fofr / sdxl-xmas-sweater
SDXL fine-tuned on Xmas sweaters
- Public
- 621 runs
-
L40S
- SDXL fine-tune
Prediction
fofr/sdxl-xmas-sweater:0690f6c650d0899dcdeaf789d33cf86bad646a00d5efe7b7600998f2950705dbIDwbor6vtb3gdqz5gv3mrsd3zg4eStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 768
- height
- 768
- prompt
- A photo of a TOK sweater, Christmas tree
- 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
- prompt_strength
- 0.8
- num_inference_steps
- 30
{ "width": 768, "height": 768, "prompt": "A photo of a TOK sweater, Christmas tree", "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": "", "prompt_strength": 0.8, "num_inference_steps": 30 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run fofr/sdxl-xmas-sweater using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-xmas-sweater:0690f6c650d0899dcdeaf789d33cf86bad646a00d5efe7b7600998f2950705db", { input: { width: 768, height: 768, prompt: "A photo of a TOK sweater, Christmas tree", 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: "", prompt_strength: 0.8, num_inference_steps: 30 } } ); // 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 replicate
Import the client:import replicate
Run fofr/sdxl-xmas-sweater using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-xmas-sweater:0690f6c650d0899dcdeaf789d33cf86bad646a00d5efe7b7600998f2950705db", input={ "width": 768, "height": 768, "prompt": "A photo of a TOK sweater, Christmas tree", "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": "", "prompt_strength": 0.8, "num_inference_steps": 30 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run fofr/sdxl-xmas-sweater 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-xmas-sweater:0690f6c650d0899dcdeaf789d33cf86bad646a00d5efe7b7600998f2950705db", "input": { "width": 768, "height": 768, "prompt": "A photo of a TOK sweater, Christmas tree", "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": "", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-12-03T21:31:33.530598Z", "created_at": "2023-12-03T21:31:26.972342Z", "data_removed": false, "error": null, "id": "wbor6vtb3gdqz5gv3mrsd3zg4e", "input": { "width": 768, "height": 768, "prompt": "A photo of a TOK sweater, Christmas tree", "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": "", "prompt_strength": 0.8, "num_inference_steps": 30 }, "logs": "Using seed: 27501\nskipping loading .. weights already loaded\nPrompt: A photo of a <s0><s1> sweater, Christmas tree\ntxt2img mode\n 0%| | 0/27 [00:00<?, ?it/s]\n 4%|▎ | 1/27 [00:00<00:04, 6.15it/s]\n 7%|▋ | 2/27 [00:00<00:04, 6.09it/s]\n 11%|█ | 3/27 [00:00<00:03, 6.11it/s]\n 15%|█▍ | 4/27 [00:00<00:03, 6.11it/s]\n 19%|█▊ | 5/27 [00:00<00:03, 6.11it/s]\n 22%|██▏ | 6/27 [00:00<00:03, 6.10it/s]\n 26%|██▌ | 7/27 [00:01<00:03, 6.10it/s]\n 30%|██▉ | 8/27 [00:01<00:03, 6.10it/s]\n 33%|███▎ | 9/27 [00:01<00:02, 6.10it/s]\n 37%|███▋ | 10/27 [00:01<00:02, 6.11it/s]\n 41%|████ | 11/27 [00:01<00:02, 6.10it/s]\n 44%|████▍ | 12/27 [00:01<00:02, 6.09it/s]\n 48%|████▊ | 13/27 [00:02<00:02, 6.10it/s]\n 52%|█████▏ | 14/27 [00:02<00:02, 6.10it/s]\n 56%|█████▌ | 15/27 [00:02<00:01, 6.10it/s]\n 59%|█████▉ | 16/27 [00:02<00:01, 6.09it/s]\n 63%|██████▎ | 17/27 [00:02<00:01, 6.07it/s]\n 67%|██████▋ | 18/27 [00:02<00:01, 6.07it/s]\n 70%|███████ | 19/27 [00:03<00:01, 6.07it/s]\n 74%|███████▍ | 20/27 [00:03<00:01, 6.08it/s]\n 78%|███████▊ | 21/27 [00:03<00:00, 6.08it/s]\n 81%|████████▏ | 22/27 [00:03<00:00, 6.08it/s]\n 85%|████████▌ | 23/27 [00:03<00:00, 6.08it/s]\n 89%|████████▉ | 24/27 [00:03<00:00, 6.08it/s]\n 93%|█████████▎| 25/27 [00:04<00:00, 6.07it/s]\n 96%|█████████▋| 26/27 [00:04<00:00, 6.08it/s]\n100%|██████████| 27/27 [00:04<00:00, 6.08it/s]\n100%|██████████| 27/27 [00:04<00:00, 6.09it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 7.73it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 7.64it/s]\n100%|██████████| 3/3 [00:00<00:00, 7.62it/s]\n100%|██████████| 3/3 [00:00<00:00, 7.63it/s]", "metrics": { "predict_time": 6.518381, "total_time": 6.558256 }, "output": [ "https://replicate.delivery/pbxt/qfRo9tfIr1nJc0uCgXmALHCb5zdpd2RaNbfqmrlpRn6ptU9jA/out-0.png" ], "started_at": "2023-12-03T21:31:27.012217Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/wbor6vtb3gdqz5gv3mrsd3zg4e", "cancel": "https://api.replicate.com/v1/predictions/wbor6vtb3gdqz5gv3mrsd3zg4e/cancel" }, "version": "0690f6c650d0899dcdeaf789d33cf86bad646a00d5efe7b7600998f2950705db" }
Generated inUsing seed: 27501 skipping loading .. weights already loaded Prompt: A photo of a <s0><s1> sweater, Christmas tree txt2img mode 0%| | 0/27 [00:00<?, ?it/s] 4%|▎ | 1/27 [00:00<00:04, 6.15it/s] 7%|▋ | 2/27 [00:00<00:04, 6.09it/s] 11%|█ | 3/27 [00:00<00:03, 6.11it/s] 15%|█▍ | 4/27 [00:00<00:03, 6.11it/s] 19%|█▊ | 5/27 [00:00<00:03, 6.11it/s] 22%|██▏ | 6/27 [00:00<00:03, 6.10it/s] 26%|██▌ | 7/27 [00:01<00:03, 6.10it/s] 30%|██▉ | 8/27 [00:01<00:03, 6.10it/s] 33%|███▎ | 9/27 [00:01<00:02, 6.10it/s] 37%|███▋ | 10/27 [00:01<00:02, 6.11it/s] 41%|████ | 11/27 [00:01<00:02, 6.10it/s] 44%|████▍ | 12/27 [00:01<00:02, 6.09it/s] 48%|████▊ | 13/27 [00:02<00:02, 6.10it/s] 52%|█████▏ | 14/27 [00:02<00:02, 6.10it/s] 56%|█████▌ | 15/27 [00:02<00:01, 6.10it/s] 59%|█████▉ | 16/27 [00:02<00:01, 6.09it/s] 63%|██████▎ | 17/27 [00:02<00:01, 6.07it/s] 67%|██████▋ | 18/27 [00:02<00:01, 6.07it/s] 70%|███████ | 19/27 [00:03<00:01, 6.07it/s] 74%|███████▍ | 20/27 [00:03<00:01, 6.08it/s] 78%|███████▊ | 21/27 [00:03<00:00, 6.08it/s] 81%|████████▏ | 22/27 [00:03<00:00, 6.08it/s] 85%|████████▌ | 23/27 [00:03<00:00, 6.08it/s] 89%|████████▉ | 24/27 [00:03<00:00, 6.08it/s] 93%|█████████▎| 25/27 [00:04<00:00, 6.07it/s] 96%|█████████▋| 26/27 [00:04<00:00, 6.08it/s] 100%|██████████| 27/27 [00:04<00:00, 6.08it/s] 100%|██████████| 27/27 [00:04<00:00, 6.09it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 7.73it/s] 67%|██████▋ | 2/3 [00:00<00:00, 7.64it/s] 100%|██████████| 3/3 [00:00<00:00, 7.62it/s] 100%|██████████| 3/3 [00:00<00:00, 7.63it/s]
Prediction
fofr/sdxl-xmas-sweater:0690f6c650d0899dcdeaf789d33cf86bad646a00d5efe7b7600998f2950705dbIDjyk3zk3bnovkio7kfalkm6xlxiStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 768
- height
- 768
- prompt
- A photo of santa wearing a TOK sweater
- 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
- prompt_strength
- 0.8
- num_inference_steps
- 30
