fofr / sdxl-tron
A fine-tuned SDXL lora based on Tron Legacy
- Public
- 13K runs
-
L40S
Prediction
fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2dIDtfsjyxdbhyfvf52lu5cjasossuStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedby @fofrInput
- width
- 1360
- height
- 768
- prompt
- In the style of TOK, a photo of an epic overgrown garden on a spaceship
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 4
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- ugly
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1360, "height": 768, "prompt": "In the style of TOK, a photo of an epic overgrown garden on a spaceship", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "ugly", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run fofr/sdxl-tron using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", { input: { width: 1360, height: 768, prompt: "In the style of TOK, a photo of an epic overgrown garden on a spaceship", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 4, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.8, negative_prompt: "ugly", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun fofr/sdxl-tron using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", input={ "width": 1360, "height": 768, "prompt": "In the style of TOK, a photo of an epic overgrown garden on a spaceship", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.8, "negative_prompt": "ugly", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run fofr/sdxl-tron 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": "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", "input": { "width": 1360, "height": 768, "prompt": "In the style of TOK, a photo of an epic overgrown garden on a spaceship", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "ugly", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-08-08T10:54:30.857700Z", "created_at": "2023-08-08T10:53:35.882403Z", "data_removed": false, "error": null, "id": "tfsjyxdbhyfvf52lu5cjasossu", "input": { "width": 1360, "height": 768, "prompt": "In the style of TOK, a photo of an epic overgrown garden on a spaceship", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "ugly", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 51900\nPrompt: In the style of <s0><s1>, a photo of an epic overgrown garden on a spaceship\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:01<00:49, 1.00s/it]\n 4%|▍ | 2/50 [00:02<00:48, 1.01s/it]\n 6%|▌ | 3/50 [00:03<00:47, 1.01s/it]\n 8%|▊ | 4/50 [00:04<00:46, 1.01s/it]\n 10%|█ | 5/50 [00:05<00:45, 1.01s/it]\n 12%|█▏ | 6/50 [00:06<00:44, 1.01s/it]\n 14%|█▍ | 7/50 [00:07<00:43, 1.01s/it]\n 16%|█▌ | 8/50 [00:08<00:42, 1.01s/it]\n 18%|█▊ | 9/50 [00:09<00:41, 1.01s/it]\n 20%|██ | 10/50 [00:10<00:40, 1.01s/it]\n 22%|██▏ | 11/50 [00:11<00:39, 1.01s/it]\n 24%|██▍ | 12/50 [00:12<00:38, 1.01s/it]\n 26%|██▌ | 13/50 [00:13<00:37, 1.01s/it]\n 28%|██▊ | 14/50 [00:14<00:36, 1.01s/it]\n 30%|███ | 15/50 [00:15<00:35, 1.01s/it]\n 32%|███▏ | 16/50 [00:16<00:34, 1.01s/it]\n 34%|███▍ | 17/50 [00:17<00:33, 1.01s/it]\n 36%|███▌ | 18/50 [00:18<00:32, 1.01s/it]\n 38%|███▊ | 19/50 [00:19<00:31, 1.01s/it]\n 40%|████ | 20/50 [00:20<00:30, 1.01s/it]\n 42%|████▏ | 21/50 [00:21<00:29, 1.01s/it]\n 44%|████▍ | 22/50 [00:22<00:28, 1.01s/it]\n 46%|████▌ | 23/50 [00:23<00:27, 1.01s/it]\n 48%|████▊ | 24/50 [00:24<00:26, 1.01s/it]\n 50%|█████ | 25/50 [00:25<00:25, 1.01s/it]\n 52%|█████▏ | 26/50 [00:26<00:24, 1.01s/it]\n 54%|█████▍ | 27/50 [00:27<00:23, 1.01s/it]\n 56%|█████▌ | 28/50 [00:28<00:22, 1.01s/it]\n 58%|█████▊ | 29/50 [00:29<00:21, 1.01s/it]\n 60%|██████ | 30/50 [00:30<00:20, 1.01s/it]\n 62%|██████▏ | 31/50 [00:31<00:19, 1.01s/it]\n 64%|██████▍ | 32/50 [00:32<00:18, 1.01s/it]\n 66%|██████▌ | 33/50 [00:33<00:17, 1.01s/it]\n 68%|██████▊ | 34/50 [00:34<00:16, 1.01s/it]\n 70%|███████ | 35/50 [00:35<00:15, 1.02s/it]\n 72%|███████▏ | 36/50 [00:36<00:14, 1.01s/it]\n 74%|███████▍ | 37/50 [00:37<00:13, 1.02s/it]\n 76%|███████▌ | 38/50 [00:38<00:12, 1.02s/it]\n 78%|███████▊ | 39/50 [00:39<00:11, 1.02s/it]\n 80%|████████ | 40/50 [00:40<00:10, 1.02s/it]\n 82%|████████▏ | 41/50 [00:41<00:09, 1.02s/it]\n 84%|████████▍ | 42/50 [00:42<00:08, 1.02s/it]\n 86%|████████▌ | 43/50 [00:43<00:07, 1.02s/it]\n 88%|████████▊ | 44/50 [00:44<00:06, 1.02s/it]\n 90%|█████████ | 45/50 [00:45<00:05, 1.02s/it]\n 92%|█████████▏| 46/50 [00:46<00:04, 1.02s/it]\n 94%|█████████▍| 47/50 [00:47<00:03, 1.02s/it]\n 96%|█████████▌| 48/50 [00:48<00:02, 1.02s/it]\n 98%|█████████▊| 49/50 [00:49<00:01, 1.02s/it]\n100%|██████████| 50/50 [00:50<00:00, 1.02s/it]\n100%|██████████| 50/50 [00:50<00:00, 1.01s/it]", "metrics": { "predict_time": 55.003861, "total_time": 54.975297 }, "output": [ "https://replicate.delivery/pbxt/DGWqCUY2SzLcL9ToAe2OOwLLzZgf2aYRiKWElMoei5kKH6viA/out-0.png", "https://replicate.delivery/pbxt/n0RtbmmUOsaXMFvtWzOrB5ubra56z5uB62GLudogGelyheXRA/out-1.png", "https://replicate.delivery/pbxt/f6A3XOu7LYUpBC37CPf3Y9ZdAkYsHNStD163pGS3fuFMH6viA/out-2.png", "https://replicate.delivery/pbxt/7Hq2eelnOeEP9I4eTOmbpNT0cu19HAgXVOu3W5mCQUkYO0fKC/out-3.png" ], "started_at": "2023-08-08T10:53:35.853839Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/tfsjyxdbhyfvf52lu5cjasossu", "cancel": "https://api.replicate.com/v1/predictions/tfsjyxdbhyfvf52lu5cjasossu/cancel" }, "version": "fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d" }Generated inUsing seed: 51900 Prompt: In the style of <s0><s1>, a photo of an epic overgrown garden on a spaceship txt2img mode 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<00:49, 1.00s/it] 4%|▍ | 2/50 [00:02<00:48, 1.01s/it] 6%|▌ | 3/50 [00:03<00:47, 1.01s/it] 8%|▊ | 4/50 [00:04<00:46, 1.01s/it] 10%|█ | 5/50 [00:05<00:45, 1.01s/it] 12%|█▏ | 6/50 [00:06<00:44, 1.01s/it] 14%|█▍ | 7/50 [00:07<00:43, 1.01s/it] 16%|█▌ | 8/50 [00:08<00:42, 1.01s/it] 18%|█▊ | 9/50 [00:09<00:41, 1.01s/it] 20%|██ | 10/50 [00:10<00:40, 1.01s/it] 22%|██▏ | 11/50 [00:11<00:39, 1.01s/it] 24%|██▍ | 12/50 [00:12<00:38, 1.01s/it] 26%|██▌ | 13/50 [00:13<00:37, 1.01s/it] 28%|██▊ | 14/50 [00:14<00:36, 1.01s/it] 30%|███ | 15/50 [00:15<00:35, 1.01s/it] 32%|███▏ | 16/50 [00:16<00:34, 1.01s/it] 34%|███▍ | 17/50 [00:17<00:33, 1.01s/it] 36%|███▌ | 18/50 [00:18<00:32, 1.01s/it] 38%|███▊ | 19/50 [00:19<00:31, 1.01s/it] 40%|████ | 20/50 [00:20<00:30, 1.01s/it] 42%|████▏ | 21/50 [00:21<00:29, 1.01s/it] 44%|████▍ | 22/50 [00:22<00:28, 1.01s/it] 46%|████▌ | 23/50 [00:23<00:27, 1.01s/it] 48%|████▊ | 24/50 [00:24<00:26, 1.01s/it] 50%|█████ | 25/50 [00:25<00:25, 1.01s/it] 52%|█████▏ | 26/50 [00:26<00:24, 1.01s/it] 54%|█████▍ | 27/50 [00:27<00:23, 1.01s/it] 56%|█████▌ | 28/50 [00:28<00:22, 1.01s/it] 58%|█████▊ | 29/50 [00:29<00:21, 1.01s/it] 60%|██████ | 30/50 [00:30<00:20, 1.01s/it] 62%|██████▏ | 31/50 [00:31<00:19, 1.01s/it] 64%|██████▍ | 32/50 [00:32<00:18, 1.01s/it] 66%|██████▌ | 33/50 [00:33<00:17, 1.01s/it] 68%|██████▊ | 34/50 [00:34<00:16, 1.01s/it] 70%|███████ | 35/50 [00:35<00:15, 1.02s/it] 72%|███████▏ | 36/50 [00:36<00:14, 1.01s/it] 74%|███████▍ | 37/50 [00:37<00:13, 1.02s/it] 76%|███████▌ | 38/50 [00:38<00:12, 1.02s/it] 78%|███████▊ | 39/50 [00:39<00:11, 1.02s/it] 80%|████████ | 40/50 [00:40<00:10, 1.02s/it] 82%|████████▏ | 41/50 [00:41<00:09, 1.02s/it] 84%|████████▍ | 42/50 [00:42<00:08, 1.02s/it] 86%|████████▌ | 43/50 [00:43<00:07, 1.02s/it] 88%|████████▊ | 44/50 [00:44<00:06, 1.02s/it] 90%|█████████ | 45/50 [00:45<00:05, 1.02s/it] 92%|█████████▏| 46/50 [00:46<00:04, 1.02s/it] 94%|█████████▍| 47/50 [00:47<00:03, 1.02s/it] 96%|█████████▌| 48/50 [00:48<00:02, 1.02s/it] 98%|█████████▊| 49/50 [00:49<00:01, 1.02s/it] 100%|██████████| 50/50 [00:50<00:00, 1.02s/it] 100%|██████████| 50/50 [00:50<00:00, 1.01s/it]Prediction
fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2dIDvxrk7u3bxsajq3nxf3lwltulpqStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 832
- height
- 1248
- prompt
- A close-up portrait photo of a person's face in the style of TOK, in an epic overgrown garden on a spaceship
