gileslerockeur
/
mbappe
Creates stunning images of the best soccer player in the world 💙🤍❤️
- Public
- 91 runs
-
L40S
- SDXL fine-tune
- GitHub
Prediction
gileslerockeur/mbappe:b838a04a475885971f77e3a58946f1e95c1519b2d53dbd361d4f09789c4bd450IDguwljetbiwrxasjy64lfyvcyhyStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- A photo of TOK, running on soccer field, wearing the white jersey of soccer team Real Madrid. close shot.
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.85
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.95
- negative_prompt
- PSG Paris Saint Germain Dark blue jersey
- prompt_strength
- 0.8
- num_inference_steps
- 100
{ "width": 1024, "height": 1024, "prompt": "A photo of TOK, running on soccer field, wearing the white jersey of soccer team Real Madrid. close shot.", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.85, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.95, "negative_prompt": "PSG\nParis Saint Germain\nDark blue jersey", "prompt_strength": 0.8, "num_inference_steps": 100 }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 gileslerockeur/mbappe using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "gileslerockeur/mbappe:b838a04a475885971f77e3a58946f1e95c1519b2d53dbd361d4f09789c4bd450", { input: { width: 1024, height: 1024, prompt: "A photo of TOK, running on soccer field, wearing the white jersey of soccer team Real Madrid. close shot.", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.85, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.95, negative_prompt: "PSG\nParis Saint Germain\nDark blue jersey", prompt_strength: 0.8, num_inference_steps: 100 } } ); // 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 gileslerockeur/mbappe using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "gileslerockeur/mbappe:b838a04a475885971f77e3a58946f1e95c1519b2d53dbd361d4f09789c4bd450", input={ "width": 1024, "height": 1024, "prompt": "A photo of TOK, running on soccer field, wearing the white jersey of soccer team Real Madrid. close shot.", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.85, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.95, "negative_prompt": "PSG\nParis Saint Germain\nDark blue jersey", "prompt_strength": 0.8, "num_inference_steps": 100 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run gileslerockeur/mbappe 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": "b838a04a475885971f77e3a58946f1e95c1519b2d53dbd361d4f09789c4bd450", "input": { "width": 1024, "height": 1024, "prompt": "A photo of TOK, running on soccer field, wearing the white jersey of soccer team Real Madrid. close shot.", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.85, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.95, "negative_prompt": "PSG\\nParis Saint Germain\\nDark blue jersey", "prompt_strength": 0.8, "num_inference_steps": 100 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-02-15T23:05:20.098382Z", "created_at": "2024-02-15T23:04:45.230786Z", "data_removed": false, "error": null, "id": "guwljetbiwrxasjy64lfyvcyhy", "input": { "width": 1024, "height": 1024, "prompt": "A photo of TOK, running on soccer field, wearing the white jersey of soccer team Real Madrid. close shot.", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.85, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.95, "negative_prompt": "PSG\nParis Saint Germain\nDark blue jersey", "prompt_strength": 0.8, "num_inference_steps": 100 }, "logs": "Using seed: 12659\nEnsuring enough disk space...