{ "width": 768, "height": 768, "prompt": "A photo of santa wearing a TOK sweater", "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": "", "prompt_strength": 0.8, "num_inference_steps": 30 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run fofr/sdxl-xmas-sweater using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-xmas-sweater:0690f6c650d0899dcdeaf789d33cf86bad646a00d5efe7b7600998f2950705db", { input: { width: 768, height: 768, prompt: "A photo of santa wearing a TOK sweater", 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: "", prompt_strength: 0.8, num_inference_steps: 30 } } ); // 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 replicate
Import the client:import replicate
Run fofr/sdxl-xmas-sweater using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-xmas-sweater:0690f6c650d0899dcdeaf789d33cf86bad646a00d5efe7b7600998f2950705db", input={ "width": 768, "height": 768, "prompt": "A photo of santa wearing a TOK sweater", "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": "", "prompt_strength": 0.8, "num_inference_steps": 30 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run fofr/sdxl-xmas-sweater 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-xmas-sweater:0690f6c650d0899dcdeaf789d33cf86bad646a00d5efe7b7600998f2950705db", "input": { "width": 768, "height": 768, "prompt": "A photo of santa wearing a TOK sweater", "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": "", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-12-03T21:32:06.232070Z", "created_at": "2023-12-03T21:31:54.922767Z", "data_removed": false, "error": null, "id": "jyk3zk3bnovkio7kfalkm6xlxi", "input": { "width": 768, "height": 768, "prompt": "A photo of santa wearing a TOK sweater", "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": "", "prompt_strength": 0.8, "num_inference_steps": 30 }, "logs": "Using seed: 19576\nEnsuring enough disk space...\nFree disk space: 2440310452224\nDownloading weights: https://replicate.delivery/pbxt/uSerlhyRLxz5fUKP2sXU3RhukmHeeFiUVM0WTB5mvNNlbF4HB/trained_model.tar\nb'Downloaded 186 MB bytes in 0.239s (779 MB/s)\\nExtracted 186 MB in 0.062s (3.0 GB/s)\\n'\nDownloaded weights in 0.45714402198791504 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A photo of santa wearing a <s0><s1> sweater\ntxt2img mode\n 0%| | 0/27 [00:00<?, ?it/s]\n 4%|▎ | 1/27 [00:00<00:04, 6.16it/s]\n 7%|▋ | 2/27 [00:00<00:04, 6.13it/s]\n 11%|█ | 3/27 [00:00<00:03, 6.11it/s]\n 15%|█▍ | 4/27 [00:00<00:03, 6.10it/s]\n 19%|█▊ | 5/27 [00:00<00:03, 6.10it/s]\n 22%|██▏ | 6/27 [00:00<00:03, 6.09it/s]\n 26%|██▌ | 7/27 [00:01<00:03, 6.09it/s]\n 30%|██▉ | 8/27 [00:01<00:03, 6.09it/s]\n 33%|███▎ | 9/27 [00:01<00:02, 6.09it/s]\n 37%|███▋ | 10/27 [00:01<00:02, 6.08it/s]\n 41%|████ | 11/27 [00:01<00:02, 6.08it/s]\n 44%|████▍ | 12/27 [00:01<00:02, 6.09it/s]\n 48%|████▊ | 13/27 [00:02<00:02, 6.09it/s]\n 52%|█████▏ | 14/27 [00:02<00:02, 6.08it/s]\n 56%|█████▌ | 15/27 [00:02<00:01, 6.08it/s]\n 59%|█████▉ | 16/27 [00:02<00:01, 6.08it/s]\n 63%|██████▎ | 17/27 [00:02<00:01, 6.09it/s]\n 67%|██████▋ | 18/27 [00:02<00:01, 6.10it/s]\n 70%|███████ | 19/27 [00:03<00:01, 6.10it/s]\n 74%|███████▍ | 20/27 [00:03<00:01, 6.10it/s]\n 78%|███████▊ | 21/27 [00:03<00:00, 6.11it/s]\n 81%|████████▏ | 22/27 [00:03<00:00, 6.11it/s]\n 85%|████████▌ | 23/27 [00:03<00:00, 6.11it/s]\n 89%|████████▉ | 24/27 [00:03<00:00, 6.11it/s]\n 93%|█████████▎| 25/27 [00:04<00:00, 6.11it/s]\n 96%|█████████▋| 26/27 [00:04<00:00, 6.11it/s]\n100%|██████████| 27/27 [00:04<00:00, 6.11it/s]\n100%|██████████| 27/27 [00:04<00:00, 6.10it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 6.80it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 7.25it/s]\n100%|██████████| 3/3 [00:00<00:00, 7.40it/s]\n100%|██████████| 3/3 [00:00<00:00, 7.30it/s]", "metrics": { "predict_time": 6.805732, "total_time": 11.309303 }, "output": [ "https://replicate.delivery/pbxt/Dd9IAXSX2cJCANdbvYFBa7YI6518qoSXSz9UF6lDb8Q1lqfIA/out-0.png" ], "started_at": "2023-12-03T21:31:59.426338Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/jyk3zk3bnovkio7kfalkm6xlxi", "cancel": "https://api.replicate.com/v1/predictions/jyk3zk3bnovkio7kfalkm6xlxi/cancel" }, "version": "0690f6c650d0899dcdeaf789d33cf86bad646a00d5efe7b7600998f2950705db" }
Generated inUsing seed: 19576 Ensuring enough disk space... Free disk space: 2440310452224 Downloading weights: https://replicate.delivery/pbxt/uSerlhyRLxz5fUKP2sXU3RhukmHeeFiUVM0WTB5mvNNlbF4HB/trained_model.tar b'Downloaded 186 MB bytes in 0.239s (779 MB/s)\nExtracted 186 MB in 0.062s (3.0 GB/s)\n' Downloaded weights in 0.45714402198791504 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A photo of santa wearing a <s0><s1> sweater txt2img mode 0%| | 0/27 [00:00<?, ?it/s] 4%|▎ | 1/27 [00:00<00:04, 6.16it/s] 7%|▋ | 2/27 [00:00<00:04, 6.13it/s] 11%|█ | 3/27 [00:00<00:03, 6.11it/s] 15%|█▍ | 4/27 [00:00<00:03, 6.10it/s] 19%|█▊ | 5/27 [00:00<00:03, 6.10it/s] 22%|██▏ | 6/27 [00:00<00:03, 6.09it/s] 26%|██▌ | 7/27 [00:01<00:03, 6.09it/s] 30%|██▉ | 8/27 [00:01<00:03, 6.09it/s] 33%|███▎ | 9/27 [00:01<00:02, 6.09it/s] 37%|███▋ | 10/27 [00:01<00:02, 6.08it/s] 41%|████ | 11/27 [00:01<00:02, 6.08it/s] 44%|████▍ | 12/27 [00:01<00:02, 6.09it/s] 48%|████▊ | 13/27 [00:02<00:02, 6.09it/s] 52%|█████▏ | 14/27 [00:02<00:02, 6.08it/s] 56%|█████▌ | 15/27 [00:02<00:01, 6.08it/s] 59%|█████▉ | 16/27 [00:02<00:01, 6.08it/s] 63%|██████▎ | 17/27 [00:02<00:01, 6.09it/s] 67%|██████▋ | 18/27 [00:02<00:01, 6.10it/s] 70%|███████ | 19/27 [00:03<00:01, 6.10it/s] 74%|███████▍ | 20/27 [00:03<00:01, 6.10it/s] 78%|███████▊ | 21/27 [00:03<00:00, 6.11it/s] 81%|████████▏ | 22/27 [00:03<00:00, 6.11it/s] 85%|████████▌ | 23/27 [00:03<00:00, 6.11it/s] 89%|████████▉ | 24/27 [00:03<00:00, 6.11it/s] 93%|█████████▎| 25/27 [00:04<00:00, 6.11it/s] 96%|█████████▋| 26/27 [00:04<00:00, 6.11it/s] 100%|██████████| 27/27 [00:04<00:00, 6.11it/s] 100%|██████████| 27/27 [00:04<00:00, 6.10it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 6.80it/s] 67%|██████▋ | 2/3 [00:00<00:00, 7.25it/s] 100%|██████████| 3/3 [00:00<00:00, 7.40it/s] 100%|██████████| 3/3 [00:00<00:00, 7.30it/s]
Prediction
fofr/sdxl-xmas-sweater:0690f6c650d0899dcdeaf789d33cf86bad646a00d5efe7b7600998f2950705dbIDbgz26sdbbtehqt3g66nz2sfljuStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 768
- height
- 768
- prompt
- A photo of a TOK sweater, city skyline
- 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
- prompt_strength
