twn39 / lama
π¦ LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
- Public
- 25.8K runs
-
L40S
- Paper
Prediction
twn39/lama:663392a92eb159ab831b6cbd2131f96d7323e70fb14902edb9f903ff6aea6570ModelID32d62hbbrzeecevdvoziup5ncqStatusSucceededSourceWebHardwareT4Total durationCreatedInput
- mask
- image
{ "mask": "https://replicate.delivery/pbxt/JvTRKJGicDDw0Dmb2wNl9pzMHfc9o9PKGOzFRXePz0C8kS54/ComfyUI_temp_vvldi_00012__mask.jpg", "image": "https://replicate.delivery/pbxt/JvTRKxR8l9fWHtZs32TVt1e0eGERhjZNMpnHurpZBv7JwcG3/ComfyUI_temp_vvldi_00012_.png" }Install Replicateβs Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run twn39/lama using Replicateβs API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "twn39/lama:663392a92eb159ab831b6cbd2131f96d7323e70fb14902edb9f903ff6aea6570", { input: { mask: "https://replicate.delivery/pbxt/JvTRKJGicDDw0Dmb2wNl9pzMHfc9o9PKGOzFRXePz0C8kS54/ComfyUI_temp_vvldi_00012__mask.jpg", image: "https://replicate.delivery/pbxt/JvTRKxR8l9fWHtZs32TVt1e0eGERhjZNMpnHurpZBv7JwcG3/ComfyUI_temp_vvldi_00012_.png" } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicateβs Python client library:pip install replicateImport the client:import replicateRun twn39/lama using Replicateβs API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "twn39/lama:663392a92eb159ab831b6cbd2131f96d7323e70fb14902edb9f903ff6aea6570", input={ "mask": "https://replicate.delivery/pbxt/JvTRKJGicDDw0Dmb2wNl9pzMHfc9o9PKGOzFRXePz0C8kS54/ComfyUI_temp_vvldi_00012__mask.jpg", "image": "https://replicate.delivery/pbxt/JvTRKxR8l9fWHtZs32TVt1e0eGERhjZNMpnHurpZBv7JwcG3/ComfyUI_temp_vvldi_00012_.png" } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())To learn more, take a look at the guide on getting started with Python.
Run twn39/lama using Replicateβs 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": "twn39/lama:663392a92eb159ab831b6cbd2131f96d7323e70fb14902edb9f903ff6aea6570", "input": { "mask": "https://replicate.delivery/pbxt/JvTRKJGicDDw0Dmb2wNl9pzMHfc9o9PKGOzFRXePz0C8kS54/ComfyUI_temp_vvldi_00012__mask.jpg", "image": "https://replicate.delivery/pbxt/JvTRKxR8l9fWHtZs32TVt1e0eGERhjZNMpnHurpZBv7JwcG3/ComfyUI_temp_vvldi_00012_.png" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicateβs HTTP API reference docs.
Output
{ "completed_at": "2023-11-23T08:14:03.443113Z", "created_at": "2023-11-23T08:13:41.029040Z", "data_removed": false, "error": null, "id": "32d62hbbrzeecevdvoziup5ncq", "input": { "mask": "https://replicate.delivery/pbxt/JvTRKJGicDDw0Dmb2wNl9pzMHfc9o9PKGOzFRXePz0C8kS54/ComfyUI_temp_vvldi_00012__mask.jpg", "image": "https://replicate.delivery/pbxt/JvTRKxR8l9fWHtZs32TVt1e0eGERhjZNMpnHurpZBv7JwcG3/ComfyUI_temp_vvldi_00012_.png" }, "logs": "Original image too large for refinement! Resizing (1152, 896) to (1075, 836)...\n 0%| | 0/15 [00:00<?, ?it/s]\n 0%| | 0/15 [00:00<?, ?it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0331: 0%| | 0/15 [00:00<?, ?it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0331: 7%|β | 1/15 [00:01<00:16, 1.17s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0292: 7%|β | 1/15 [00:01<00:16, 1.17s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0292: 13%|ββ | 2/15 [00:02<00:16, 1.30s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0223: 13%|ββ | 2/15 [00:03<00:16, 1.30s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0223: 20%|ββ | 3/15 [00:03<00:16, 1.34s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0221: 20%|ββ | 3/15 [00:04<00:16, 1.34s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0221: 27%|βββ | 4/15 [00:05<00:15, 1.37s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0198: 