take a look at the Cog documentation.
Pull and run mchong6/gans-n-roses using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/mchong6/gans-n-roses@sha256:3184865fe046280b9b202f9639a1198545677530678e86a75124aa6e0c3dc65b
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "inpath": "https://replicate.delivery/mgxm/7a6a089b-1505-4eb6-ab6d-987843b62b4c/robbie.jpeg" } }' \ http://localhost:5000/predictions
Output
{ "completed_at": "2022-05-25T08:17:38.811679Z", "created_at": "2022-05-25T08:16:44.152316Z", "data_removed": false, "error": null, "id": "inrqympobrfq3l565ecynkhy6q", "input": { "inpath": "https://replicate.delivery/mgxm/7a6a089b-1505-4eb6-ab6d-987843b62b4c/robbie.jpeg" }, "logs": "*** Processing image input: /tmp/tmpexq8e13jrobbie.jpeg ***\n/root/.pyenv/versions/3.8.13/lib/python3.8/site-packages/torchvision/utils.py:63: UserWarning: The parameter 'range' is deprecated since 0.12 and will be removed in 0.14. Please use 'value_range' instead.\n warnings.warn(\nsaving to /tmp/tmpbazdezcy/output.png", "metrics": { "predict_time": 9.950347, "total_time": 54.659363 }, "output": "https://replicate.delivery/mgxm/1f0618ba-78c5-4eea-a668-7ed59e5181a4/output.png", "started_at": "2022-05-25T08:17:28.861332Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/inrqympobrfq3l565ecynkhy6q", "cancel": "https://api.replicate.com/v1/predictions/inrqympobrfq3l565ecynkhy6q/cancel" }, "version": "46a971683df0f15ad7b37f20f220f6739c7a85f6f8508969e780828e8473ab08" }
Generated in*** Processing image input: /tmp/tmpexq8e13jrobbie.jpeg *** /root/.pyenv/versions/3.8.13/lib/python3.8/site-packages/torchvision/utils.py:63: UserWarning: The parameter 'range' is deprecated since 0.12 and will be removed in 0.14. Please use 'value_range' instead. warnings.warn( saving to /tmp/tmpbazdezcy/output.png
Prediction
mchong6/gans-n-roses:3184865fIDs5mratasajhu3pp5isomawnijiStatusSucceededSourceWebHardware–Total durationCreatedInput
{ "inpath": "https://replicate.delivery/mgxm/513d239e-5eb6-4658-a5d5-27b305dcee87/hepburn.jpeg" }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run mchong6/gans-n-roses using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "mchong6/gans-n-roses:3184865fe046280b9b202f9639a1198545677530678e86a75124aa6e0c3dc65b", { input: { inpath: "https://replicate.delivery/mgxm/513d239e-5eb6-4658-a5d5-27b305dcee87/hepburn.jpeg" } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run mchong6/gans-n-roses using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "mchong6/gans-n-roses:3184865fe046280b9b202f9639a1198545677530678e86a75124aa6e0c3dc65b", input={ "inpath": "https://replicate.delivery/mgxm/513d239e-5eb6-4658-a5d5-27b305dcee87/hepburn.jpeg" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run mchong6/gans-n-roses using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "3184865fe046280b9b202f9639a1198545677530678e86a75124aa6e0c3dc65b", "input": { "inpath": "https://replicate.delivery/mgxm/513d239e-5eb6-4658-a5d5-27b305dcee87/hepburn.jpeg" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cog
If you don’t have Homebrew, there are other installation options available.
Pull and run mchong6/gans-n-roses using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/mchong6/gans-n-roses@sha256:3184865fe046280b9b202f9639a1198545677530678e86a75124aa6e0c3dc65b \ -i 'inpath="https://replicate.delivery/mgxm/513d239e-5eb6-4658-a5d5-27b305dcee87/hepburn.jpeg"'
To learn more, take a look at the Cog documentation.