- 0.8
- num_inference_steps
- 30
{ "width": 768, "height": 768, "prompt": "A photo of a TOK sweater, city skyline", "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": "", "prompt_strength": 0.8, "num_inference_steps": 30 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run fofr/sdxl-xmas-sweater using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-xmas-sweater:0690f6c650d0899dcdeaf789d33cf86bad646a00d5efe7b7600998f2950705db", { input: { width: 768, height: 768, prompt: "A photo of a TOK sweater, city skyline", 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: "", prompt_strength: 0.8, num_inference_steps: 30 } } ); // 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 replicate
Import the client:import replicate
Run fofr/sdxl-xmas-sweater using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-xmas-sweater:0690f6c650d0899dcdeaf789d33cf86bad646a00d5efe7b7600998f2950705db", input={ "width": 768, "height": 768, "prompt": "A photo of a TOK sweater, city skyline", "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": "", "prompt_strength": 0.8, "num_inference_steps": 30 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run fofr/sdxl-xmas-sweater 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-xmas-sweater:0690f6c650d0899dcdeaf789d33cf86bad646a00d5efe7b7600998f2950705db", "input": { "width": 768, "height": 768, "prompt": "A photo of a TOK sweater, city skyline", "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": "", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-12-03T21:33:38.319855Z", "created_at": "2023-12-03T21:33:26.608673Z", "data_removed": false, "error": null, "id": "bgz26sdbbtehqt3g66nz2sflju", "input": { "width": 768, "height": 768, "prompt": "A photo of a TOK sweater, city skyline", "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": "", "prompt_strength": 0.8, "num_inference_steps": 30 }, "logs": "Using seed: 40840\nEnsuring enough disk space...\nFree disk space: 1461308792832\nDownloading weights: https://replicate.delivery/pbxt/uSerlhyRLxz5fUKP2sXU3RhukmHeeFiUVM0WTB5mvNNlbF4HB/trained_model.tar\nb'Downloaded 186 MB bytes in 0.073s (2.5 GB/s)\\nExtracted 186 MB in 0.063s (2.9 GB/s)\\n'\nDownloaded weights in 0.2544443607330322 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A photo of a <s0><s1> sweater, city skyline\ntxt2img mode\n 0%| | 0/27 [00:00<?, ?it/s]\n 4%|▎ | 1/27 [00:00<00:04, 6.25it/s]\n 7%|▋ | 2/27 [00:00<00:04, 6.24it/s]\n 11%|█ | 3/27 [00:00<00:03, 6.23it/s]\n 15%|█▍ | 4/27 [00:00<00:03, 6.22it/s]\n 19%|█▊ | 5/27 [00:00<00:03, 6.22it/s]\n 22%|██▏ | 6/27 [00:00<00:03, 6.22it/s]\n 26%|██▌ | 7/27 [00:01<00:03, 6.22it/s]\n 30%|██▉ | 8/27 [00:01<00:03, 6.22it/s]\n 33%|███▎ | 9/27 [00:01<00:02, 6.22it/s]\n 37%|███▋ | 10/27 [00:01<00:02, 6.22it/s]\n 41%|████ | 11/27 [00:01<00:02, 6.22it/s]\n 44%|████▍ | 12/27 [00:01<00:02, 6.22it/s]\n 48%|████▊ | 13/27 [00:02<00:02, 6.22it/s]\n 52%|█████▏ | 14/27 [00:02<00:02, 6.22it/s]\n 56%|█████▌ | 15/27 [00:02<00:01, 6.21it/s]\n 59%|█████▉ | 16/27 [00:02<00:01, 6.21it/s]\n 63%|██████▎ | 17/27 [00:02<00:01, 6.21it/s]\n 67%|██████▋ | 18/27 [00:02<00:01, 6.21it/s]\n 70%|███████ | 19/27 [00:03<00:01, 6.22it/s]\n 