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 4
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- full body, ugly, disfigured, distorted
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 832, "height": 1248, "prompt": "A close-up portrait photo of a person's face in the style of TOK, in an epic overgrown garden on a spaceship", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "full body, ugly, disfigured, distorted", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run fofr/sdxl-tron using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", { input: { width: 832, height: 1248, prompt: "A close-up portrait photo of a person's face in the style of TOK, in an epic overgrown garden on a spaceship", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 4, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.8, negative_prompt: "full body, ugly, disfigured, distorted", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun fofr/sdxl-tron using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", input={ "width": 832, "height": 1248, "prompt": "A close-up portrait photo of a person's face in the style of TOK, in an epic overgrown garden on a spaceship", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.8, "negative_prompt": "full body, ugly, disfigured, distorted", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run fofr/sdxl-tron 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": "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", "input": { "width": 832, "height": 1248, "prompt": "A close-up portrait photo of a person\'s face in the style of TOK, in an epic overgrown garden on a spaceship", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "full body, ugly, disfigured, distorted", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-08-08T11:05:55.649427Z", "created_at": "2023-08-08T11:05:00.438197Z", "data_removed": false, "error": null, "id": "vxrk7u3bxsajq3nxf3lwltulpq", "input": { "width": 832, "height": 1248, "prompt": "A close-up portrait photo of a person's face in the style of TOK, in an epic overgrown garden on a spaceship", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "full body, ugly, disfigured, distorted", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 59516\nPrompt: A close-up portrait photo of a person's face in the style of <s0><s1>, in an epic overgrown garden on a spaceship\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:01<00:49, 1.01s/it]\n 4%|▍ | 2/50 [00:02<00:48, 1.01s/it]\n 6%|▌ | 3/50 [00:03<00:47, 1.01s/it]\n 8%|▊ | 4/50 [00:04<00:46, 1.01s/it]\n 10%|█ | 5/50 [00:05<00:45, 1.01s/it]\n 12%|█▏ | 6/50 [00:06<00:44, 1.01s/it]\n 14%|█▍ | 7/50 [00:07<00:43, 1.01s/it]\n 16%|█▌ | 8/50 [00:08<00:42, 1.01s/it]\n 18%|█▊ | 9/50 [00:09<00:41, 1.01s/it]\n 20%|██ | 10/50 [00:10<00:40, 1.01s/it]\n 22%|██▏ | 11/50 [00:11<00:39, 1.01s/it]\n 24%|██▍ | 12/50 [00:12<00:38, 1.01s/it]\n 26%|██▌ | 13/50 [00:13<00:37, 1.01s/it]\n 28%|██▊ | 14/50 [00:14<00:36, 1.01s/it]\n 30%|███ | 15/50 [00:15<00:35, 1.01s/it]\n 32%|███▏ | 16/50 [00:16<00:34, 1.01s/it]\n 34%|███▍ | 17/50 [00:17<00:33, 1.01s/it]\n 36%|███▌ | 18/50 [00:18<00:32, 1.01s/it]\n 38%|███▊ | 19/50 [00:19<00:31, 1.01s/it]\n 40%|████ | 20/50 [00:20<00:30, 1.01s/it]\n 42%|████▏ | 21/50 [00:21<00:29, 1.01s/it]\n 44%|████▍ | 22/50 [00:22<00:28, 1.01s/it]\n 46%|████▌ | 23/50 [00:23<00:27, 1.01s/it]\n 48%|████▊ | 24/50 [00:24<00:26, 1.01s/it]\n 50%|█████ | 25/50 [00:25<00:25, 1.01s/it]\n 52%|█████▏ | 26/50 [00:26<00:24, 1.01s/it]\n 54%|█████▍ | 27/50 [00:27<00:23, 1.01s/it]\n 56%|█████▌ | 28/50 [00:28<00:22, 1.01s/it]\n 58%|█████▊ | 29/50 [00:29<00:21, 1.01s/it]\n 60%|██████ | 30/50 [00:30<00:20, 1.02s/it]\n 62%|██████▏ | 31/50 [00:31<00:19, 1.02s/it]\n 64%|██████▍ | 32/50 [00:32<00:18, 1.02s/it]\n 66%|██████▌ | 33/50 [00:33<00:17, 1.02s/it]\n 68%|██████▊ | 34/50 [00:34<00:16, 1.02s/it]\n 70%|███████ | 35/50 [00:35<00:15, 1.02s/it]\n 72%|███████▏ | 36/50 [00:36<00:14, 1.02s/it]\n 74%|███████▍ | 37/50 [00:37<00:13, 1.02s/it]\n 76%|███████▌ | 38/50 [00:38<00:12, 1.02s/it]\n 78%|███████▊ | 39/50 [00:39<00:11, 1.02s/it]\n 80%|████████ | 40/50 [00:40<00:10, 1.02s/it]\n 82%|████████▏ | 41/50 [00:41<00:09, 1.02s/it]\n 84%|████████▍ | 42/50 [00:42<00:08, 1.02s/it]\n 86%|████████▌ | 43/50 [00:43<00:07, 1.02s/it]\n 88%|████████▊ | 44/50 [00:44<00:06, 1.02s/it]\n 90%|█████████ | 45/50 [00:45<00:05, 1.02s/it]\n 92%|█████████▏| 46/50 [00:46<00:04, 1.02s/it]\n 94%|█████████▍| 47/50 [00:47<00:03, 1.02s/it]\n 96%|█████████▌| 48/50 [00:48<00:02, 1.02s/it]\n 98%|█████████▊| 49/50 [00:49<00:01, 1.02s/it]\n100%|██████████| 50/50 [00:50<00:00, 1.02s/it]\n100%|██████████| 50/50 [00:50<00:00, 1.01s/it]", "metrics": { "predict_time": 55.271947, "total_time": 55.21123 }, "output": [ "https://replicate.delivery/pbxt/KLeULpQjL3TGfky33m8cg2gr2VTwZhVp9pknl2PesBPlc6viA/out-0.png", "https://replicate.delivery/pbxt/uJvhbMY4ZlIHCdGgK3iyzwEtxdL9dCX57EzTffQ1MoaSO9XRA/out-1.png", "https://replicate.delivery/pbxt/2DGCU5ZcvzptHFpWbo2pmzUESZKk1QOpydpclfs9KthJneXRA/out-2.png", "https://replicate.delivery/pbxt/ZbEex0Lwbb1UMSmIgghoQ2Uf0BreCgZsQefJBJBKTw2cypfVE/out-3.png" ], "started_at": "2023-08-08T11:05:00.377480Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/vxrk7u3bxsajq3nxf3lwltulpq", "cancel": "https://api.replicate.com/v1/predictions/vxrk7u3bxsajq3nxf3lwltulpq/cancel" }, "version": "fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d" }Generated inUsing seed: 59516 Prompt: A close-up portrait photo of a person's face in the style of <s0><s1>, in an epic overgrown garden on a spaceship txt2img mode 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<00:49, 1.01s/it] 4%|▍ | 2/50 [00:02<00:48, 1.01s/it] 6%|▌ | 3/50 [00:03<00:47, 1.01s/it] 8%|▊ | 4/50 [00:04<00:46, 1.01s/it] 10%|█ | 5/50 [00:05<00:45, 1.01s/it] 12%|█▏ | 6/50 [00:06<00:44, 1.01s/it] 14%|█▍ | 7/50 [00:07<00:43, 1.01s/it] 16%|█▌ | 8/50 [00:08<00:42, 1.01s/it] 18%|█▊ | 9/50 [00:09<00:41, 1.01s/it] 20%|██ | 10/50 [00:10<00:40, 1.01s/it] 22%|██▏ | 11/50 [00:11<00:39, 1.01s/it] 24%|██▍ | 12/50 [00:12<00:38, 1.01s/it] 26%|██▌ | 13/50 [00:13<00:37, 1.01s/it] 28%|██▊ | 14/50 [00:14<00:36, 1.01s/it] 30%|███ | 15/50 [00:15<00:35, 1.01s/it] 32%|███▏ | 16/50 [00:16<00:34, 1.01s/it] 34%|███▍ | 17/50 [00:17<00:33, 1.01s/it] 36%|███▌ | 18/50 [00:18<00:32, 1.01s/it] 38%|███▊ | 19/50 [00:19<00:31, 1.01s/it] 40%|████ | 20/50 [00:20<00:30, 1.01s/it] 42%|████▏ | 21/50 [00:21<00:29, 1.01s/it] 44%|████▍ | 22/50 [00:22<00:28, 1.01s/it] 46%|████▌ | 23/50 [00:23<00:27, 1.01s/it] 48%|████▊ | 24/50 [00:24<00:26, 1.01s/it] 50%|█████ | 25/50 [00:25<00:25, 1.01s/it] 52%|█████▏ | 26/50 [00:26<00:24, 1.01s/it] 54%|█████▍ | 27/50 [00:27<00:23, 1.01s/it] 56%|█████▌ | 28/50 [00:28<00:22, 1.01s/it] 58%|█████▊ | 29/50 [00:29<00:21, 1.01s/it] 60%|██████ | 30/50 [00:30<00:20, 1.02s/it] 62%|██████▏ | 31/50 [00:31<00:19, 1.02s/it] 64%|██████▍ | 32/50 [00:32<00:18, 1.02s/it] 66%|██████▌ | 33/50 [00:33<00:17, 1.02s/it] 68%|██████▊ | 34/50 [00:34<00:16, 1.02s/it] 70%|███████ | 35/50 [00:35<00:15, 1.02s/it] 72%|███████▏ | 36/50 [00:36<00:14, 1.02s/it] 74%|███████▍ | 37/50 [00:37<00:13, 1.02s/it] 76%|███████▌ | 38/50 [00:38<00:12, 1.02s/it] 78%|███████▊ | 39/50 [00:39<00:11, 1.02s/it] 80%|████████ | 40/50 [00:40<00:10, 1.02s/it] 82%|████████▏ | 41/50 [00:41<00:09, 1.02s/it] 84%|████████▍ | 42/50 [00:42<00:08, 1.02s/it] 86%|████████▌ | 43/50 [00:43<00:07, 1.02s/it] 88%|████████▊ | 44/50 [00:44<00:06, 1.02s/it] 90%|█████████ | 45/50 [00:45<00:05, 1.02s/it] 92%|█████████▏| 46/50 [00:46<00:04, 1.02s/it] 94%|█████████▍| 47/50 [00:47<00:03, 1.02s/it] 96%|█████████▌| 48/50 [00:48<00:02, 1.02s/it] 98%|█████████▊| 49/50 [00:49<00:01, 1.02s/it] 100%|██████████| 50/50 [00:50<00:00, 1.02s/it] 100%|██████████| 50/50 [00:50<00:00, 1.01s/it]Prediction
fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2dIDwk5kretbmuvpdxeka6zis56roeStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1360
- height
- 768
- prompt