Pull and run mchong6/gans-n-roses using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/mchong6/gans-n-roses@sha256:3184865fe046280b9b202f9639a1198545677530678e86a75124aa6e0c3dc65b
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "inpath": "https://replicate.delivery/mgxm/513d239e-5eb6-4658-a5d5-27b305dcee87/hepburn.jpeg" } }' \ http://localhost:5000/predictions
Output
{ "completed_at": "2022-05-25T08:19:16.453209Z", "created_at": "2022-05-25T08:19:13.957874Z", "data_removed": false, "error": null, "id": "s5mratasajhu3pp5isomawniji", "input": { "inpath": "https://replicate.delivery/mgxm/513d239e-5eb6-4658-a5d5-27b305dcee87/hepburn.jpeg" }, "logs": "*** Processing image input: /tmp/tmpaaig_qe3hepburn.jpeg ***\nsaving to /tmp/tmprcqucp4k/output.png", "metrics": { "predict_time": 2.36422, "total_time": 2.495335 }, "output": "https://replicate.delivery/mgxm/c8386d42-6cf4-40a8-b639-60dd4e01f2e7/output.png", "started_at": "2022-05-25T08:19:14.088989Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/s5mratasajhu3pp5isomawniji", "cancel": "https://api.replicate.com/v1/predictions/s5mratasajhu3pp5isomawniji/cancel" }, "version": "46a971683df0f15ad7b37f20f220f6739c7a85f6f8508969e780828e8473ab08" }
Generated in*** Processing image input: /tmp/tmpaaig_qe3hepburn.jpeg *** saving to /tmp/tmprcqucp4k/output.png
Prediction
mchong6/gans-n-roses:3184865fInput
{ "inpath": "https://replicate.delivery/mgxm/acd9861b-b300-4b88-9755-a28208e910d9/liu.jpeg" }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run mchong6/gans-n-roses using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "mchong6/gans-n-roses:3184865fe046280b9b202f9639a1198545677530678e86a75124aa6e0c3dc65b", { input: { inpath: "https://replicate.delivery/mgxm/acd9861b-b300-4b88-9755-a28208e910d9/liu.jpeg" } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run mchong6/gans-n-roses using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "mchong6/gans-n-roses:3184865fe046280b9b202f9639a1198545677530678e86a75124aa6e0c3dc65b", input={ "inpath": "https://replicate.delivery/mgxm/acd9861b-b300-4b88-9755-a28208e910d9/liu.jpeg" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run mchong6/gans-n-roses using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "3184865fe046280b9b202f9639a1198545677530678e86a75124aa6e0c3dc65b", "input": { "inpath": "https://replicate.delivery/mgxm/acd9861b-b300-4b88-9755-a28208e910d9/liu.jpeg" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cog
If you don’t have Homebrew, there are other installation options available.
Pull and run mchong6/gans-n-roses using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/mchong6/gans-n-roses@sha256:3184865fe046280b9b202f9639a1198545677530678e86a75124aa6e0c3dc65b \ -i 'inpath="https://replicate.delivery/mgxm/acd9861b-b300-4b88-9755-a28208e910d9/liu.jpeg"'
To learn more, take a look at the Cog documentation.
Pull and run mchong6/gans-n-roses using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/mchong6/gans-n-roses@sha256:3184865fe046280b9b202f9639a1198545677530678e86a75124aa6e0c3dc65b