27%|βββ | 4/15 [00:06<00:15, 1.37s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0198: 33%|ββββ | 5/15 [00:06<00:13, 1.38s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0185: 33%|ββββ | 5/15 [00:07<00:13, 1.38s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0185: 40%|ββββ | 6/15 [00:08<00:12, 1.39s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0177: 40%|ββββ | 6/15 [00:08<00:12, 1.39s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0177: 47%|βββββ | 7/15 [00:09<00:11, 1.40s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0167: 47%|βββββ | 7/15 [00:10<00:11, 1.40s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0167: 53%|ββββββ | 8/15 [00:11<00:09, 1.40s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0161: 53%|ββββββ | 8/15 [00:11<00:09, 1.40s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0161: 60%|ββββββ | 9/15 [00:12<00:08, 1.41s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0155: 60%|ββββββ | 9/15 [00:13<00:08, 1.41s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0155: 67%|βββββββ | 10/15 [00:13<00:07, 1.42s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0147: 67%|βββββββ | 10/15 [00:14<00:07, 1.42s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0147: 73%|ββββββββ | 11/15 [00:15<00:05, 1.43s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0142: 73%|ββββββββ | 11/15 [00:16<00:05, 1.43s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0142: 80%|ββββββββ | 12/15 [00:16<00:04, 1.43s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0137: 80%|ββββββββ | 12/15 [00:17<00:04, 1.43s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0137: 87%|βββββββββ | 13/15 [00:18<00:02, 1.44s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0133: 87%|βββββββββ | 13/15 [00:18<00:02, 1.44s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0133: 93%|ββββββββββ| 14/15 [00:19<00:01, 1.45s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0129: 93%|ββββββββββ| 14/15 [00:20<00:01, 1.45s/it]\nRefining scale 2 using scale 1 ...current loss: 0.0129: 100%|ββββββββββ| 15/15 [00:20<00:00, 1.24s/it]", "metrics": { "predict_time": 22.396727, "total_time": 22.414073 }, "output": "https://replicate.delivery/pbxt/O1oyCjsafhTKe0fCnKx1qrY0KnbbSyQphzBGXKExk61UeusHB/output.png", "started_at": "2023-11-23T08:13:41.046386Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/32d62hbbrzeecevdvoziup5ncq", "cancel": "https://api.replicate.com/v1/predictions/32d62hbbrzeecevdvoziup5ncq/cancel" }, "version": "663392a92eb159ab831b6cbd2131f96d7323e70fb14902edb9f903ff6aea6570" }Generated inOriginal image too large for refinement! Resizing (1152, 896) to (1075, 836)... 0%| | 0/15 [00:00<?, ?it/s] 0%| | 0/15 [00:00<?, ?it/s] Refining scale 2 using scale 1 ...current loss: 0.0331: 0%| | 0/15 [00:00<?, ?it/s] Refining scale 2 using scale 1 ...current loss: 0.0331: 7%|β | 1/15 [00:01<00:16, 1.17s/it] Refining scale 2 using scale 1 ...current loss: 0.0292: 7%|β | 1/15 [00:01<00:16, 1.17s/it] Refining scale 2 using scale 1 ...current loss: 0.0292: 13%|ββ | 2/15 [00:02<00:16, 1.30s/it] Refining scale 2 using scale 1 ...current loss: 0.0223: 13%|ββ | 2/15 [00:03<00:16, 1.30s/it] Refining scale 2 using scale 1 ...current loss: 0.0223: 20%|ββ | 3/15 [00:03<00:16, 1.34s/it] Refining scale 2 using scale 1 ...current loss: 0.0221: 20%|ββ | 3/15 [00:04<00:16, 1.34s/it] Refining scale 2 using scale 1 ...current loss: 0.0221: 27%|βββ | 4/15 [00:05<00:15, 1.37s/it] Refining scale 2 using scale 1 ...current loss: 0.0198: 27%|βββ | 4/15 [00:06<00:15, 1.37s/it] Refining scale 2 using scale 1 ...current loss: 0.0198: 