- A baroque painting of an epic battle on the sea, in the style of TOK, renaissance, neon
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.95
- num_outputs
- 4
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.95
- negative_prompt
- cluttered, ugly, render, photo
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1360, "height": 768, "prompt": "A baroque painting of an epic battle on the sea, in the style of TOK, renaissance, neon", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.95, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "cluttered, ugly, render, photo", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run fofr/sdxl-tron using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", { input: { width: 1360, height: 768, prompt: "A baroque painting of an epic battle on the sea, in the style of TOK, renaissance, neon", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.95, num_outputs: 4, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.95, negative_prompt: "cluttered, ugly, render, photo", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun fofr/sdxl-tron using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", input={ "width": 1360, "height": 768, "prompt": "A baroque painting of an epic battle on the sea, in the style of TOK, renaissance, neon", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.95, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.95, "negative_prompt": "cluttered, ugly, render, photo", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run fofr/sdxl-tron 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": "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", "input": { "width": 1360, "height": 768, "prompt": "A baroque painting of an epic battle on the sea, in the style of TOK, renaissance, neon", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.95, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "cluttered, ugly, render, photo", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-08-08T11:29:23.276327Z", "created_at": "2023-08-08T11:28:28.815637Z", "data_removed": false, "error": null, "id": "wk5kretbmuvpdxeka6zis56roe", "input": { "width": 1360, "height": 768, "prompt": "A baroque painting of an epic battle on the sea, in the style of TOK, renaissance, neon", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.95, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "cluttered, ugly, render, photo", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 44752\nPrompt: A baroque painting of an epic battle on the sea, in the style of <s0><s1>, renaissance, neon\ntxt2img mode\n 0%| | 0/47 [00:00<?, ?it/s]\n 2%|▏ | 1/47 [00:01<00:46, 1.00s/it]\n 4%|▍ | 2/47 [00:02<00:45, 1.00s/it]\n 6%|▋ | 3/47 [00:03<00:44, 1.00s/it]\n 9%|▊ | 4/47 [00:04<00:43, 1.01s/it]\n 11%|█ | 5/47 [00:05<00:42, 1.01s/it]\n 13%|█▎ | 6/47 [00:06<00:41, 1.01s/it]\n 15%|█▍ | 7/47 [00:07<00:40, 1.01s/it]\n 17%|█▋ | 8/47 [00:08<00:39, 1.01s/it]\n 19%|█▉ | 9/47 [00:09<00:38, 1.01s/it]\n 21%|██▏ | 10/47 [00:10<00:37, 1.01s/it]\n 23%|██▎ | 11/47 [00:11<00:36, 1.01s/it]\n 26%|██▌ | 12/47 [00:12<00:35, 1.01s/it]\n 28%|██▊ | 13/47 [00:13<00:34, 1.01s/it]\n 30%|██▉ | 14/47 [00:14<00:33, 1.01s/it]\n 32%|███▏ | 15/47 [00:15<00:32, 1.01s/it]\n 34%|███▍ | 16/47 [00:16<00:31, 1.01s/it]\n 36%|███▌ | 17/47 [00:17<00:30, 1.01s/it]\n 38%|███▊ | 18/47 [00:18<00:29, 1.01s/it]\n 40%|████ | 19/47 [00:19<00:28, 1.01s/it]\n 43%|████▎ | 20/47 [00:20<00:27, 1.01s/it]\n 45%|████▍ | 21/47 [00:21<00:26, 1.01s/it]\n 47%|████▋ | 22/47 [00:22<00:25, 1.01s/it]\n 49%|████▉ | 23/47 [00:23<00:24, 1.01s/it]\n 51%|█████ | 24/47 [00:24<00:23, 1.01s/it]\n 53%|█████▎ | 25/47 [00:25<00:22, 1.01s/it]\n 55%|█████▌ | 26/47 [00:26<00:21, 1.01s/it]\n 57%|█████▋ | 27/47 [00:27<00:20, 1.01s/it]\n 60%|█████▉ | 28/47 [00:28<00:19, 1.01s/it]\n 62%|██████▏ | 29/47 [00:29<00:18, 1.01s/it]\n 64%|██████▍ | 30/47 [00:30<00:17, 1.01s/it]\n 66%|██████▌ | 31/47 [00:31<00:16, 1.01s/it]\n 68%|██████▊ | 32/47 [00:32<00:15, 1.01s/it]\n 70%|███████ | 33/47 [00:33<00:14, 1.01s/it]\n 72%|███████▏ | 34/47 [00:34<00:13, 1.01s/it]\n 74%|███████▍ | 35/47 [00:35<00:12, 1.01s/it]\n 77%|███████▋ | 36/47 [00:36<00:11, 1.01s/it]\n 79%|███████▊ | 37/47 [00:37<00:10, 1.01s/it]\n 81%|████████ | 38/47 [00:38<00:09, 1.01s/it]\n 83%|████████▎ | 39/47 [00:39<00:08, 1.01s/it]\n 85%|████████▌ | 40/47 [00:40<00:07, 1.01s/it]\n 87%|████████▋ | 41/47 [00:41<00:06, 1.01s/it]\n 89%|████████▉ | 42/47 [00:42<00:05, 1.01s/it]\n 91%|█████████▏| 43/47 [00:43<00:04, 1.01s/it]\n 94%|█████████▎| 44/47 [00:44<00:03, 1.01s/it]\n 96%|█████████▌| 45/47 [00:45<00:02, 1.01s/it]\n 98%|█████████▊| 46/47 [00:46<00:01, 1.01s/it]\n100%|██████████| 47/47 [00:47<00:00, 1.01s/it]\n100%|██████████| 47/47 [00:47<00:00, 1.01s/it]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:01, 1.22it/s]\n 67%|██████▋ | 2/3 [00:01<00:00, 1.22it/s]\n100%|██████████| 3/3 [00:02<00:00, 1.21it/s]\n100%|██████████| 3/3 [00:02<00:00, 1.21it/s]", "metrics": { "predict_time": 54.499441, "total_time": 54.46069 }, "output": [ "https://replicate.delivery/pbxt/0t7lXY7CDaq6EJGb9ewfT4ppzED7fsijeB2xc6quxTfIisfVE/out-0.png", "https://replicate.delivery/pbxt/069YqMnwyQ6gDtiGGbNsirffPvT7Z5hBTUBwfnKsW6rlI7viA/out-1.png", "https://replicate.delivery/pbxt/M0yEKC49On4NNxBo9OeH3Pa3BmteusGXK5ErNkpBNeokI7viA/out-2.png", "https://replicate.delivery/pbxt/XeGCshnT5W1gOSy8seRQzwP5y4yZy0IrqSVIB9nySCLTk9XRA/out-3.png" ], "started_at": "2023-08-08T11:28:28.776886Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/wk5kretbmuvpdxeka6zis56roe", "cancel": "https://api.replicate.com/v1/predictions/wk5kretbmuvpdxeka6zis56roe/cancel" }, "version": "fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d" }Generated inUsing seed: 44752 Prompt: A baroque painting of an epic battle on the sea, in the style of <s0><s1>, renaissance, neon txt2img mode 0%| | 0/47 [00:00<?, ?it/s] 2%|▏ | 1/47 [00:01<00:46, 1.00s/it] 4%|▍ | 2/47 [00:02<00:45, 1.00s/it] 6%|▋ | 3/47 [00:03<00:44, 1.00s/it] 9%|▊ | 4/47 [00:04<00:43, 1.01s/it] 11%|█ | 5/47 [00:05<00:42, 1.01s/it] 13%|█▎ | 6/47 [00:06<00:41, 1.01s/it] 15%|█▍ | 7/47 [00:07<00:40, 1.01s/it] 17%|█▋ | 8/47 [00:08<00:39, 1.01s/it] 19%|█▉ | 9/47 [00:09<00:38, 1.01s/it] 21%|██▏ | 10/47 [00:10<00:37, 1.01s/it] 23%|██▎ | 11/47 [00:11<00:36, 1.01s/it] 26%|██▌ | 12/47 [00:12<00:35, 1.01s/it] 28%|██▊ | 13/47 [00:13<00:34, 1.01s/it] 30%|██▉ | 14/47 [00:14<00:33, 1.01s/it] 32%|███▏ | 15/47 [00:15<00:32, 1.01s/it] 34%|███▍ | 16/47 [00:16<00:31, 1.01s/it] 36%|███▌ | 17/47 [00:17<00:30, 1.01s/it] 38%|███▊ | 18/47 [00:18<00:29, 1.01s/it] 40%|████ | 19/47 [00:19<00:28, 1.01s/it] 43%|████▎ | 20/47 [00:20<00:27, 1.01s/it] 45%|████▍ | 21/47 [00:21<00:26, 1.01s/it] 47%|████▋ | 22/47 [00:22<00:25, 1.01s/it] 49%|████▉ | 23/47 [00:23<00:24, 1.01s/it] 51%|█████ | 24/47 [00:24<00:23, 1.01s/it] 53%|█████▎ | 25/47 [00:25<00:22, 1.01s/it] 55%|█████▌ | 26/47 [00:26<00:21, 1.01s/it] 57%|█████▋ | 27/47 [00:27<00:20, 1.01s/it] 60%|█████▉ | 28/47 [00:28<00:19, 1.01s/it] 62%|██████▏ | 29/47 [00:29<00:18, 1.01s/it] 64%|██████▍ | 30/47 [00:30<00:17, 1.01s/it] 66%|██████▌ | 31/47 [00:31<00:16, 1.01s/it] 68%|██████▊ | 32/47 [00:32<00:15, 1.01s/it] 70%|███████ | 33/47 [00:33<00:14, 1.01s/it] 72%|███████▏ | 34/47 [00:34<00:13, 1.01s/it] 74%|███████▍ | 35/47 [00:35<00:12, 1.01s/it] 77%|███████▋ | 36/47 [00:36<00:11, 1.01s/it] 79%|███████▊ | 37/47 [00:37<00:10, 1.01s/it] 81%|████████ | 38/47 [00:38<00:09, 1.01s/it] 83%|████████▎ | 39/47 [00:39<00:08, 1.01s/it] 85%|████████▌ | 40/47 [00:40<00:07, 1.01s/it] 87%|████████▋ | 41/47 [00:41<00:06, 1.01s/it] 89%|████████▉ | 42/47 [00:42<00:05, 1.01s/it] 91%|█████████▏| 43/47 [00:43<00:04, 1.01s/it] 94%|█████████▎| 44/47 [00:44<00:03, 1.01s/it] 96%|█████████▌| 45/47 [00:45<00:02, 1.01s/it] 98%|█████████▊| 46/47 [00:46<00:01, 1.01s/it] 100%|██████████| 47/47 [00:47<00:00, 1.01s/it] 100%|██████████| 47/47 [00:47<00:00, 1.01s/it] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:01, 1.22it/s] 67%|██████▋ | 2/3 [00:01<00:00, 1.22it/s] 100%|██████████| 3/3 [00:02<00:00, 1.21it/s] 100%|██████████| 3/3 [00:02<00:00, 1.21it/s]Prediction
fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2dIDbcsu66tbbq25vy7uec5p4iqyciStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1360
- height
- 768
- prompt
- A pixar rendering of boat on the sea, in the style of TOK, neon
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.72
- num_outputs
- 4
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.95
- negative_prompt
- cluttered, ugly, photo
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1360, "height": 768, "prompt": "A pixar rendering of boat on the sea, in the style of TOK, neon", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.72, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "cluttered, ugly, photo", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run fofr/sdxl-tron using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", { input: { width: 1360, height: 768, prompt: "A pixar rendering of boat on the sea, in the style of TOK, neon", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.72, num_outputs: 4, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.95, negative_prompt: "cluttered, ugly, photo", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun fofr/sdxl-tron using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", input={ "width": 1360, "height": 768, "prompt": "A pixar rendering of boat on the sea, in the style of TOK, neon", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.72, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.95, "negative_prompt": "cluttered, ugly, photo", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run fofr/sdxl-tron 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": "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", "input": { "width": 1360, "height": 768, "prompt": "A pixar rendering of boat on the sea, in the style of TOK, neon", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.72, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "cluttered, ugly, photo", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-08-08T11:49:30.240238Z", "created_at": "2023-08-08T11:47:32.665180Z", "data_removed": false, "error": null, "id": "bcsu66tbbq25vy7uec5p4iqyci", "input": { "width": 1360, "height": 768, "prompt": "A pixar rendering of boat on the sea, in the style of TOK, neon", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.72, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "cluttered, ugly, photo", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 30457\nPrompt: A pixar rendering of boat on the sea, in the style of <s0><s1>, neon\ntxt2img mode\n 0%| | 0/47 [00:00<?, ?it/s]\n 2%|▏ | 1/47 [00:01<01:12, 1.57s/it]\n 4%|▍ | 2/47 [00:02<00:55, 1.24s/it]\n 6%|▋ | 3/47 [00:03<00:49, 1.13s/it]\n 9%|▊ | 4/47 [00:04<00:46, 1.08s/it]\n 11%|█ | 5/47 [00:05<00:44, 1.05s/it]\n 13%|█▎ | 6/47 [00:06<00:42, 1.04s/it]\n 15%|█▍ | 7/47 [00:07<00:41, 1.03s/it]\n 17%|█▋ | 8/47 [00:08<00:39, 1.02s/it]\n 19%|█▉ | 9/47 [00:09<00:38, 1.01s/it]\n 21%|██▏ | 10/47 [00:10<00:37, 1.01s/it]\n 23%|██▎ | 11/47 [00:11<00:36, 1.01s/it]\n 26%|██▌ | 12/47 [00:12<00:35, 1.01s/it]\n 28%|██▊ | 13/47 [00:13<00:34, 1.01s/it]\n 30%|██▉ | 14/47 [00:14<00:33, 1.01s/it]\n 32%|███▏ | 15/47 [00:15<00:32, 1.01s/it]\n 34%|███▍ | 16/47 [00:16<00:31, 1.01s/it]\n 36%|███▌ | 17/47 [00:17<00:30, 1.01s/it]\n 38%|███▊ | 18/47 [00:18<00:29, 1.01s/it]\n 40%|████ | 19/47 [00:19<00:28, 1.01s/it]\n 43%|████▎ | 20/47 [00:20<00:27, 1.01s/it]\n 45%|████▍ | 21/47 [00:21<00:26, 1.01s/it]\n 47%|████▋ | 22/47 [00:22<00:25, 1.01s/it]\n 49%|████▉ | 23/47 [00:23<00:24, 1.01s/it]\n 51%|█████ | 24/47 [00:24<00:23, 1.01s/it]\n 53%|█████▎ | 25/47 [00:25<00:22, 1.01s/it]\n 55%|█████▌ | 26/47 [00:26<00:21, 1.01s/it]\n 57%|█████▋ | 27/47 [00:27<00:20, 1.01s/it]\n 60%|█████▉ | 28/47 [00:28<00:19, 1.01s/it]\n 62%|██████▏ | 29/47 [00:29<00:18, 1.01s/it]\n 64%|██████▍ | 30/47 [00:30<00:17, 1.01s/it]\n 66%|██████▌ | 31/47 [00:31<00:16, 1.01s/it]\n 68%|██████▊ | 32/47 [00:32<00:15, 1.01s/it]\n 70%|███████ | 33/47 [00:33<00:14, 1.01s/it]\n 72%|███████▏ | 34/47 [00:34<00:13, 1.01s/it]\n 74%|███████▍ | 35/47 [00:35<00:12, 1.01s/it]\n 77%|███████▋ | 36/47 [00:36<00:11, 1.01s/it]\n 79%|███████▊ | 37/47 [00:37<00:10, 1.01s/it]\n 81%|████████ | 38/47 [00:38<00:09, 1.01s/it]\n 83%|████████▎ | 39/47 [00:39<00:08, 1.01s/it]\n 85%|████████▌ | 40/47 [00:40<00:07, 1.01s/it]\n 87%|████████▋ | 41/47 [00:41<00:06, 1.01s/it]\n 89%|████████▉ | 42/47 [00:42<00:05, 1.01s/it]\n 91%|█████████▏| 43/47 [00:43<00:04, 1.01s/it]\n 94%|█████████▎| 44/47 [00:45<00:03, 1.01s/it]\n 96%|█████████▌| 45/47 [00:46<00:02, 1.01s/it]\n 98%|█████████▊| 46/47 [00:47<00:01, 1.01s/it]\n100%|██████████| 47/47 [00:48<00:00, 1.01s/it]\n100%|██████████| 47/47 [00:48<00:00, 1.02s/it]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:01, 1.22it/s]\n 67%|██████▋ | 2/3 [00:01<00:00, 1.21it/s]\n100%|██████████| 3/3 [00:02<00:00, 1.21it/s]\n100%|██████████| 3/3 [00:02<00:00, 1.21it/s]", "metrics": { "predict_time": 56.499221, "total_time": 117.575058 }, "output": [ "https://replicate.delivery/pbxt/ifSfQpcoLFmkIkS7SxZisXQeIhPHGFf3PTcfyiyEgGRC5ufVE/out-0.png", "https://replicate.delivery/pbxt/f56A6VceDCmM6EvPf592WBGHjFA3ghCZU1Q6cNwGqhTSu7viA/out-1.png", "https://replicate.delivery/pbxt/kgfF6seyk3jB1ktQ7o1D9gM5UA65Wm83md7odArR4oUJ39XRA/out-2.png", "https://replicate.delivery/pbxt/4JozGAeqNWRxNK4UTJZSwniODl1BHsDF3ia3EJWW1Qhk7eXRA/out-3.png" ], "started_at": "2023-08-08T11:48:33.741017Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/bcsu66tbbq25vy7uec5p4iqyci", "cancel": "https://api.replicate.com/v1/predictions/bcsu66tbbq25vy7uec5p4iqyci/cancel" }, "version": "fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d" }Generated inUsing seed: 30457 Prompt: A pixar rendering of boat on the sea, in the style of <s0><s1>, neon txt2img mode 0%| | 0/47 [00:00<?, ?it/s] 2%|▏ | 1/47 [00:01<01:12, 1.57s/it] 4%|▍ | 2/47 [00:02<00:55, 1.24s/it] 6%|▋ | 3/47 [00:03<00:49, 1.13s/it] 9%|▊ | 4/47 [00:04<00:46, 1.08s/it] 11%|█ | 5/47 [00:05<00:44, 1.05s/it] 13%|█▎ | 6/47 [00:06<00:42, 1.04s/it] 15%|█▍ | 7/47 [00:07<00:41, 1.03s/it] 17%|█▋ | 8/47 [00:08<00:39, 1.02s/it] 19%|█▉ | 9/47 [00:09<00:38, 1.01s/it] 21%|██▏ | 10/47 [00:10<00:37, 1.01s/it] 23%|██▎ | 11/47 [00:11<00:36, 1.01s/it] 26%|██▌ | 12/47 [00:12<00:35, 1.01s/it] 28%|██▊ | 13/47 [00:13<00:34, 1.01s/it] 30%|██▉ | 14/47 [00:14<00:33, 1.01s/it] 32%|███▏ | 15/47 [00:15<00:32, 1.01s/it] 34%|███▍ | 16/47 [00:16<00:31, 1.01s/it] 36%|███▌ | 17/47 [00:17<00:30, 1.01s/it] 38%|███▊ | 18/47 [00:18<00:29, 1.01s/it] 40%|████ | 19/47 [00:19<00:28, 1.01s/it] 43%|████▎ | 20/47 [00:20<00:27, 1.01s/it] 45%|████▍ | 21/47 [00:21<00:26, 1.01s/it] 47%|████▋ | 22/47 [00:22<00:25, 1.01s/it] 49%|████▉ | 23/47 [00:23<00:24, 1.01s/it] 51%|█████ | 24/47 [00:24<00:23, 1.01s/it] 53%|█████▎ | 25/47 [00:25<00:22, 1.01s/it] 55%|█████▌ | 26/47 [00:26<00:21, 1.01s/it] 57%|█████▋ | 27/47 [00:27<00:20, 1.01s/it] 60%|█████▉ | 28/47 [00:28<00:19, 1.01s/it] 62%|██████▏ | 29/47 [00:29<00:18, 1.01s/it] 64%|██████▍ | 30/47 [00:30<00:17, 1.01s/it] 66%|██████▌ | 31/47 [00:31<00:16, 1.01s/it] 68%|██████▊ | 32/47 [00:32<00:15, 1.01s/it] 70%|███████ | 33/47 [00:33<00:14, 1.01s/it] 72%|███████▏ | 34/47 [00:34<00:13, 1.01s/it] 74%|███████▍ | 35/47 [00:35<00:12, 1.01s/it] 77%|███████▋ | 36/47 [00:36<00:11, 1.01s/it] 79%|███████▊ | 37/47 [00:37<00:10, 1.01s/it] 81%|████████ | 38/47 [00:38<00:09, 1.01s/it] 83%|████████▎ | 39/47 [00:39<00:08, 1.01s/it] 85%|████████▌ | 40/47 [00:40<00:07, 1.01s/it] 87%|████████▋ | 41/47 [00:41<00:06, 1.01s/it] 89%|████████▉ | 42/47 [00:42<00:05, 1.01s/it] 91%|█████████▏| 43/47 [00:43<00:04, 1.01s/it] 94%|█████████▎| 44/47 [00:45<00:03, 1.01s/it] 96%|█████████▌| 45/47 [00:46<00:02, 1.01s/it] 98%|█████████▊| 46/47 [00:47<00:01, 1.01s/it] 100%|██████████| 47/47 [00:48<00:00, 1.01s/it] 100%|██████████| 47/47 [00:48<00:00, 1.02s/it] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:01, 1.22it/s] 67%|██████▋ | 2/3 [00:01<00:00, 1.21it/s] 100%|██████████| 3/3 [00:02<00:00, 1.21it/s] 100%|██████████| 3/3 [00:02<00:00, 1.21it/s]Prediction
fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2dID5lr3fudbjqdoytkhhq3xu3q7viStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1248
- height
- 832
- prompt
- A painting of a monstera plant in the style of TOK, orange and cyan
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 1
- num_outputs
- 4
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- ugly, disfigured, distorted
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1248, "height": 832, "prompt": "A painting of a monstera plant in the style of TOK, orange and cyan", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 1, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "ugly, disfigured, distorted", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run fofr/sdxl-tron using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", { input: { width: 1248, height: 832, prompt: "A painting of a monstera plant in the style of TOK, orange and cyan", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 1, num_outputs: 4, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.8, negative_prompt: "ugly, disfigured, distorted", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun fofr/sdxl-tron using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", input={ "width": 1248, "height": 832, "prompt": "A painting of a monstera plant in the style of TOK, orange and cyan", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 1, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.8, "negative_prompt": "ugly, disfigured, distorted", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run fofr/sdxl-tron 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": "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", "input": { "width": 1248, "height": 832, "prompt": "A painting of a monstera plant in the style of TOK, orange and cyan", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 1, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "ugly, disfigured, distorted", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-08-08T11:29:02.639678Z", "created_at": "2023-08-08T11:28:06.437100Z", "data_removed": false, "error": null, "id": "5lr3fudbjqdoytkhhq3xu3q7vi", "input": { "width": 1248, "height": 832, "prompt": "A painting of a monstera plant in the style of TOK, orange and cyan", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 1, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "ugly, disfigured, distorted", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 16220\nPrompt: A painting of a monstera plant in the style of <s0><s1>, orange and cyan\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:01<00:49, 1.01s/it]\n 4%|▍ | 2/50 [00:02<00:48, 1.00s/it]\n 6%|▌ | 3/50 [00:03<00:47, 1.00s/it]\n 8%|▊ | 4/50 [00:04<00:46, 1.00s/it]\n 10%|█ | 5/50 [00:05<00:45, 1.00s/it]\n 12%|█▏ | 6/50 [00:06<00:44, 1.00s/it]\n 14%|█▍ | 7/50 [00:07<00:43, 1.00s/it]\n 16%|█▌ | 8/50 [00:08<00:42, 1.01s/it]\n 18%|█▊ | 9/50 [00:09<00:41, 1.01s/it]\n 20%|██ | 10/50 [00:10<00:40, 1.01s/it]\n 22%|██▏ | 11/50 [00:11<00:39, 1.01s/it]\n 24%|██▍ | 12/50 [00:12<00:38, 1.01s/it]\n 26%|██▌ | 13/50 [00:13<00:37, 1.01s/it]\n 28%|██▊ | 14/50 [00:14<00:36, 1.01s/it]\n 30%|███ | 15/50 [00:15<00:35, 1.01s/it]\n 32%|███▏ | 16/50 [00:16<00:34, 1.01s/it]\n 34%|███▍ | 17/50 [00:17<00:33, 1.01s/it]\n 36%|███▌ | 18/50 [00:18<00:32, 1.01s/it]\n 38%|███▊ | 19/50 [00:19<00:31, 1.01s/it]\n 40%|████ | 20/50 [00:20<00:30, 1.01s/it]\n 42%|████▏ | 21/50 [00:21<00:29, 1.01s/it]\n 44%|████▍ | 22/50 [00:22<00:28, 1.01s/it]\n 46%|████▌ | 23/50 [00:23<00:27, 1.01s/it]\n 48%|████▊ | 24/50 [00:24<00:26, 1.01s/it]\n 50%|█████ | 25/50 [00:25<00:25, 1.01s/it]\n 52%|█████▏ | 26/50 [00:26<00:24, 1.01s/it]\n 54%|█████▍ | 27/50 [00:27<00:23, 1.01s/it]\n 56%|█████▌ | 28/50 [00:28<00:22, 1.01s/it]\n 58%|█████▊ | 29/50 [00:29<00:21, 1.01s/it]\n 60%|██████ | 30/50 [00:30<00:20, 1.01s/it]\n 62%|██████▏ | 31/50 [00:31<00:19, 1.01s/it]\n 64%|██████▍ | 32/50 [00:32<00:18, 1.01s/it]\n 66%|██████▌ | 33/50 [00:33<00:17, 1.01s/it]\n 68%|██████▊ | 34/50 [00:34<00:16, 1.01s/it]\n 70%|███████ | 35/50 [00:35<00:15, 1.01s/it]\n 72%|███████▏ | 36/50 [00:36<00:14, 1.01s/it]\n 74%|███████▍ | 37/50 [00:37<00:13, 1.01s/it]\n 76%|███████▌ | 38/50 [00:38<00:12, 1.02s/it]\n 78%|███████▊ | 39/50 [00:39<00:11, 1.01s/it]\n 80%|████████ | 40/50 [00:40<00:10, 1.02s/it]\n 82%|████████▏ | 41/50 [00:41<00:09, 1.02s/it]\n 84%|████████▍ | 42/50 [00:42<00:08, 1.02s/it]\n 86%|████████▌ | 43/50 [00:43<00:07, 1.02s/it]\n 88%|████████▊ | 44/50 [00:44<00:06, 1.02s/it]\n 90%|█████████ | 45/50 [00:45<00:05, 1.02s/it]\n 92%|█████████▏| 46/50 [00:46<00:04, 1.02s/it]\n 94%|█████████▍| 47/50 [00:47<00:03, 1.02s/it]\n 96%|█████████▌| 48/50 [00:48<00:02, 1.02s/it]\n 98%|█████████▊| 49/50 [00:49<00:01, 1.02s/it]\n100%|██████████| 50/50 [00:50<00:00, 1.02s/it]\n100%|██████████| 50/50 [00:50<00:00, 1.01s/it]", "metrics": { "predict_time": 56.214655, "total_time": 56.202578 }, "output": [ "https://replicate.delivery/pbxt/gDMnIkCe4ASnN65v5n7RgVtpgpbDKIUxjcoFfypxdMT7j9XRA/out-0.png", "https://replicate.delivery/pbxt/2OL8KHlclQKyOFsrBrJlUuUot25uEKDmsX8DK3LwxSZfxeXRA/out-1.png", "https://replicate.delivery/pbxt/oN4JD7eA2z2ANiK6RUxNBM1VBOVjYspkpd9WOYFwes89j9XRA/out-2.png", "https://replicate.delivery/pbxt/FUOrKzaSiLL2GZOyJDk5xVUQHlMTqy6wzvbYCf1pwaCfj9XRA/out-3.png" ], "started_at": "2023-08-08T11:28:06.425023Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/5lr3fudbjqdoytkhhq3xu3q7vi", "cancel": "https://api.replicate.com/v1/predictions/5lr3fudbjqdoytkhhq3xu3q7vi/cancel" }, "version": "fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d" }Generated inUsing seed: 16220 Prompt: A painting of a monstera plant in the style of <s0><s1>, orange and cyan txt2img mode 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<00:49, 1.01s/it] 4%|▍ | 2/50 [00:02<00:48, 1.00s/it] 6%|▌ | 3/50 [00:03<00:47, 1.00s/it] 8%|▊ | 4/50 [00:04<00:46, 1.00s/it] 10%|█ | 5/50 [00:05<00:45, 1.00s/it] 12%|█▏ | 6/50 [00:06<00:44, 1.00s/it] 14%|█▍ | 7/50 [00:07<00:43, 1.00s/it] 16%|█▌ | 8/50 [00:08<00:42, 1.01s/it] 18%|█▊ | 9/50 [00:09<00:41, 1.01s/it] 20%|██ | 10/50 [00:10<00:40, 1.01s/it] 22%|██▏ | 11/50 [00:11<00:39, 1.01s/it] 24%|██▍ | 12/50 [00:12<00:38, 1.01s/it] 26%|██▌ | 13/50 [00:13<00:37, 1.01s/it] 28%|██▊ | 14/50 [00:14<00:36, 1.01s/it] 30%|███ | 15/50 [00:15<00:35, 1.01s/it] 32%|███▏ | 16/50 [00:16<00:34, 1.01s/it] 34%|███▍ | 17/50 [00:17<00:33, 1.01s/it] 36%|███▌ | 18/50 [00:18<00:32, 1.01s/it] 38%|███▊ | 19/50 [00:19<00:31, 1.01s/it] 40%|████ | 20/50 [00:20<00:30, 1.01s/it] 42%|████▏ | 21/50 [00:21<00:29, 1.01s/it] 44%|████▍ | 22/50 [00:22<00:28, 1.01s/it] 46%|████▌ | 23/50 [00:23<00:27, 1.01s/it] 48%|████▊ | 24/50 [00:24<00:26, 1.01s/it] 50%|█████ | 25/50 [00:25<00:25, 1.01s/it] 52%|█████▏ | 26/50 [00:26<00:24, 1.01s/it] 54%|█████▍ | 27/50 [00:27<00:23, 1.01s/it] 56%|█████▌ | 28/50 [00:28<00:22, 1.01s/it] 58%|█████▊ | 29/50 [00:29<00:21, 1.01s/it] 60%|██████ | 30/50 [00:30<00:20, 1.01s/it] 62%|██████▏ | 31/50 [00:31<00:19, 1.01s/it] 64%|██████▍ | 32/50 [00:32<00:18, 1.01s/it] 66%|██████▌ | 33/50 [00:33<00:17, 1.01s/it] 68%|██████▊ | 34/50 [00:34<00:16, 1.01s/it] 70%|███████ | 35/50 [00:35<00:15, 1.01s/it] 72%|███████▏ | 36/50 [00:36<00:14, 1.01s/it] 74%|███████▍ | 37/50 [00:37<00:13, 1.01s/it] 76%|███████▌ | 38/50 [00:38<00:12, 1.02s/it] 78%|███████▊ | 39/50 [00:39<00:11, 1.01s/it] 80%|████████ | 40/50 [00:40<00:10, 1.02s/it] 82%|████████▏ | 41/50 [00:41<00:09, 1.02s/it] 84%|████████▍ | 42/50 [00:42<00:08, 1.02s/it] 86%|████████▌ | 43/50 [00:43<00:07, 1.02s/it] 88%|████████▊ | 44/50 [00:44<00:06, 1.02s/it] 90%|█████████ | 45/50 [00:45<00:05, 1.02s/it] 92%|█████████▏| 46/50 [00:46<00:04, 1.02s/it] 94%|█████████▍| 47/50 [00:47<00:03, 1.02s/it] 96%|█████████▌| 48/50 [00:48<00:02, 1.02s/it] 98%|█████████▊| 49/50 [00:49<00:01, 1.02s/it] 100%|██████████| 50/50 [00:50<00:00, 1.02s/it] 100%|██████████| 50/50 [00:50<00:00, 1.01s/it]Prediction
fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2dIDbtkuistbhi2sxctpvzq4nzr6ymStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1360
- height
- 768
- prompt
- An impasto painting in the style of TOK, neon, orange and cyan
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.72
- num_outputs
- 4
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.95
- negative_prompt
- yellow, cluttered, ugly, photo
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1360, "height": 768, "prompt": "An impasto painting in the style of TOK, neon, orange and cyan", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.72, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "yellow, cluttered, ugly, photo", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run fofr/sdxl-tron using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", { input: { width: 1360, height: 768, prompt: "An impasto painting in the style of TOK, neon, orange and cyan", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.72, num_outputs: 4, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.95, negative_prompt: "yellow, cluttered, ugly, photo", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun fofr/sdxl-tron using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", input={ "width": 1360, "height": 768, "prompt": "An impasto painting in the style of TOK, neon, orange and cyan", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.72, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.95, "negative_prompt": "yellow, cluttered, ugly, photo", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run fofr/sdxl-tron 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": "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", "input": { "width": 1360, "height": 768, "prompt": "An impasto painting in the style of TOK, neon, orange and cyan", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.72, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "yellow, cluttered, ugly, photo", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-08-08T12:16:07.978883Z", "created_at": "2023-08-08T12:14:43.331121Z", "data_removed": false, "error": null, "id": "btkuistbhi2sxctpvzq4nzr6ym", "input": { "width": 1360, "height": 768, "prompt": "An impasto painting in the style of TOK, neon, orange and cyan", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.72, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "yellow, cluttered, ugly, photo", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 9684\nPrompt: An impasto painting in the style of <s0><s1>, neon, orange and cyan\ntxt2img mode\n 0%| | 0/47 [00:00<?, ?it/s]\n 2%|▏ | 1/47 [00:01<00:46, 1.01s/it]\n 4%|▍ | 2/47 [00:02<00:45, 1.02s/it]\n 6%|▋ | 3/47 [00:03<00:44, 1.02s/it]\n 9%|▊ | 4/47 [00:04<00:43, 1.02s/it]\n 11%|█ | 5/47 [00:05<00:42, 1.02s/it]\n 13%|█▎ | 6/47 [00:06<00:41, 1.02s/it]\n 15%|█▍ | 7/47 [00:07<00:40, 1.02s/it]\n 17%|█▋ | 8/47 [00:08<00:39, 1.02s/it]\n 19%|█▉ | 9/47 [00:09<00:38, 1.02s/it]\n 21%|██▏ | 10/47 [00:10<00:37, 1.02s/it]\n 23%|██▎ | 11/47 [00:11<00:36, 1.02s/it]\n 26%|██▌ | 12/47 [00:12<00:35, 1.02s/it]\n 28%|██▊ | 13/47 [00:13<00:34, 1.02s/it]\n 30%|██▉ | 14/47 [00:14<00:33, 1.02s/it]\n 32%|███▏ | 15/47 [00:15<00:32, 1.02s/it]\n 34%|███▍ | 16/47 [00:16<00:31, 1.02s/it]\n 36%|███▌ | 17/47 [00:17<00:30, 1.02s/it]\n 38%|███▊ | 18/47 [00:18<00:29, 1.02s/it]\n 40%|████ | 19/47 [00:19<00:28, 1.02s/it]\n 43%|████▎ | 20/47 [00:20<00:27, 1.02s/it]\n 45%|████▍ | 21/47 [00:21<00:26, 1.02s/it]\n 47%|████▋ | 22/47 [00:22<00:25, 1.02s/it]\n 49%|████▉ | 23/47 [00:23<00:24, 1.02s/it]\n 51%|█████ | 24/47 [00:24<00:23, 1.02s/it]\n 53%|█████▎ | 25/47 [00:25<00:22, 1.02s/it]\n 55%|█████▌ | 26/47 [00:26<00:21, 1.02s/it]\n 57%|█████▋ | 27/47 [00:27<00:20, 1.02s/it]\n 60%|█████▉ | 28/47 [00:28<00:19, 1.02s/it]\n 62%|██████▏ | 29/47 [00:29<00:18, 1.02s/it]\n 64%|██████▍ | 30/47 [00:30<00:17, 1.02s/it]\n 66%|██████▌ | 31/47 [00:31<00:16, 1.02s/it]\n 68%|██████▊ | 32/47 [00:32<00:15, 1.02s/it]\n 70%|███████ | 33/47 [00:33<00:14, 1.02s/it]\n 72%|███████▏ | 34/47 [00:34<00:13, 1.02s/it]\n 74%|███████▍ | 35/47 [00:35<00:12, 1.02s/it]\n 77%|███████▋ | 36/47 [00:36<00:11, 1.02s/it]\n 79%|███████▊ | 37/47 [00:37<00:10, 1.02s/it]\n 81%|████████ | 38/47 [00:38<00:09, 1.02s/it]\n 83%|████████▎ | 39/47 [00:39<00:08, 1.02s/it]\n 85%|████████▌ | 40/47 [00:40<00:07, 1.02s/it]\n 87%|████████▋ | 41/47 [00:41<00:06, 1.02s/it]\n 89%|████████▉ | 42/47 [00:42<00:05, 1.02s/it]\n 91%|█████████▏| 43/47 [00:43<00:04, 1.02s/it]\n 94%|█████████▎| 44/47 [00:44<00:03, 1.02s/it]\n 96%|█████████▌| 45/47 [00:45<00:02, 1.02s/it]\n 98%|█████████▊| 46/47 [00:46<00:01, 1.02s/it]\n100%|██████████| 47/47 [00:47<00:00, 1.02s/it]\n100%|██████████| 47/47 [00:47<00:00, 1.02s/it]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:01, 1.21it/s]\n 67%|██████▋ | 2/3 [00:01<00:00, 1.21it/s]\n100%|██████████| 3/3 [00:02<00:00, 1.21it/s]\n100%|██████████| 3/3 [00:02<00:00, 1.21it/s]", "metrics": { "predict_time": 54.966168, "total_time": 84.647762 }, "output": [ "https://replicate.delivery/pbxt/Ayzb8PCuzrJrOpea8qG2bPe112n9dAacePCVvLxN7dDNg8viA/out-0.png", "https://replicate.delivery/pbxt/UUrskdfw4vy9C6CRgB8Tc2jGAf6sNqkr9QRRrAiHBr0HQeviA/out-1.png", "https://replicate.delivery/pbxt/kqarEsplITJBMF6a5BEiQgvLekTCxSqZf1usxpvmFnyHQeviA/out-2.png", "https://replicate.delivery/pbxt/v2cknLVYOnbRIFWqSv7fLXJ0I2y21A890KIMCh8nPSpDIfXRA/out-3.png" ], "started_at": "2023-08-08T12:15:13.012715Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/btkuistbhi2sxctpvzq4nzr6ym", "cancel": "https://api.replicate.com/v1/predictions/btkuistbhi2sxctpvzq4nzr6ym/cancel" }, "version": "fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d" }Generated inUsing seed: 9684 Prompt: An impasto painting in the style of <s0><s1>, neon, orange and cyan txt2img mode 0%| | 0/47 [00:00<?, ?it/s] 2%|▏ | 1/47 [00:01<00:46, 1.01s/it] 4%|▍ | 2/47 [00:02<00:45, 1.02s/it] 6%|▋ | 3/47 [00:03<00:44, 1.02s/it] 9%|▊ | 4/47 [00:04<00:43, 1.02s/it] 11%|█ | 5/47 [00:05<00:42, 1.02s/it] 13%|█▎ | 6/47 [00:06<00:41, 1.02s/it] 15%|█▍ | 7/47 [00:07<00:40, 1.02s/it] 17%|█▋ | 8/47 [00:08<00:39, 1.02s/it] 19%|█▉ | 9/47 [00:09<00:38, 1.02s/it] 21%|██▏ | 10/47 [00:10<00:37, 1.02s/it] 23%|██▎ | 11/47 [00:11<00:36, 1.02s/it] 26%|██▌ | 12/47 [00:12<00:35, 1.02s/it] 28%|██▊ | 13/47 [00:13<00:34, 1.02s/it] 30%|██▉ | 14/47 [00:14<00:33, 1.02s/it] 32%|███▏ | 15/47 [00:15<00:32, 1.02s/it] 34%|███▍ | 16/47 [00:16<00:31, 1.02s/it] 36%|███▌ | 17/47 [00:17<00:30, 1.02s/it] 38%|███▊ | 18/47 [00:18<00:29, 1.02s/it] 40%|████ | 19/47 [00:19<00:28, 1.02s/it] 43%|████▎ | 20/47 [00:20<00:27, 1.02s/it] 45%|████▍ | 21/47 [00:21<00:26, 1.02s/it] 47%|████▋ | 22/47 [00:22<00:25, 1.02s/it] 49%|████▉ | 23/47 [00:23<00:24, 1.02s/it] 51%|█████ | 24/47 [00:24<00:23, 1.02s/it] 53%|█████▎ | 25/47 [00:25<00:22, 1.02s/it] 55%|█████▌ | 26/47 [00:26<00:21, 1.02s/it] 57%|█████▋ | 27/47 [00:27<00:20, 1.02s/it] 60%|█████▉ | 28/47 [00:28<00:19, 1.02s/it] 62%|██████▏ | 29/47 [00:29<00:18, 1.02s/it] 64%|██████▍ | 30/47 [00:30<00:17, 1.02s/it] 66%|██████▌ | 31/47 [00:31<00:16, 1.02s/it] 68%|██████▊ | 32/47 [00:32<00:15, 1.02s/it] 70%|███████ | 33/47 [00:33<00:14, 1.02s/it] 72%|███████▏ | 34/47 [00:34<00:13, 1.02s/it] 74%|███████▍ | 35/47 [00:35<00:12, 1.02s/it] 77%|███████▋ | 36/47 [00:36<00:11, 1.02s/it] 79%|███████▊ | 37/47 [00:37<00:10, 1.02s/it] 81%|████████ | 38/47 [00:38<00:09, 1.02s/it] 83%|████████▎ | 39/47 [00:39<00:08, 1.02s/it] 85%|████████▌ | 40/47 [00:40<00:07, 1.02s/it] 87%|████████▋ | 41/47 [00:41<00:06, 1.02s/it] 89%|████████▉ | 42/47 [00:42<00:05, 1.02s/it] 91%|█████████▏| 43/47 [00:43<00:04, 1.02s/it] 94%|█████████▎| 44/47 [00:44<00:03, 1.02s/it] 96%|█████████▌| 45/47 [00:45<00:02, 1.02s/it] 98%|█████████▊| 46/47 [00:46<00:01, 1.02s/it] 100%|██████████| 47/47 [00:47<00:00, 1.02s/it] 100%|██████████| 47/47 [00:47<00:00, 1.02s/it] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:01, 1.21it/s] 67%|██████▋ | 2/3 [00:01<00:00, 1.21it/s] 100%|██████████| 3/3 [00:02<00:00, 1.21it/s] 100%|██████████| 3/3 [00:02<00:00, 1.21it/s]Prediction
fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2dIDusddtilb4ufyzccenrbg6owwauStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1360
- height
- 768
- prompt
- In the style of TOK, an IKEA catalogue photo of a living room, neon
- refine
- no_refiner
- scheduler
- K_EULER_ANCESTRAL
- lora_scale
- 0.6
- num_outputs
- 4
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- text, logo, garish, oversaturated, outside, windows, ugly, corridor
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1360, "height": 768, "prompt": "In the style of TOK, an IKEA catalogue photo of a living room, neon", "refine": "no_refiner", "scheduler": "K_EULER_ANCESTRAL", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "text, logo, garish, oversaturated, outside, windows, ugly, corridor", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run fofr/sdxl-tron using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", { input: { width: 1360, height: 768, prompt: "In the style of TOK, an IKEA catalogue photo of a living room, neon", refine: "no_refiner", scheduler: "K_EULER_ANCESTRAL", lora_scale: 0.6, num_outputs: 4, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.8, negative_prompt: "text, logo, garish, oversaturated, outside, windows, ugly, corridor", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun fofr/sdxl-tron using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", input={ "width": 1360, "height": 768, "prompt": "In the style of TOK, an IKEA catalogue photo of a living room, neon", "refine": "no_refiner", "scheduler": "K_EULER_ANCESTRAL", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.8, "negative_prompt": "text, logo, garish, oversaturated, outside, windows, ugly, corridor", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run fofr/sdxl-tron 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": "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", "input": { "width": 1360, "height": 768, "prompt": "In the style of TOK, an IKEA catalogue photo of a living room, neon", "refine": "no_refiner", "scheduler": "K_EULER_ANCESTRAL", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "text, logo, garish, oversaturated, outside, windows, ugly, corridor", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-08-08T13:20:08.177661Z", "created_at": "2023-08-08T13:19:11.824066Z", "data_removed": false, "error": null, "id": "usddtilb4ufyzccenrbg6owwau", "input": { "width": 1360, "height": 768, "prompt": "In the style of TOK, an IKEA catalogue photo of a living room, neon", "refine": "no_refiner", "scheduler": "K_EULER_ANCESTRAL", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "text, logo, garish, oversaturated, outside, windows, ugly, corridor", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 20278\nPrompt: In the style of <s0><s1>, an IKEA catalogue photo of a living room, neon\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:01<00:49, 1.01s/it]\n 4%|▍ | 2/50 [00:02<00:48, 1.01s/it]\n 6%|▌ | 3/50 [00:03<00:47, 1.01s/it]\n 8%|▊ | 4/50 [00:04<00:46, 1.01s/it]\n 10%|█ | 5/50 [00:05<00:45, 1.01s/it]\n 12%|█▏ | 6/50 [00:06<00:44, 1.01s/it]\n 14%|█▍ | 7/50 [00:07<00:43, 1.02s/it]\n 16%|█▌ | 8/50 [00:08<00:42, 1.02s/it]\n 18%|█▊ | 9/50 [00:09<00:41, 1.02s/it]\n 20%|██ | 10/50 [00:10<00:40, 1.02s/it]\n 22%|██▏ | 11/50 [00:11<00:39, 1.02s/it]\n 24%|██▍ | 12/50 [00:12<00:38, 1.02s/it]\n 26%|██▌ | 13/50 [00:13<00:37, 1.02s/it]\n 28%|██▊ | 14/50 [00:14<00:36, 1.02s/it]\n 30%|███ | 15/50 [00:15<00:35, 1.02s/it]\n 32%|███▏ | 16/50 [00:16<00:34, 1.02s/it]\n 34%|███▍ | 17/50 [00:17<00:33, 1.02s/it]\n 36%|███▌ | 18/50 [00:18<00:32, 1.02s/it]\n 38%|███▊ | 19/50 [00:19<00:31, 1.02s/it]\n 40%|████ | 20/50 [00:20<00:30, 1.02s/it]\n 42%|████▏ | 21/50 [00:21<00:29, 1.02s/it]\n 44%|████▍ | 22/50 [00:22<00:28, 1.02s/it]\n 46%|████▌ | 23/50 [00:23<00:27, 1.02s/it]\n 48%|████▊ | 24/50 [00:24<00:26, 1.02s/it]\n 50%|█████ | 25/50 [00:25<00:25, 1.02s/it]\n 52%|█████▏ | 26/50 [00:26<00:24, 1.02s/it]\n 54%|█████▍ | 27/50 [00:27<00:23, 1.02s/it]\n 56%|█████▌ | 28/50 [00:28<00:22, 1.02s/it]\n 58%|█████▊ | 29/50 [00:29<00:21, 1.02s/it]\n 60%|██████ | 30/50 [00:30<00:20, 1.02s/it]\n 62%|██████▏ | 31/50 [00:31<00:19, 1.02s/it]\n 64%|██████▍ | 32/50 [00:32<00:18, 1.02s/it]\n 66%|██████▌ | 33/50 [00:33<00:17, 1.02s/it]\n 68%|██████▊ | 34/50 [00:34<00:16, 1.02s/it]\n 70%|███████ | 35/50 [00:35<00:15, 1.02s/it]\n 72%|███████▏ | 36/50 [00:36<00:14, 1.02s/it]\n 74%|███████▍ | 37/50 [00:37<00:13, 1.02s/it]\n 76%|███████▌ | 38/50 [00:38<00:12, 1.02s/it]\n 78%|███████▊ | 39/50 [00:39<00:11, 1.02s/it]\n 80%|████████ | 40/50 [00:40<00:10, 1.02s/it]\n 82%|████████▏ | 41/50 [00:41<00:09, 1.02s/it]\n 84%|████████▍ | 42/50 [00:42<00:08, 1.02s/it]\n 86%|████████▌ | 43/50 [00:43<00:07, 1.02s/it]\n 88%|████████▊ | 44/50 [00:44<00:06, 1.02s/it]\n 90%|█████████ | 45/50 [00:45<00:05, 1.02s/it]\n 92%|█████████▏| 46/50 [00:46<00:04, 1.02s/it]\n 94%|█████████▍| 47/50 [00:47<00:03, 1.02s/it]\n 96%|█████████▌| 48/50 [00:48<00:02, 1.02s/it]\n 98%|█████████▊| 49/50 [00:49<00:01, 1.02s/it]\n100%|██████████| 50/50 [00:50<00:00, 1.02s/it]\n100%|██████████| 50/50 [00:50<00:00, 1.02s/it]", "metrics": { "predict_time": 56.384902, "total_time": 56.353595 }, "output": [ "https://replicate.delivery/pbxt/fnNJOiyrmv3GbaEefPphMbidzahMWhITBpJxWpKvRdAKYefKC/out-0.png", "https://replicate.delivery/pbxt/mWTKPRBUfqwenkY5MiKyHErRqV4hifHFPeJewrdSM3Uwg5fVE/out-1.png", "https://replicate.delivery/pbxt/B0GOdM1D8lrLH5c6A96X86tM2WctEm5D3b68rTQgzM9BzfrIA/out-2.png", "https://replicate.delivery/pbxt/Bd31BNRNIg55MlWOFL5eqd3nrYLy1UpuqeJXzMxwh5LHMfviA/out-3.png" ], "started_at": "2023-08-08T13:19:11.792759Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/usddtilb4ufyzccenrbg6owwau", "cancel": "https://api.replicate.com/v1/predictions/usddtilb4ufyzccenrbg6owwau/cancel" }, "version": "fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d" }Generated inUsing seed: 20278 Prompt: In the style of <s0><s1>, an IKEA catalogue photo of a living room, neon txt2img mode 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:01<00:49, 1.01s/it] 4%|▍ | 2/50 [00:02<00:48, 1.01s/it] 6%|▌ | 3/50 [00:03<00:47, 1.01s/it] 8%|▊ | 4/50 [00:04<00:46, 1.01s/it] 10%|█ | 5/50 [00:05<00:45, 1.01s/it] 12%|█▏ | 6/50 [00:06<00:44, 1.01s/it] 14%|█▍ | 7/50 [00:07<00:43, 1.02s/it] 16%|█▌ | 8/50 [00:08<00:42, 1.02s/it] 18%|█▊ | 9/50 [00:09<00:41, 1.02s/it] 20%|██ | 10/50 [00:10<00:40, 1.02s/it] 22%|██▏ | 11/50 [00:11<00:39, 1.02s/it] 24%|██▍ | 12/50 [00:12<00:38, 1.02s/it] 26%|██▌ | 13/50 [00:13<00:37, 1.02s/it] 28%|██▊ | 14/50 [00:14<00:36, 1.02s/it] 30%|███ | 15/50 [00:15<00:35, 1.02s/it] 32%|███▏ | 16/50 [00:16<00:34, 1.02s/it] 34%|███▍ | 17/50 [00:17<00:33, 1.02s/it] 36%|███▌ | 18/50 [00:18<00:32, 1.02s/it] 38%|███▊ | 19/50 [00:19<00:31, 1.02s/it] 40%|████ | 20/50 [00:20<00:30, 1.02s/it] 42%|████▏ | 21/50 [00:21<00:29, 1.02s/it] 44%|████▍ | 22/50 [00:22<00:28, 1.02s/it] 46%|████▌ | 23/50 [00:23<00:27, 1.02s/it] 48%|████▊ | 24/50 [00:24<00:26, 1.02s/it] 50%|█████ | 25/50 [00:25<00:25, 1.02s/it] 52%|█████▏ | 26/50 [00:26<00:24, 1.02s/it] 54%|█████▍ | 27/50 [00:27<00:23, 1.02s/it] 56%|█████▌ | 28/50 [00:28<00:22, 1.02s/it] 58%|█████▊ | 29/50 [00:29<00:21, 1.02s/it] 60%|██████ | 30/50 [00:30<00:20, 1.02s/it] 62%|██████▏ | 31/50 [00:31<00:19, 1.02s/it] 64%|██████▍ | 32/50 [00:32<00:18, 1.02s/it] 66%|██████▌ | 33/50 [00:33<00:17, 1.02s/it] 68%|██████▊ | 34/50 [00:34<00:16, 1.02s/it] 70%|███████ | 35/50 [00:35<00:15, 1.02s/it] 72%|███████▏ | 36/50 [00:36<00:14, 1.02s/it] 74%|███████▍ | 37/50 [00:37<00:13, 1.02s/it] 76%|███████▌ | 38/50 [00:38<00:12, 1.02s/it] 78%|███████▊ | 39/50 [00:39<00:11, 1.02s/it] 80%|████████ | 40/50 [00:40<00:10, 1.02s/it] 82%|████████▏ | 41/50 [00:41<00:09, 1.02s/it] 84%|████████▍ | 42/50 [00:42<00:08, 1.02s/it] 86%|████████▌ | 43/50 [00:43<00:07, 1.02s/it] 88%|████████▊ | 44/50 [00:44<00:06, 1.02s/it] 90%|█████████ | 45/50 [00:45<00:05, 1.02s/it] 92%|█████████▏| 46/50 [00:46<00:04, 1.02s/it] 94%|█████████▍| 47/50 [00:47<00:03, 1.02s/it] 96%|█████████▌| 48/50 [00:48<00:02, 1.02s/it] 98%|█████████▊| 49/50 [00:49<00:01, 1.02s/it] 100%|██████████| 50/50 [00:50<00:00, 1.02s/it] 100%|██████████| 50/50 [00:50<00:00, 1.02s/it]Prediction
fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2dIDw42rvslbxscjx4qe6swc5w732iStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- A futuristic close-up portrait photo in the style of TRN
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.9
- negative_prompt
- ugly, broken, disfigured, people
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "A futuristic close-up portrait photo in the style of TRN", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.9, "negative_prompt": "ugly, broken, disfigured, people", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run fofr/sdxl-tron using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", { input: { width: 1024, height: 1024, prompt: "A futuristic close-up portrait photo in the style of TRN", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.9, negative_prompt: "ugly, broken, disfigured, people", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun fofr/sdxl-tron using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", input={ "width": 1024, "height": 1024, "prompt": "A futuristic close-up portrait photo in the style of TRN", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.9, "negative_prompt": "ugly, broken, disfigured, people", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run fofr/sdxl-tron 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": "fofr/sdxl-tron:fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d", "input": { "width": 1024, "height": 1024, "prompt": "A futuristic close-up portrait photo in the style of TRN", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.9, "negative_prompt": "ugly, broken, disfigured, people", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-08-10T13:30:27.489798Z", "created_at": "2023-08-10T13:30:12.800723Z", "data_removed": false, "error": null, "id": "w42rvslbxscjx4qe6swc5w732i", "input": { "width": 1024, "height": 1024, "prompt": "A futuristic close-up portrait photo in the style of TRN", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.9, "negative_prompt": "ugly, broken, disfigured, people", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 38525\nPrompt: A futuristic close-up portrait photo in the style of TRN\ntxt2img mode\n 0%| | 0/45 [00:00<?, ?it/s]\n 2%|▏ | 1/45 [00:00<00:11, 3.70it/s]\n 4%|▍ | 2/45 [00:00<00:11, 3.70it/s]\n 7%|▋ | 3/45 [00:00<00:11, 3.70it/s]\n 9%|▉ | 4/45 [00:01<00:11, 3.68it/s]\n 11%|█ | 5/45 [00:01<00:10, 3.69it/s]\n 13%|█▎ | 6/45 [00:01<00:10, 3.69it/s]\n 16%|█▌ | 7/45 [00:01<00:10, 3.69it/s]\n 18%|█▊ | 8/45 [00:02<00:10, 3.68it/s]\n 20%|██ | 9/45 [00:02<00:09, 3.68it/s]\n 22%|██▏ | 10/45 [00:02<00:09, 3.68it/s]\n 24%|██▍ | 11/45 [00:02<00:09, 3.68it/s]\n 27%|██▋ | 12/45 [00:03<00:08, 3.67it/s]\n 29%|██▉ | 13/45 [00:03<00:08, 3.67it/s]\n 31%|███ | 14/45 [00:03<00:08, 3.67it/s]\n 33%|███▎ | 15/45 [00:04<00:08, 3.67it/s]\n 36%|███▌ | 16/45 [00:04<00:07, 3.67it/s]\n 38%|███▊ | 17/45 [00:04<00:07, 3.67it/s]\n 40%|████ | 18/45 [00:04<00:07, 3.67it/s]\n 42%|████▏ | 19/45 [00:05<00:07, 3.67it/s]\n 44%|████▍ | 20/45 [00:05<00:06, 3.67it/s]\n 47%|████▋ | 21/45 [00:05<00:06, 3.67it/s]\n 49%|████▉ | 22/45 [00:05<00:06, 3.67it/s]\n 51%|█████ | 23/45 [00:06<00:05, 3.67it/s]\n 53%|█████▎ | 24/45 [00:06<00:05, 3.67it/s]\n 56%|█████▌ | 25/45 [00:06<00:05, 3.67it/s]\n 58%|█████▊ | 26/45 [00:07<00:05, 3.67it/s]\n 60%|██████ | 27/45 [00:07<00:04, 3.67it/s]\n 62%|██████▏ | 28/45 [00:07<00:04, 3.67it/s]\n 64%|██████▍ | 29/45 [00:07<00:04, 3.66it/s]\n 67%|██████▋ | 30/45 [00:08<00:04, 3.67it/s]\n 69%|██████▉ | 31/45 [00:08<00:03, 3.66it/s]\n 71%|███████ | 32/45 [00:08<00:03, 3.66it/s]\n 73%|███████▎ | 33/45 [00:08<00:03, 3.66it/s]\n 76%|███████▌ | 34/45 [00:09<00:03, 3.66it/s]\n 78%|███████▊ | 35/45 [00:09<00:02, 3.66it/s]\n 80%|████████ | 36/45 [00:09<00:02, 3.66it/s]\n 82%|████████▏ | 37/45 [00:10<00:02, 3.66it/s]\n 84%|████████▍ | 38/45 [00:10<00:01, 3.66it/s]\n 87%|████████▋ | 39/45 [00:10<00:01, 3.66it/s]\n 89%|████████▉ | 40/45 [00:10<00:01, 3.66it/s]\n 91%|█████████ | 41/45 [00:11<00:01, 3.66it/s]\n 93%|█████████▎| 42/45 [00:11<00:00, 3.66it/s]\n 96%|█████████▌| 43/45 [00:11<00:00, 3.66it/s]\n 98%|█████████▊| 44/45 [00:11<00:00, 3.66it/s]\n100%|██████████| 45/45 [00:12<00:00, 3.66it/s]\n100%|██████████| 45/45 [00:12<00:00, 3.67it/s]\n 0%| | 0/5 [00:00<?, ?it/s]\n 20%|██ | 1/5 [00:00<00:00, 4.33it/s]\n 40%|████ | 2/5 [00:00<00:00, 4.31it/s]\n 60%|██████ | 3/5 [00:00<00:00, 4.30it/s]\n 80%|████████ | 4/5 [00:00<00:00, 4.29it/s]\n100%|██████████| 5/5 [00:01<00:00, 4.28it/s]\n100%|██████████| 5/5 [00:01<00:00, 4.29it/s]", "metrics": { "predict_time": 14.72912, "total_time": 14.689075 }, "output": [ "https://replicate.delivery/pbxt/POE8cHFcZtqQL5glo2ln85giLmgTsO6u3JtFGxJ6Afx5wUsIA/out-0.png" ], "started_at": "2023-08-10T13:30:12.760678Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/w42rvslbxscjx4qe6swc5w732i", "cancel": "https://api.replicate.com/v1/predictions/w42rvslbxscjx4qe6swc5w732i/cancel" }, "version": "fd920825e12db2a942f8a9cac40ad4f624a34a06faba3ac1b44a5305df8c6e2d" }Generated inUsing seed: 38525 Prompt: A futuristic close-up portrait photo in the style of TRN txt2img mode 0%| | 0/45 [00:00<?, ?it/s] 2%|▏ | 1/45 [00:00<00:11, 3.70it/s] 4%|▍ | 2/45 [00:00<00:11, 3.70it/s] 7%|▋ | 3/45 [00:00<00:11, 3.70it/s] 9%|▉ | 4/45 [00:01<00:11, 3.68it/s] 11%|█ | 5/45 [00:01<00:10, 3.69it/s] 13%|█▎ | 6/45 [00:01<00:10, 3.69it/s] 16%|█▌ | 7/45 [00:01<00:10, 3.69it/s] 18%|█▊ | 8/45 [00:02<00:10, 3.68it/s] 20%|██ | 9/45 [00:02<00:09, 3.68it/s] 22%|██▏ | 10/45 [00:02<00:09, 3.68it/s] 24%|██▍ | 11/45 [00:02<00:09, 3.68it/s] 27%|██▋ | 12/45 [00:03<00:08, 3.67it/s] 29%|██▉ | 13/45 [00:03<00:08, 3.67it/s] 31%|███ | 14/45 [00:03<00:08, 3.67it/s] 33%|███▎ | 15/45 [00:04<00:08, 3.67it/s] 36%|███▌ | 16/45 [00:04<00:07, 3.67it/s] 38%|███▊ | 17/45 [00:04<00:07, 3.67it/s] 40%|████ | 18/45 [00:04<00:07, 3.67it/s] 42%|████▏ | 19/45 [00:05<00:07, 3.67it/s] 44%|████▍ | 20/45 [00:05<00:06, 3.67it/s] 47%|████▋ | 21/45 [00:05<00:06, 3.67it/s] 49%|████▉ | 22/45 [00:05<00:06, 3.67it/s] 51%|█████ | 23/45 [00:06<00:05, 3.67it/s] 53%|█████▎ | 24/45 [00:06<00:05, 3.67it/s] 56%|█████▌ | 25/45 [00:06<00:05, 3.67it/s] 58%|█████▊ | 26/45 [00:07<00:05, 3.67it/s] 60%|██████ | 27/45 [00:07<00:04, 3.67it/s] 62%|██████▏ | 28/45 [00:07<00:04, 3.67it/s] 64%|██████▍ | 29/45 [00:07<00:04, 3.66it/s] 67%|██████▋ | 30/45 [00:08<00:04, 3.67it/s] 69%|██████▉ | 31/45 [00:08<00:03, 3.66it/s] 71%|███████ | 32/45 [00:08<00:03, 3.66it/s] 73%|███████▎ | 33/45 [00:08<00:03, 3.66it/s] 76%|███████▌ | 34/45 [00:09<00:03, 3.66it/s] 78%|███████▊ | 35/45 [00:09<00:02, 3.66it/s] 80%|████████ | 36/45 [00:09<00:02, 3.66it/s] 82%|████████▏ | 37/45 [00:10<00:02, 3.66it/s] 84%|████████▍ | 38/45 [00:10<00:01, 3.66it/s] 87%|████████▋ | 39/45 [00:10<00:01, 3.66it/s] 89%|████████▉ | 40/45 [00:10<00:01, 3.66it/s] 91%|█████████ | 41/45 [00:11<00:01, 3.66it/s] 93%|█████████▎| 42/45 [00:11<00:00, 3.66it/s] 96%|█████████▌| 43/45 [00:11<00:00, 3.66it/s] 98%|█████████▊| 44/45 [00:11<00:00, 3.66it/s] 100%|██████████| 45/45 [00:12<00:00, 3.66it/s] 100%|██████████| 45/45 [00:12<00:00, 3.67it/s] 0%| | 0/5 [00:00<?, ?it/s] 20%|██ | 1/5 [00:00<00:00, 4.33it/s] 40%|████ | 2/5 [00:00<00:00, 4.31it/s] 60%|██████ | 3/5 [00:00<00:00, 4.30it/s] 80%|████████ | 4/5 [00:00<00:00, 4.29it/s] 100%|██████████| 5/5 [00:01<00:00, 4.28it/s] 100%|██████████| 5/5 [00:01<00:00, 4.29it/s]
Want to make some of these yourself?
Run this model