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "inpath": "https://replicate.delivery/mgxm/acd9861b-b300-4b88-9755-a28208e910d9/liu.jpeg" } }' \ http://localhost:5000/predictions
Output
{ "completed_at": "2022-05-25T08:19:32.763641Z", "created_at": "2022-05-25T08:19:30.193345Z", "data_removed": false, "error": null, "id": "f5jonaarzvcc7k5oa4frjou2ha", "input": { "inpath": "https://replicate.delivery/mgxm/acd9861b-b300-4b88-9755-a28208e910d9/liu.jpeg" }, "logs": "*** Processing image input: /tmp/tmp_wkigr6nliu.jpeg ***\nsaving to /tmp/tmpgvxcol2w/output.png", "metrics": { "predict_time": 2.479522, "total_time": 2.570296 }, "output": "https://replicate.delivery/mgxm/d49b1d6c-88a5-4356-9ea6-d3d9c5a2d65c/output.png", "started_at": "2022-05-25T08:19:30.284119Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/f5jonaarzvcc7k5oa4frjou2ha", "cancel": "https://api.replicate.com/v1/predictions/f5jonaarzvcc7k5oa4frjou2ha/cancel" }, "version": "46a971683df0f15ad7b37f20f220f6739c7a85f6f8508969e780828e8473ab08" }
Generated in*** Processing image input: /tmp/tmp_wkigr6nliu.jpeg *** saving to /tmp/tmpgvxcol2w/output.png
Prediction
mchong6/gans-n-roses:3184865fInput
- inpath
{ "inpath": "https://replicate.delivery/mgxm/3cda38b8-7444-4a96-a8e9-af607e469c27/tiktok.mp4" }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run mchong6/gans-n-roses using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "mchong6/gans-n-roses:3184865fe046280b9b202f9639a1198545677530678e86a75124aa6e0c3dc65b", { input: { inpath: "https://replicate.delivery/mgxm/3cda38b8-7444-4a96-a8e9-af607e469c27/tiktok.mp4" } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run mchong6/gans-n-roses using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "mchong6/gans-n-roses:3184865fe046280b9b202f9639a1198545677530678e86a75124aa6e0c3dc65b", input={ "inpath": "https://replicate.delivery/mgxm/3cda38b8-7444-4a96-a8e9-af607e469c27/tiktok.mp4" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run mchong6/gans-n-roses using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "3184865fe046280b9b202f9639a1198545677530678e86a75124aa6e0c3dc65b", "input": { "inpath": "https://replicate.delivery/mgxm/3cda38b8-7444-4a96-a8e9-af607e469c27/tiktok.mp4" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cog
If you don’t have Homebrew, there are other installation options available.
Pull and run mchong6/gans-n-roses using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/mchong6/gans-n-roses@sha256:3184865fe046280b9b202f9639a1198545677530678e86a75124aa6e0c3dc65b \ -i 'inpath="https://replicate.delivery/mgxm/3cda38b8-7444-4a96-a8e9-af607e469c27/tiktok.mp4"'
To learn more, take a look at the Cog documentation.
Pull and run mchong6/gans-n-roses using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/mchong6/gans-n-roses@sha256:3184865fe046280b9b202f9639a1198545677530678e86a75124aa6e0c3dc65b
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "inpath": "https://replicate.delivery/mgxm/3cda38b8-7444-4a96-a8e9-af607e469c27/tiktok.mp4" } }' \ http://localhost:5000/predictions