33%|ββββ | 5/15 [00:06<00:13, 1.38s/it] Refining scale 2 using scale 1 ...current loss: 0.0185: 33%|ββββ | 5/15 [00:07<00:13, 1.38s/it] Refining scale 2 using scale 1 ...current loss: 0.0185: 40%|ββββ | 6/15 [00:08<00:12, 1.39s/it] Refining scale 2 using scale 1 ...current loss: 0.0177: 40%|ββββ | 6/15 [00:08<00:12, 1.39s/it] Refining scale 2 using scale 1 ...current loss: 0.0177: 47%|βββββ | 7/15 [00:09<00:11, 1.40s/it] Refining scale 2 using scale 1 ...current loss: 0.0167: 47%|βββββ | 7/15 [00:10<00:11, 1.40s/it] Refining scale 2 using scale 1 ...current loss: 0.0167: 53%|ββββββ | 8/15 [00:11<00:09, 1.40s/it] Refining scale 2 using scale 1 ...current loss: 0.0161: 53%|ββββββ | 8/15 [00:11<00:09, 1.40s/it] Refining scale 2 using scale 1 ...current loss: 0.0161: 60%|ββββββ | 9/15 [00:12<00:08, 1.41s/it] Refining scale 2 using scale 1 ...current loss: 0.0155: 60%|ββββββ | 9/15 [00:13<00:08, 1.41s/it] Refining scale 2 using scale 1 ...current loss: 0.0155: 67%|βββββββ | 10/15 [00:13<00:07, 1.42s/it] Refining scale 2 using scale 1 ...current loss: 0.0147: 67%|βββββββ | 10/15 [00:14<00:07, 1.42s/it] Refining scale 2 using scale 1 ...current loss: 0.0147: 73%|ββββββββ | 11/15 [00:15<00:05, 1.43s/it] Refining scale 2 using scale 1 ...current loss: 0.0142: 73%|ββββββββ | 11/15 [00:16<00:05, 1.43s/it] Refining scale 2 using scale 1 ...current loss: 0.0142: 80%|ββββββββ | 12/15 [00:16<00:04, 1.43s/it] Refining scale 2 using scale 1 ...current loss: 0.0137: 80%|ββββββββ | 12/15 [00:17<00:04, 1.43s/it] Refining scale 2 using scale 1 ...current loss: 0.0137: 87%|βββββββββ | 13/15 [00:18<00:02, 1.44s/it] Refining scale 2 using scale 1 ...current loss: 0.0133: 87%|βββββββββ | 13/15 [00:18<00:02, 1.44s/it] Refining scale 2 using scale 1 ...current loss: 0.0133: 93%|ββββββββββ| 14/15 [00:19<00:01, 1.45s/it] Refining scale 2 using scale 1 ...current loss: 0.0129: 93%|ββββββββββ| 14/15 [00:20<00:01, 1.45s/it] Refining scale 2 using scale 1 ...current loss: 0.0129: 100%|ββββββββββ| 15/15 [00:20<00:00, 1.24s/it]Prediction
twn39/lama:c5537e510ca1323c525a61ce462a32a4c5e9bdbb0d75a577fa07f06aa0b969e8ModelIDomjan3tba7hgbgwfwrfeo6chrmStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- mask
- image
{ "mask": "https://replicate.delivery/pbxt/JvTNNI5GXp1iol2Sjf3XYfUX83Bemhx4Q5TwoAOeZJXrvc8m/image_inpainting_mask.png", "image": "https://replicate.delivery/pbxt/JvTNNPkuMNTMjetsF4LO9eKdXAPy9xkNqUcphkbFcA2WF2TH/image_inpainting.png" }Install Replicateβs Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run twn39/lama using Replicateβs API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "twn39/lama:c5537e510ca1323c525a61ce462a32a4c5e9bdbb0d75a577fa07f06aa0b969e8", { input: { mask: "https://replicate.delivery/pbxt/JvTNNI5GXp1iol2Sjf3XYfUX83Bemhx4Q5TwoAOeZJXrvc8m/image_inpainting_mask.png", image: "https://replicate.delivery/pbxt/JvTNNPkuMNTMjetsF4LO9eKdXAPy9xkNqUcphkbFcA2WF2TH/image_inpainting.png" } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicateβs Python client library:pip install replicateImport the client:import replicateRun twn39/lama using Replicateβs API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "twn39/lama:c5537e510ca1323c525a61ce462a32a4c5e9bdbb0d75a577fa07f06aa0b969e8", input={ "mask": "https://replicate.delivery/pbxt/JvTNNI5GXp1iol2Sjf3XYfUX83Bemhx4Q5TwoAOeZJXrvc8m/image_inpainting_mask.png", "image": "https://replicate.delivery/pbxt/JvTNNPkuMNTMjetsF4LO9eKdXAPy9xkNqUcphkbFcA2WF2TH/image_inpainting.png" } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())To learn more, take a look at the guide on getting started with Python.