\nFree disk space: 1585451642880\nDownloading weights: https://replicate.delivery/pbxt/YDOmKBNclz5bFpPC8mKcB6zUZHLjmbArJcxNYJnMHuXHBxlE/trained_model.tar\n2024-02-15T23:04:48Z | INFO | [ Initiating ] dest=/src/weights-cache/0eda00f750189c5b minimum_chunk_size=150M url=https://replicate.delivery/pbxt/YDOmKBNclz5bFpPC8mKcB6zUZHLjmbArJcxNYJnMHuXHBxlE/trained_model.tar\n2024-02-15T23:04:49Z | INFO | [ Complete ] dest=/src/weights-cache/0eda00f750189c5b size=\"186 MB\" total_elapsed=0.646s url=https://replicate.delivery/pbxt/YDOmKBNclz5bFpPC8mKcB6zUZHLjmbArJcxNYJnMHuXHBxlE/trained_model.tar\nb''\nDownloaded weights in 0.8245742321014404 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A photo of <s0><s1>, running on soccer field, wearing the white jersey of soccer team Real Madrid. close shot.\ntxt2img mode\n 0%| | 0/95 [00:00<?, ?it/s]\n 1%| | 1/95 [00:00<00:25, 3.69it/s]\n 2%|▏ | 2/95 [00:00<00:25, 3.68it/s]\n 3%|▎ | 3/95 [00:00<00:25, 3.68it/s]\n 4%|▍ | 4/95 [00:01<00:24, 3.67it/s]\n 5%|▌ | 5/95 [00:01<00:24, 3.67it/s]\n 6%|▋ | 6/95 [00:01<00:24, 3.68it/s]\n 7%|▋ | 7/95 [00:01<00:23, 3.68it/s]\n 8%|▊ | 8/95 [00:02<00:23, 3.67it/s]\n 9%|▉ | 9/95 [00:02<00:23, 3.67it/s]\n 11%|█ | 10/95 [00:02<00:23, 3.67it/s]\n 12%|█▏ | 11/95 [00:02<00:22, 3.67it/s]\n 13%|█▎ | 12/95 [00:03<00:22, 3.67it/s]\n 14%|█▎ | 13/95 [00:03<00:22, 3.67it/s]\n 15%|█▍ | 14/95 [00:03<00:22, 3.67it/s]\n 16%|█▌ | 15/95 [00:04<00:21, 3.67it/s]\n 17%|█▋ | 16/95 [00:04<00:21, 3.67it/s]\n 18%|█▊ | 17/95 [00:04<00:21, 3.67it/s]\n 19%|█▉ | 18/95 [00:04<00:20, 3.67it/s]\n 20%|██ | 19/95 [00:05<00:20, 3.67it/s]\n 21%|██ | 20/95 [00:05<00:20, 3.67it/s]\n 22%|██▏ | 21/95 [00:05<00:20, 3.66it/s]\n 23%|██▎ | 22/95 [00:05<00:19, 3.66it/s]\n 24%|██▍ | 23/95 [00:06<00:19, 3.66it/s]\n 25%|██▌ | 24/95 [00:06<00:19, 3.66it/s]\n 26%|██▋ | 25/95 [00:06<00:19, 3.66it/s]\n 27%|██▋ | 26/95 [00:07<00:18, 3.66it/s]\n 28%|██▊ | 27/95 [00:07<00:18, 3.66it/s]\n 29%|██▉ | 28/95 [00:07<00:18, 3.66it/s]\n 31%|███ | 29/95 [00:07<00:18, 3.66it/s]\n 32%|███▏ | 30/95 [00:08<00:17, 3.66it/s]\n 33%|███▎ | 31/95 [00:08<00:17, 3.65it/s]\n 34%|███▎ | 32/95 [00:08<00:17, 3.66it/s]\n 35%|███▍ | 33/95 [00:09<00:16, 3.65it/s]\n 36%|███▌ | 34/95 [00:09<00:16, 3.65it/s]\n 37%|███▋ | 35/95 [00:09<00:16, 3.65it/s]\n 38%|███▊ | 36/95 [00:09<00:16, 3.65it/s]\n 39%|███▉ | 37/95 [00:10<00:15, 3.65it/s]\n 40%|████ | 38/95 [00:10<00:15, 3.65it/s]\n 41%|████ | 39/95 [00:10<00:15, 3.65it/s]\n 42%|████▏ | 40/95 [00:10<00:15, 3.65it/s]\n 43%|████▎ | 41/95 [00:11<00:14, 3.65it/s]\n 44%|████▍ | 42/95 [00:11<00:14, 3.65it/s]\n 45%|████▌ | 43/95 [00:11<00:14, 3.65it/s]\n 46%|████▋ | 44/95 [00:12<00:13, 3.65it/s]\n 47%|████▋ | 45/95 [00:12<00:13, 3.65it/s]\n 48%|████▊ | 46/95 [00:12<00:13, 3.65it/s]\n 49%|████▉ | 47/95 [00:12<00:13, 3.65it/s]\n 51%|█████ | 48/95 [00:13<00:12, 3.65it/s]\n 52%|█████▏ | 49/95 [00:13<00:12, 3.65it/s]\n 53%|█████▎ | 50/95 [00:13<00:12, 3.65it/s]\n 54%|█████▎ | 51/95 [00:13<00:12, 3.65it/s]\n 55%|█████▍ | 52/95 [00:14<00:11, 3.64it/s]\n 56%|█████▌ | 53/95 [00:14<00:11, 3.64it/s]\n 57%|█████▋ | 54/95 [00:14<00:11, 3.65it/s]\n 58%|█████▊ | 55/95 [00:15<00:10, 3.65it/s]\n 59%|█████▉ | 56/95 [00:15<00:10, 3.64it/s]\n 60%|██████ | 57/95 [00:15<00:10, 3.64it/s]\n 61%|██████ | 58/95 [00:15<00:10, 3.64it/s]\n 62%|██████▏ | 59/95 [00:16<00:09, 3.64it/s]\n 63%|██████▎ | 60/95 [00:16<00:09, 3.65it/s]\n 