Output
{ "completed_at": "2022-05-25T17:07:38.032971Z", "created_at": "2022-05-25T17:04:25.474585Z", "data_removed": false, "error": null, "id": "y5ibyan26vbgjic4nwv7mknygm", "input": { "inpath": "https://replicate.delivery/mgxm/3cda38b8-7444-4a96-a8e9-af607e469c27/tiktok.mp4" }, "logs": "*** Processing video input: /tmp/tmp_alix35dtiktok.mp4 ***\n/root/.pyenv/versions/3.8.13/lib/python3.8/site-packages/torchvision/utils.py:63: UserWarning: The parameter 'range' is deprecated since 0.12 and will be removed in 0.14. Please use 'value_range' instead.\n warnings.warn(\nMoviepy - Building video /tmp/tmpj4_06mu1/output.mp4.\nMoviepy - Writing video /tmp/tmpj4_06mu1/output.mp4\n\n\nt: 0%| | 0/320 [00:00<?, ?it/s, now=None]\nt: 2%|▏ | 7/320 [00:00<00:04, 67.61it/s, now=None]\nt: 4%|▍ | 14/320 [00:00<00:04, 63.40it/s, now=None]\nt: 7%|▋ | 21/320 [00:00<00:04, 61.95it/s, now=None]\nt: 9%|▉ | 28/320 [00:00<00:04, 59.54it/s, now=None]\nt: 11%|█ | 35/320 [00:00<00:04, 59.89it/s, now=None]\nt: 13%|█▎ | 42/320 [00:00<00:04, 59.59it/s, now=None]\nt: 15%|█▌ | 48/320 [00:00<00:05, 50.53it/s, now=None]\nt: 17%|█▋ | 54/320 [00:01<00:06, 40.50it/s, now=None]\nt: 18%|█▊ | 59/320 [00:01<00:07, 34.87it/s, now=None]\nt: 20%|█▉ | 63/320 [00:01<00:07, 34.20it/s, now=None]\nt: 21%|██ | 67/320 [00:01<00:07, 33.23it/s, now=None]\nt: 22%|██▏ | 71/320 [00:01<00:08, 29.94it/s, now=None]\nt: 23%|██▎ | 75/320 [00:01<00:08, 27.71it/s, now=None]\nt: 24%|██▍ | 78/320 [00:01<00:08, 27.92it/s, now=None]\nt: 25%|██▌ | 81/320 [00:02<00:08, 28.13it/s, now=None]\nt: 27%|██▋ | 85/320 [00:02<00:07, 30.10it/s, now=None]\nt: 28%|██▊ | 89/320 [00:02<00:08, 27.72it/s, now=None]\nt: 29%|██▉ | 92/320 [00:02<00:08, 27.23it/s, now=None]\nt: 30%|██▉ | 95/320 [00:02<00:08, 26.58it/s, now=None]\nt: 31%|███ | 98/320 [00:02<00:08, 26.42it/s, now=None]\nt: 32%|███▏ | 101/320 [00:02<00:08, 24.42it/s, now=None]\nt: 33%|███▎ | 105/320 [00:02<00:07, 27.10it/s, now=None]\nt: 34%|███▍ | 109/320 [00:03<00:07, 29.79it/s, now=None]\nt: 35%|███▌ | 113/320 [00:03<00:07, 26.49it/s, now=None]\nt: 36%|███▋ | 116/320 [00:03<00:07, 26.87it/s, now=None]\nt: 37%|███▋ | 119/320 [00:03<00:07, 25.95it/s, now=None]\nt: 38%|███▊ | 122/320 [00:03<00:07, 26.21it/s, now=None]\nt: 39%|███▉ | 125/320 [00:03<00:07, 26.79it/s, now=None]\nt: 40%|████ | 129/320 [00:03<00:07, 25.71it/s, now=None]\nt: 41%|████▏ | 132/320 [00:04<00:07, 25.77it/s, now=None]\nt: 42%|████▎ | 136/320 [00:04<00:06, 29.11it/s, now=None]\nt: 43%|████▎ | 139/320 [00:04<00:06, 29.08it/s, now=None]\nt: 44%|████▍ | 142/320 [00:04<00:06, 25.82it/s, now=None]\nt: 45%|████▌ | 145/320 [00:04<00:07, 24.96it/s, now=None]\nt: 46%|████▋ | 148/320 [00:04<00:06, 24.88it/s, now=None]\nt: 47%|████▋ | 151/320 [00:04<00:06, 25.67it/s, now=None]\nt: 48%|████▊ | 154/320 [00:04<00:06, 23.75it/s, now=None]\nt: 49%|████▉ | 158/320 [00:04<00:06, 26.64it/s, now=None]\nt: 51%|█████ | 162/320 [00:05<00:05, 28.22it/s, now=None]\nt: 