Run twn39/lama using Replicateβs 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": "twn39/lama:c5537e510ca1323c525a61ce462a32a4c5e9bdbb0d75a577fa07f06aa0b969e8", "input": { "mask": "https://replicate.delivery/pbxt/JvTNNI5GXp1iol2Sjf3XYfUX83Bemhx4Q5TwoAOeZJXrvc8m/image_inpainting_mask.png", "image": "https://replicate.delivery/pbxt/JvTNNPkuMNTMjetsF4LO9eKdXAPy9xkNqUcphkbFcA2WF2TH/image_inpainting.png" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicateβs HTTP API reference docs.
Output
{ "completed_at": "2023-11-26T12:34:13.515278Z", "created_at": "2023-11-26T12:34:06.417418Z", "data_removed": false, "error": null, "id": "omjan3tba7hgbgwfwrfeo6chrm", "input": { "mask": "https://replicate.delivery/pbxt/JvTNNI5GXp1iol2Sjf3XYfUX83Bemhx4Q5TwoAOeZJXrvc8m/image_inpainting_mask.png", "image": "https://replicate.delivery/pbxt/JvTNNPkuMNTMjetsF4LO9eKdXAPy9xkNqUcphkbFcA2WF2TH/image_inpainting.png" }, "logs": "Original image too large for refinement! Resizing (999, 1499) to (774, 1162)...\n 0%| | 0/15 [00:00<?, ?it/s]\n 0%| | 0/15 [00:00<?, ?it/s]\nRefining scale 2 using scale 1 ...current loss: 0.1006: 0%| | 0/15 [00:00<?, ?it/s]\nRefining scale 2 using scale 1 ...current loss: 0.1006: 7%|β | 1/15 [00:00<00:03, 3.54it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0888: 7%|β | 1/15 [00:00<00:03, 3.54it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0888: 13%|ββ | 2/15 [00:00<00:03, 3.30it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0810: 13%|ββ | 2/15 [00:00<00:03, 3.30it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0810: 20%|ββ | 3/15 [00:00<00:03, 3.23it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0761: 20%|ββ | 3/15 [00:01<00:03, 3.23it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0761: 27%|βββ | 4/15 [00:01<00:03, 3.20it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0722: 27%|βββ | 4/15 [00:01<00:03, 3.20it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0722: 33%|ββββ | 5/15 [00:01<00:03, 3.18it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0692: 33%|ββββ | 5/15 [00:01<00:03, 3.18it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0692: 40%|ββββ | 6/15 [00:01<00:02, 3.17it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0663: 40%|ββββ | 6/15 [00:02<00:02, 3.17it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0663: 47%|βββββ | 7/15 [00:02<00:02, 3.16it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0640: 47%|βββββ | 7/15 [00:02<00:02, 3.16it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0640: 53%|ββββββ | 8/15 [00:02<00:02, 3.16it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0618: 53%|ββββββ | 8/15 [00:02<00:02, 3.16it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0618: 60%|ββββββ | 9/15 [00:02<00:01, 3.15it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0600: 60%|ββββββ | 9/15 [00:02<00:01, 3.15it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0600: 67%|βββββββ | 10/15 [00:03<00:01, 3.15it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0582: 67%|βββββββ | 10/15 [00:03<00:01, 3.15it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0582: 73%|ββββββββ | 11/15 [00:03<00:01, 3.15it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0567: 73%|ββββββββ | 11/15 [00:03<00:01, 3.15it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0567: 80%|ββββββββ | 12/15 [00:03<00:00, 3.15it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0553: 80%|ββββββββ | 12/15 [00:03<00:00, 3.15it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0553: 87%|βββββββββ | 13/15 [00:04<00:00, 3.15it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0540: 87%|βββββββββ | 13/15 [00:04<00:00, 3.15it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0540: 93%|ββββββββββ| 14/15 [00:04<00:00, 