74%|███████▍ | 20/27 [00:03<00:01, 6.21it/s]\n 78%|███████▊ | 21/27 [00:03<00:00, 6.20it/s]\n 81%|████████▏ | 22/27 [00:03<00:00, 6.20it/s]\n 85%|████████▌ | 23/27 [00:03<00:00, 6.20it/s]\n 89%|████████▉ | 24/27 [00:03<00:00, 6.20it/s]\n 93%|█████████▎| 25/27 [00:04<00:00, 6.20it/s]\n 96%|█████████▋| 26/27 [00:04<00:00, 6.21it/s]\n100%|██████████| 27/27 [00:04<00:00, 6.21it/s]\n100%|██████████| 27/27 [00:04<00:00, 6.21it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 6.91it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 7.39it/s]\n100%|██████████| 3/3 [00:00<00:00, 7.55it/s]\n100%|██████████| 3/3 [00:00<00:00, 7.45it/s]", "metrics": { "predict_time": 6.660678, "total_time": 11.711182 }, "output": [ "https://replicate.delivery/pbxt/YRKr8gAwfeqo007jYV45VW6gNXqN7vtyMtpoeFudsvuixU9jA/out-0.png" ], "started_at": "2023-12-03T21:33:31.659177Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/bgz26sdbbtehqt3g66nz2sflju", "cancel": "https://api.replicate.com/v1/predictions/bgz26sdbbtehqt3g66nz2sflju/cancel" }, "version": "0690f6c650d0899dcdeaf789d33cf86bad646a00d5efe7b7600998f2950705db" }
Generated inUsing seed: 40840 Ensuring enough disk space... Free disk space: 1461308792832 Downloading weights: https://replicate.delivery/pbxt/uSerlhyRLxz5fUKP2sXU3RhukmHeeFiUVM0WTB5mvNNlbF4HB/trained_model.tar b'Downloaded 186 MB bytes in 0.073s (2.5 GB/s)\nExtracted 186 MB in 0.063s (2.9 GB/s)\n' Downloaded weights in 0.2544443607330322 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A photo of a <s0><s1> sweater, city skyline txt2img mode 0%| | 0/27 [00:00<?, ?it/s] 4%|▎ | 1/27 [00:00<00:04, 6.25it/s] 7%|▋ | 2/27 [00:00<00:04, 6.24it/s] 11%|█ | 3/27 [00:00<00:03, 6.23it/s] 15%|█▍ | 4/27 [00:00<00:03, 6.22it/s] 19%|█▊ | 5/27 [00:00<00:03, 6.22it/s] 22%|██▏ | 6/27 [00:00<00:03, 6.22it/s] 26%|██▌ | 7/27 [00:01<00:03, 6.22it/s] 30%|██▉ | 8/27 [00:01<00:03, 6.22it/s] 33%|███▎ | 9/27 [00:01<00:02, 6.22it/s] 37%|███▋ | 10/27 [00:01<00:02, 6.22it/s] 41%|████ | 11/27 [00:01<00:02, 6.22it/s] 44%|████▍ | 12/27 [00:01<00:02, 6.22it/s] 48%|████▊ | 13/27 [00:02<00:02, 6.22it/s] 52%|█████▏ | 14/27 [00:02<00:02, 6.22it/s] 56%|█████▌ | 15/27 [00:02<00:01, 6.21it/s] 59%|█████▉ | 16/27 [00:02<00:01, 6.21it/s] 63%|██████▎ | 17/27 [00:02<00:01, 6.21it/s] 67%|██████▋ | 18/27 [00:02<00:01, 6.21it/s] 70%|███████ | 19/27 [00:03<00:01, 6.22it/s] 74%|███████▍ | 20/27 [00:03<00:01, 6.21it/s] 78%|███████▊ | 21/27 [00:03<00:00, 6.20it/s] 81%|████████▏ | 22/27 [00:03<00:00, 6.20it/s] 85%|████████▌ | 23/27 [00:03<00:00, 6.20it/s] 89%|████████▉ | 24/27 [00:03<00:00, 6.20it/s] 93%|█████████▎| 25/27 [00:04<00:00, 6.20it/s] 96%|█████████▋| 26/27 [00:04<00:00, 6.21it/s] 100%|██████████| 27/27 [00:04<00:00, 6.21it/s] 100%|██████████| 27/27 [00:04<00:00, 6.21it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 6.91it/s] 67%|██████▋ | 2/3 [00:00<00:00, 7.39it/s] 100%|██████████| 3/3 [00:00<00:00, 7.55it/s] 100%|██████████| 3/3 [00:00<00:00, 7.45it/s]
Prediction
fofr/sdxl-xmas-sweater:0690f6c650d0899dcdeaf789d33cf86bad646a00d5efe7b7600998f2950705dbIDcooocy3bp5kgbsprerwe7626oqStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 768
- height
- 768
- prompt