52%|█████▏ | 165/320 [00:05<00:05, 28.18it/s, now=None]\nt: 52%|█████▎ | 168/320 [00:05<00:05, 25.85it/s, now=None]\nt: 53%|█████▎ | 171/320 [00:05<00:06, 24.77it/s, now=None]\nt: 54%|█████▍ | 174/320 [00:05<00:05, 24.86it/s, now=None]\nt: 55%|█████▌ | 177/320 [00:05<00:06, 23.17it/s, now=None]\nt: 56%|█████▋ | 180/320 [00:05<00:05, 24.58it/s, now=None]\nt: 57%|█████▋ | 183/320 [00:05<00:05, 25.20it/s, now=None]\nt: 58%|█████▊ | 186/320 [00:06<00:05, 25.43it/s, now=None]\nt: 59%|█████▉ | 190/320 [00:06<00:04, 28.72it/s, now=None]\nt: 61%|██████ | 194/320 [00:06<00:04, 27.08it/s, now=None]\nt: 62%|██████▏ | 197/320 [00:06<00:04, 27.60it/s, now=None]\nt: 63%|██████▎ | 201/320 [00:06<00:04, 28.70it/s, now=None]\nt: 64%|██████▍ | 204/320 [00:06<00:04, 23.87it/s, now=None]\nt: 65%|██████▌ | 208/320 [00:06<00:04, 26.17it/s, now=None]\nt: 66%|██████▌ | 211/320 [00:07<00:04, 25.94it/s, now=None]\nt: 67%|██████▋ | 214/320 [00:07<00:04, 23.92it/s, now=None]\nt: 68%|██████▊ | 217/320 [00:07<00:04, 25.17it/s, now=None]\nt: 69%|██████▉ | 221/320 [00:07<00:03, 27.31it/s, now=None]\nt: 70%|███████ | 224/320 [00:07<00:03, 27.97it/s, now=None]\nt: 71%|███████ | 227/320 [00:07<00:03, 27.50it/s, now=None]\nt: 72%|███████▏ | 230/320 [00:07<00:03, 24.28it/s, now=None]\nt: 73%|███████▎ | 234/320 [00:07<00:03, 26.65it/s, now=None]\nt: 74%|███████▍ | 237/320 [00:08<00:03, 27.03it/s, now=None]\nt: 75%|███████▌ | 240/320 [00:08<00:02, 27.41it/s, now=None]\nt: 76%|███████▋ | 244/320 [00:08<00:02, 29.94it/s, now=None]\nt: 78%|███████▊ | 248/320 [00:08<00:02, 27.80it/s, now=None]\nt: 78%|███████▊ | 251/320 [00:08<00:02, 26.16it/s, now=None]\nt: 79%|███████▉ | 254/320 [00:08<00:02, 26.86it/s, now=None]\nt: 81%|████████ | 258/320 [00:08<00:02, 25.76it/s, now=None]\nt: 82%|████████▏ | 261/320 [00:08<00:02, 26.08it/s, now=None]\nt: 83%|████████▎ | 265/320 [00:09<00:01, 28.53it/s, now=None]\nt: 84%|████████▍ | 268/320 [00:09<00:01, 28.51it/s, now=None]\nt: 85%|████████▍ | 271/320 [00:09<00:01, 25.84it/s, now=None]\nt: 86%|████████▌ | 274/320 [00:09<00:01, 26.04it/s, now=None]\nt: 87%|████████▋ | 277/320 [00:09<00:01, 25.93it/s, now=None]\nt: 88%|████████▊ | 281/320 [00:09<00:01, 29.40it/s, now=None]\nt: 89%|████████▉ | 285/320 [00:09<00:01, 26.96it/s, now=None]\nt: 90%|█████████ | 289/320 [00:09<00:01, 28.95it/s, now=None]\nt: 91%|█████████▏| 292/320 [00:10<00:01, 26.79it/s, now=None]\nt: 92%|█████████▏| 295/320 [00:10<00:01, 23.79it/s, now=None]\nt: 93%|█████████▎| 298/320 [00:10<00:01, 21.79it/s, now=None]\nt: 94%|█████████▍| 301/320 [00:10<00:00, 23.56it/s, now=None]\nt: 95%|█████████▌| 305/320 [00:10<00:00, 26.48it/s, now=None]\nt: 96%|█████████▋| 308/320 [00:10<00:00, 25.79it/s, now=None]\nt: 97%|█████████▋| 311/320 [00:10<00:00, 26.06it/s, now=None]\nt: 98%|█████████▊| 314/320 [00:10<00:00, 26.60it/s, now=None]\nt: 99%|█████████▉| 318/320 [00:11<00:00, 26.36it/s, now=None]\nMoviepy - Done !\nMoviepy - video ready /tmp/tmpj4_06mu1/output.mp4\nsaving to /tmp/tmpj4_06mu1/output.mp4\n", "metrics": { "predict_time": 72.406538, "total_time": 192.558386 }, "output": "https://replicate.delivery/mgxm/f3f88682-a160-4887-b8fe-e8eebb51b145/output.mp4", "started_at": "2022-05-25T17:06:25.626433Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/y5ibyan26vbgjic4nwv7mknygm", "cancel": "https://api.replicate.com/v1/predictions/y5ibyan26vbgjic4nwv7mknygm/cancel" }, "version": "6e0ababdf7459dc736b920ef9a4731b8dbcac15c241fe4276c9ab7f5546643d7" }