3.15it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0528: 93%|ββββββββββ| 14/15 [00:04<00:00, 3.15it/s]\nRefining scale 2 using scale 1 ...current loss: 0.0528: 100%|ββββββββββ| 15/15 [00:04<00:00, 3.69it/s]", "metrics": { "predict_time": 7.05847, "total_time": 7.09786 }, "output": "https://replicate.delivery/pbxt/CLgjCk74JrLXHJetAIvS6kFi6d5K4fpLl17lzK48y3BE1O8RA/output.png", "started_at": "2023-11-26T12:34:06.456808Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/omjan3tba7hgbgwfwrfeo6chrm", "cancel": "https://api.replicate.com/v1/predictions/omjan3tba7hgbgwfwrfeo6chrm/cancel" }, "version": "c5537e510ca1323c525a61ce462a32a4c5e9bdbb0d75a577fa07f06aa0b969e8" }Generated inOriginal image too large for refinement! Resizing (999, 1499) to (774, 1162)... 0%| | 0/15 [00:00<?, ?it/s] 0%| | 0/15 [00:00<?, ?it/s] Refining scale 2 using scale 1 ...current loss: 0.1006: 0%| | 0/15 [00:00<?, ?it/s] Refining scale 2 using scale 1 ...current loss: 0.1006: 7%|β | 1/15 [00:00<00:03, 3.54it/s] Refining scale 2 using scale 1 ...current loss: 0.0888: 7%|β | 1/15 [00:00<00:03, 3.54it/s] Refining scale 2 using scale 1 ...current loss: 0.0888: 13%|ββ | 2/15 [00:00<00:03, 3.30it/s] Refining scale 2 using scale 1 ...current loss: 0.0810: 13%|ββ | 2/15 [00:00<00:03, 3.30it/s] Refining scale 2 using scale 1 ...current loss: 0.0810: 20%|ββ | 3/15 [00:00<00:03, 3.23it/s] Refining scale 2 using scale 1 ...current loss: 0.0761: 20%|ββ | 3/15 [00:01<00:03, 3.23it/s] Refining scale 2 using scale 1 ...current loss: 0.0761: 27%|βββ | 4/15 [00:01<00:03, 3.20it/s] Refining scale 2 using scale 1 ...current loss: 0.0722: 27%|βββ | 4/15 [00:01<00:03, 3.20it/s] Refining scale 2 using scale 1 ...current loss: 0.0722: 33%|ββββ | 5/15 [00:01<00:03, 3.18it/s] Refining scale 2 using scale 1 ...current loss: 0.0692: 33%|ββββ | 5/15 [00:01<00:03, 3.18it/s] Refining scale 2 using scale 1 ...current loss: 0.0692: 40%|ββββ | 6/15 [00:01<00:02, 3.17it/s] Refining scale 2 using scale 1 ...current loss: 0.0663: 40%|ββββ | 6/15 [00:02<00:02, 3.17it/s] Refining scale 2 using scale 1 ...current loss: 0.0663: 47%|βββββ | 7/15 [00:02<00:02, 3.16it/s] Refining scale 2 using scale 1 ...current loss: 0.0640: 47%|βββββ | 7/15 [00:02<00:02, 3.16it/s] Refining scale 2 using scale 1 ...current loss: 0.0640: 53%|ββββββ | 8/15 [00:02<00:02, 3.16it/s] Refining scale 2 using scale 1 ...current loss: 0.0618: 53%|ββββββ | 8/15 [00:02<00:02, 3.16it/s] Refining scale 2 using scale 1 ...current loss: 0.0618: 60%|ββββββ | 9/15 [00:02<00:01, 3.15it/s] Refining scale 2 using scale 1 ...current loss: 0.0600: 60%|ββββββ | 9/15 [00:02<00:01, 3.15it/s] Refining scale 2 using scale 1 ...current loss: 0.0600: 67%|βββββββ | 10/15 [00:03<00:01, 3.15it/s] Refining scale 2 using scale 1 ...current loss: 0.0582: 67%|βββββββ | 10/15 [00:03<00:01, 3.15it/s] Refining scale 2 using scale 1 ...current loss: 0.0582: 73%|ββββββββ | 11/15 [00:03<00:01, 3.15it/s] Refining scale 2 using scale 1 ...current loss: 0.0567: 73%|ββββββββ | 11/15 [00:03<00:01, 3.15it/s] Refining scale 2 using scale 1 ...current loss: 0.0567: 80%|ββββββββ | 12/15 [00:03<00:00, 3.15it/s] Refining scale 2 using scale 1 ...current loss: 0.0553: 80%|ββββββββ | 12/15 [00:03<00:00, 3.15it/s] Refining scale 2 using scale 1 ...current loss: 0.0553: 87%|βββββββββ | 13/15 [00:04<00:00, 3.15it/s] Refining scale 2 using scale 1 ...current loss: 0.0540: 87%|βββββββββ | 13/15 [00:04<00:00, 3.15it/s] Refining scale 2 using scale 1 ...current loss: 0.0540: 93%|ββββββββββ| 14/15 [00:04<00:00, 3.15it/s] Refining scale 2 using scale 1 ...current loss: 0.0528: 93%|ββββββββββ| 14/15 [00:04<00:00, 3.15it/s] Refining scale 2 using scale 1 ...current loss: 0.0528: 100%|ββββββββββ| 15/15 [00:04<00:00, 3.69it/s]
Want to make some of these yourself?
Run this model