- A photo of a TOK sweater, polar bear funky dance
- 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
- prompt_strength
- 0.8
- num_inference_steps
- 30
{ "width": 768, "height": 768, "prompt": "A photo of a TOK sweater, polar bear funky dance", "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": "", "prompt_strength": 0.8, "num_inference_steps": 30 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run fofr/sdxl-xmas-sweater using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-xmas-sweater:0690f6c650d0899dcdeaf789d33cf86bad646a00d5efe7b7600998f2950705db", { input: { width: 768, height: 768, prompt: "A photo of a TOK sweater, polar bear funky dance", 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: "", prompt_strength: 0.8, num_inference_steps: 30 } } ); // 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 replicate
Import the client:import replicate
Run fofr/sdxl-xmas-sweater using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-xmas-sweater:0690f6c650d0899dcdeaf789d33cf86bad646a00d5efe7b7600998f2950705db", input={ "width": 768, "height": 768, "prompt": "A photo of a TOK sweater, polar bear funky dance", "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": "", "prompt_strength": 0.8, "num_inference_steps": 30 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run fofr/sdxl-xmas-sweater 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-xmas-sweater:0690f6c650d0899dcdeaf789d33cf86bad646a00d5efe7b7600998f2950705db", "input": { "width": 768, "height": 768, "prompt": "A photo of a TOK sweater, polar bear funky dance", "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": "", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-12-03T21:34:11.483151Z", "created_at": "2023-12-03T21:34:01.860725Z", "data_removed": false, "error": null, "id": "cooocy3bp5kgbsprerwe7626oq", "input": { "width": 768, "height": 768, "prompt": "A photo of a TOK sweater, polar bear funky dance", "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": "", "prompt_strength": 0.8, "num_inference_steps": 30 }, "logs": "Using seed: 2436\nEnsuring enough disk space...\nFree disk space: 1500900110336\nDownloading weights: https://replicate.delivery/pbxt/uSerlhyRLxz5fUKP2sXU3RhukmHeeFiUVM0WTB5mvNNlbF4HB/trained_model.tar\nb'Downloaded 186 MB bytes in 0.238s (781 MB/s)\\nExtracted 186 MB in 0.072s (2.6 GB/s)\\n'\nDownloaded weights in 0.5246114730834961 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A photo of a <s0><s1> sweater, polar bear funky dance\ntxt2img mode\n 0%| | 0/27 [00:00<?, ?it/s]\n 4%|▎ | 1/27 [00:00<00:04, 6.22it/s]\n 7%|▋ | 2/27 [00:00<00:04, 6.19it/s]\n 11%|█ | 3/27 [00:00<00:03, 6.20it/s]\n 15%|█▍ | 4/27 [00:00<00:03, 6.20it/s]\n 19%|█▊ | 5/27 [00:00<00:03, 6.20it/s]\n 22%|██▏ | 6/27 [00:00<00:03, 6.20it/s]\n 26%|██▌ | 7/27 [00:01<00:03, 6.20it/s]\n 30%|██▉ | 8/27 [00:01<00:03, 6.20it/s]\n 33%|███▎ | 9/27 [00:01<00:02, 6.20it/s]\n 37%|███▋ | 10/27 [00:01<00:02, 6.20it/s]\n 41%|████ | 11/27 [00:01<00:02, 6.20it/s]\n 44%|████▍ | 12/27 [00:01<00:02, 6.20it/s]\n 48%|████▊ | 13/27 [00:02<00:02, 6.19it/s]\n 52%|█████▏ | 14/27 [00:02<00:02, 6.19it/s]\n 56%|█████▌ | 15/27 [00:02<00:01, 6.18it/s]\n 59%|█████▉ | 16/27 [00:02<00:01, 6.18it/s]\n 63%|██████▎ | 17/27 [00:02<00:01, 6.18it/s]\n 67%|██████▋ | 18/27 [00:02<00:01, 6.19it/s]\n 70%|███████ | 19/27 [00:03<00:01, 6.19it/s]\n 74%|███████▍ | 20/27 [00:03<00:01, 6.20it/s]\n 78%|███████▊ | 21/27 [00:03<00:00, 6.20it/s]\n 81%|████████▏ | 22/27 [00:03<00:00, 6.20it/s]\n 85%|████████▌ | 23/27 [00:03<00:00, 6.20it/s]\n 89%|████████▉ | 24/27 [00:03<00:00, 6.20it/s]\n 93%|█████████▎| 25/27 [00:04<00:00, 6.20it/s]\n 96%|█████████▋| 26/27 [00:04<00:00, 6.19it/s]\n100%|██████████| 27/27 [00:04<00:00, 6.18it/s]\n100%|██████████| 27/27 [00:04<00:00, 6.19it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 6.78it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 7.27it/s]\n100%|██████████| 3/3 [00:00<00:00, 7.45it/s]\n100%|██████████| 3/3 [00:00<00:00, 7.34it/s]", "metrics": { "predict_time": 7.423663, "total_time": 9.622426 }, "output": [ "https://replicate.delivery/pbxt/AytpMn6GLM77H5sPdfZJUwyq0FIGdbZ2bfwUc4oEqHsSZqejA/out-0.png" ], "started_at": "2023-12-03T21:34:04.059488Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/cooocy3bp5kgbsprerwe7626oq", "cancel": "https://api.replicate.com/v1/predictions/cooocy3bp5kgbsprerwe7626oq/cancel" }, "version": "0690f6c650d0899dcdeaf789d33cf86bad646a00d5efe7b7600998f2950705db" }
Generated inUsing seed: 2436 Ensuring enough disk space... Free disk space: 1500900110336 Downloading weights: https://replicate.delivery/pbxt/uSerlhyRLxz5fUKP2sXU3RhukmHeeFiUVM0WTB5mvNNlbF4HB/trained_model.tar b'Downloaded 186 MB bytes in 0.238s (781 MB/s)\nExtracted 186 MB in 0.072s (2.6 GB/s)\n' Downloaded weights in 0.5246114730834961 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A photo of a <s0><s1> sweater, polar bear funky dance txt2img mode 0%| | 0/27 [00:00<?, ?it/s] 4%|▎ | 1/27 [00:00<00:04, 6.22it/s] 7%|▋ | 2/27 [00:00<00:04, 6.19it/s] 11%|█ | 3/27 [00:00<00:03, 6.20it/s] 15%|█▍ | 4/27 [00:00<00:03, 6.20it/s] 19%|█▊ | 5/27 [00:00<00:03, 6.20it/s] 22%|██▏ | 6/27 [00:00<00:03, 6.20it/s] 26%|██▌ | 7/27 [00:01<00:03, 6.20it/s] 30%|██▉ | 8/27 [00:01<00:03, 6.20it/s] 33%|███▎ | 9/27 [00:01<00:02, 6.20it/s] 37%|███▋ | 10/27 [00:01<00:02, 6.20it/s] 41%|████ | 11/27 [00:01<00:02, 6.20it/s] 44%|████▍ | 12/27 [00:01<00:02, 6.20it/s] 48%|████▊ | 13/27 [00:02<00:02, 6.19it/s] 52%|█████▏ | 14/27 [00:02<00:02, 6.19it/s] 56%|█████▌ | 15/27 [00:02<00:01, 6.18it/s] 59%|█████▉ | 16/27 [00:02<00:01, 6.18it/s] 63%|██████▎ | 17/27 [00:02<00:01, 6.18it/s] 67%|██████▋ | 18/27 [00:02<00:01, 6.19it/s] 70%|███████ | 19/27 [00:03<00:01, 6.19it/s] 74%|███████▍ | 20/27 [00:03<00:01, 6.20it/s] 78%|███████▊ | 21/27 [00:03<00:00, 6.20it/s] 81%|████████▏ | 22/27 [00:03<00:00, 6.20it/s] 85%|████████▌ | 23/27 [00:03<00:00, 6.20it/s] 89%|████████▉ | 24/27 [00:03<00:00, 6.20it/s] 93%|█████████▎| 25/27 [00:04<00:00, 6.20it/s] 96%|█████████▋| 26/27 [00:04<00:00, 6.19it/s] 100%|██████████| 27/27 [00:04<00:00, 6.18it/s] 100%|██████████| 27/27 [00:04<00:00, 6.19it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 6.78it/s] 67%|██████▋ | 2/3 [00:00<00:00, 7.27it/s] 100%|██████████| 3/3 [00:00<00:00, 7.45it/s] 100%|██████████| 3/3 [00:00<00:00, 7.34it/s]
Want to make some of these yourself?
Run this model