Generated in*** Processing video input: /tmp/tmp_alix35dtiktok.mp4 *** /root/.pyenv/versions/3.8.13/lib/python3.8/site-packages/torchvision/utils.py:63: UserWarning: The parameter 'range' is deprecated since 0.12 and will be removed in 0.14. Please use 'value_range' instead. warnings.warn( Moviepy - Building video /tmp/tmpj4_06mu1/output.mp4. Moviepy - Writing video /tmp/tmpj4_06mu1/output.mp4 t: 0%| | 0/320 [00:00<?, ?it/s, now=None] t: 2%|▏ | 7/320 [00:00<00:04, 67.61it/s, now=None] t: 4%|▍ | 14/320 [00:00<00:04, 63.40it/s, now=None] t: 7%|▋ | 21/320 [00:00<00:04, 61.95it/s, now=None] t: 9%|▉ | 28/320 [00:00<00:04, 59.54it/s, now=None] t: 11%|█ | 35/320 [00:00<00:04, 59.89it/s, now=None] t: 13%|█▎ | 42/320 [00:00<00:04, 59.59it/s, now=None] t: 15%|█▌ | 48/320 [00:00<00:05, 50.53it/s, now=None] t: 17%|█▋ | 54/320 [00:01<00:06, 40.50it/s, now=None] t: 18%|█▊ | 59/320 [00:01<00:07, 34.87it/s, now=None] t: 20%|█▉ | 63/320 [00:01<00:07, 34.20it/s, now=None] t: 21%|██ | 67/320 [00:01<00:07, 33.23it/s, now=None] t: 22%|██▏ | 71/320 [00:01<00:08, 29.94it/s, now=None] t: 23%|██▎ | 75/320 [00:01<00:08, 27.71it/s, now=None] t: 24%|██▍ | 78/320 [00:01<00:08, 27.92it/s, now=None] t: 25%|██▌ | 81/320 [00:02<00:08, 28.13it/s, now=None] t: 27%|██▋ | 85/320 [00:02<00:07, 30.10it/s, now=None] t: 28%|██▊ | 89/320 [00:02<00:08, 27.72it/s, now=None] t: 29%|██▉ | 92/320 [00:02<00:08, 27.23it/s, now=None] t: 30%|██▉ | 95/320 [00:02<00:08, 26.58it/s, now=None] t: 31%|███ | 98/320 [00:02<00:08, 26.42it/s, now=None] t: 32%|███▏ | 101/320 [00:02<00:08, 24.42it/s, now=None] t: 33%|███▎ | 105/320 [00:02<00:07, 27.10it/s, now=None] t: 34%|███▍ | 109/320 [00:03<00:07, 29.79it/s, now=None] t: 35%|███▌ | 113/320 [00:03<00:07, 26.49it/s, now=None] t: 36%|███▋ | 116/320 [00:03<00:07, 26.87it/s, now=None] t: 37%|███▋ | 119/320 [00:03<00:07, 25.95it/s, now=None] t: 38%|███▊ | 122/320 [00:03<00:07, 26.21it/s, now=None] t: 39%|███▉ | 125/320 [00:03<00:07, 26.79it/s, now=None] t: 40%|████ | 129/320 [00:03<00:07, 25.71it/s, now=None] t: 41%|████▏ | 132/320 [00:04<00:07, 25.77it/s, now=None] t: 42%|████▎ | 136/320 [00:04<00:06, 29.11it/s, now=None] t: 43%|████▎ | 139/320 [00:04<00:06, 29.08it/s, now=None] t: 44%|████▍ | 142/320 [00:04<00:06, 25.82it/s, now=None] t: 45%|████▌ | 145/320 [00:04<00:07, 24.96it/s, now=None] t: 46%|████▋ | 148/320 [00:04<00:06, 24.88it/s, now=None] t: 47%|████▋ | 151/320 [00:04<00:06, 25.67it/s, now=None] t: 48%|████▊ | 154/320 [00:04<00:06, 23.75it/s, now=None] t: 49%|████▉ | 158/320 [00:04<00:06, 26.64it/s, now=None] t: 51%|█████ | 162/320 [00:05<00:05, 28.22it/s, now=None] t: 52%|█████▏ | 165/320 [00:05<00:05, 28.18it/s, now=None] t: 52%|█████▎ | 168/320 [00:05<00:05, 25.85it/s, now=None] t: 53%|█████▎ | 171/320 [00:05<00:06, 24.77it/s, now=None] t: 54%|█████▍ | 174/320 [00:05<00:05, 24.86it/s, now=None] t: 55%|█████▌ | 177/320 [00:05<00:06, 23.17it/s, now=None] t: 56%|█████▋ | 180/320 [00:05<00:05, 24.58it/s, now=None] t: 57%|█████▋ | 183/320 [00:05<00:05, 25.20it/s, now=None] t: 58%|█████▊ | 186/320 [00:06<00:05, 25.43it/s, now=None] t: 59%|█████▉ | 190/320 [00:06<00:04, 28.72it/s, now=None] t: 61%|██████ | 194/320 [00:06<00:04, 27.08it/s, now=None] t: 62%|██████▏ | 197/320 [00:06<00:04, 27.60it/s, now=None] t: 63%|██████▎ | 201/320 [00:06<00:04, 28.70it/s, now=None] t: 64%|██████▍ | 204/320 [00:06<00:04, 23.87it/s, now=None] t: 65%|██████▌ | 208/320 [00:06<00:04, 26.17it/s, now=None] t: 66%|██████▌ | 211/320 [00:07<00:04, 25.94it/s, now=None] t: 67%|██████▋ | 214/320 [00:07<00:04, 23.92it/s, now=None] t: 68%|██████▊ | 217/320 [00:07<00:04, 25.17it/s, now=None] t: 69%|██████▉ | 221/320 [00:07<00:03, 27.31it/s, now=None] t: 70%|███████ | 224/320 [00:07<00:03, 27.97it/s, now=None] t: 71%|███████ | 227/320 [00:07<00:03, 27.50it/s, now=None] t: 72%|███████▏ | 230/320 [00:07<00:03, 24.28it/s, now=None] t: 73%|███████▎ | 234/320 [00:07<00:03, 26.65it/s, now=None] t: 74%|███████▍ | 237/320 [00:08<00:03, 27.03it/s, now=None] t: 75%|███████▌ | 240/320 [00:08<00:02, 27.41it/s, now=None] t: 76%|███████▋ | 244/320 [00:08<00:02, 29.94it/s, now=None] t: 78%|███████▊ | 248/320 [00:08<00:02, 27.80it/s, now=None] t: 78%|███████▊ | 251/320 [00:08<00:02, 26.16it/s, now=None] t: 79%|███████▉ | 254/320 [00:08<00:02, 26.86it/s, now=None] t: 81%|████████ | 258/320 [00:08<00:02, 25.76it/s, now=None] t: 82%|████████▏ | 261/320 [00:08<00:02, 26.08it/s, now=None] t: 83%|████████▎ | 265/320 [00:09<00:01, 28.53it/s, now=None] t: 84%|████████▍ | 268/320 [00:09<00:01, 28.51it/s, now=None] t: 85%|████████▍ | 271/320 [00:09<00:01, 25.84it/s, now=None] t: 86%|████████▌ | 274/320 [00:09<00:01, 26.04it/s, now=None] t: 87%|████████▋ | 277/320 [00:09<00:01, 25.93it/s, now=None] t: 88%|████████▊ | 281/320 [00:09<00:01, 29.40it/s, now=None] t: 89%|████████▉ | 285/320 [00:09<00:01, 26.96it/s, now=None] t: 90%|█████████ | 289/320 [00:09<00:01, 28.95it/s, now=None] t: 91%|█████████▏| 292/320 [00:10<00:01, 26.79it/s, now=None] t: 92%|█████████▏| 295/320 [00:10<00:01, 23.79it/s, now=None] t: 93%|█████████▎| 298/320 [00:10<00:01, 21.79it/s, now=None] t: 94%|█████████▍| 301/320 [00:10<00:00, 23.56it/s, now=None] t: 95%|█████████▌| 305/320 [00:10<00:00, 26.48it/s, now=None] t: 96%|█████████▋| 308/320 [00:10<00:00, 25.79it/s, now=None] t: 97%|█████████▋| 311/320 [00:10<00:00, 26.06it/s, now=None] t: 98%|█████████▊| 314/320 [00:10<00:00, 26.60it/s, now=None] t: 99%|█████████▉| 318/320 [00:11<00:00, 26.36it/s, now=None] Moviepy - Done ! Moviepy - video ready /tmp/tmpj4_06mu1/output.mp4 saving to /tmp/tmpj4_06mu1/output.mp4
Want to make some of these yourself?
Run this model