64%|██████▍ | 61/95 [00:16<00:09, 3.64it/s]\n 65%|██████▌ | 62/95 [00:16<00:09, 3.64it/s]\n 66%|██████▋ | 63/95 [00:17<00:08, 3.64it/s]\n 67%|██████▋ | 64/95 [00:17<00:08, 3.64it/s]\n 68%|██████▊ | 65/95 [00:17<00:08, 3.64it/s]\n 69%|██████▉ | 66/95 [00:18<00:07, 3.64it/s]\n 71%|███████ | 67/95 [00:18<00:07, 3.64it/s]\n 72%|███████▏ | 68/95 [00:18<00:07, 3.64it/s]\n 73%|███████▎ | 69/95 [00:18<00:07, 3.64it/s]\n 74%|███████▎ | 70/95 [00:19<00:06, 3.64it/s]\n 75%|███████▍ | 71/95 [00:19<00:06, 3.64it/s]\n 76%|███████▌ | 72/95 [00:19<00:06, 3.64it/s]\n 77%|███████▋ | 73/95 [00:19<00:06, 3.64it/s]\n 78%|███████▊ | 74/95 [00:20<00:05, 3.64it/s]\n 79%|███████▉ | 75/95 [00:20<00:05, 3.64it/s]\n 80%|████████ | 76/95 [00:20<00:05, 3.64it/s]\n 81%|████████ | 77/95 [00:21<00:04, 3.64it/s]\n 82%|████████▏ | 78/95 [00:21<00:04, 3.63it/s]\n 83%|████████▎ | 79/95 [00:21<00:04, 3.64it/s]\n 84%|████████▍ | 80/95 [00:21<00:04, 3.64it/s]\n 85%|████████▌ | 81/95 [00:22<00:03, 3.64it/s]\n 86%|████████▋ | 82/95 [00:22<00:03, 3.64it/s]\n 87%|████████▋ | 83/95 [00:22<00:03, 3.63it/s]\n 88%|████████▊ | 84/95 [00:23<00:03, 3.63it/s]\n 89%|████████▉ | 85/95 [00:23<00:02, 3.64it/s]\n 91%|█████████ | 86/95 [00:23<00:02, 3.64it/s]\n 92%|█████████▏| 87/95 [00:23<00:02, 3.64it/s]\n 93%|█████████▎| 88/95 [00:24<00:01, 3.64it/s]\n 94%|█████████▎| 89/95 [00:24<00:01, 3.64it/s]\n 95%|█████████▍| 90/95 [00:24<00:01, 3.64it/s]\n 96%|█████████▌| 91/95 [00:24<00:01, 3.64it/s]\n 97%|█████████▋| 92/95 [00:25<00:00, 3.64it/s]\n 98%|█████████▊| 93/95 [00:25<00:00, 3.64it/s]\n 99%|█████████▉| 94/95 [00:25<00:00, 3.64it/s]\n100%|██████████| 95/95 [00:26<00:00, 3.64it/s]\n100%|██████████| 95/95 [00:26<00:00, 3.65it/s]\n 0%| | 0/5 [00:00<?, ?it/s]\n 20%|██ | 1/5 [00:00<00:00, 4.25it/s]\n 40%|████ | 2/5 [00:00<00:00, 4.22it/s]\n 60%|██████ | 3/5 [00:00<00:00, 4.21it/s]\n 80%|████████ | 4/5 [00:00<00:00, 4.21it/s]\n100%|██████████| 5/5 [00:01<00:00, 4.20it/s]\n100%|██████████| 5/5 [00:01<00:00, 4.21it/s]", "metrics": { "predict_time": 31.235973, "total_time": 34.867596 }, "output": [ "https://replicate.delivery/pbxt/OvDwcCq58YJIM5xf0JsKtlXUdrlcw9lM14q7n8AejPuuqEXSA/out-0.png" ], "started_at": "2024-02-15T23:04:48.862409Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/guwljetbiwrxasjy64lfyvcyhy", "cancel": "https://api.replicate.com/v1/predictions/guwljetbiwrxasjy64lfyvcyhy/cancel" }, "version": "b838a04a475885971f77e3a58946f1e95c1519b2d53dbd361d4f09789c4bd450" }Generated inUsing seed: 12659 Ensuring enough disk space... Free disk space: 1585451642880 Downloading weights: https://replicate.delivery/pbxt/YDOmKBNclz5bFpPC8mKcB6zUZHLjmbArJcxNYJnMHuXHBxlE/trained_model.tar 2024-02-15T23:04:48Z | INFO | [ Initiating ] dest=/src/weights-cache/0eda00f750189c5b minimum_chunk_size=150M url=https://replicate.delivery/pbxt/YDOmKBNclz5bFpPC8mKcB6zUZHLjmbArJcxNYJnMHuXHBxlE/trained_model.tar 2024-02-15T23:04:49Z | INFO | [ Complete ] dest=/src/weights-cache/0eda00f750189c5b size="186 MB" total_elapsed=0.646s url=https://replicate.delivery/pbxt/YDOmKBNclz5bFpPC8mKcB6zUZHLjmbArJcxNYJnMHuXHBxlE/trained_model.tar b'' Downloaded weights in 0.8245742321014404 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A photo of <s0><s1>, running on soccer field, wearing the white jersey of soccer team Real Madrid. close shot. txt2img mode 0%| | 0/95 [00:00<?, ?it/s] 1%| | 1/95 [00:00<00:25, 3.69it/s] 2%|▏ | 2/95 [00:00<00:25, 3.68it/s] 3%|▎ | 3/95 [00:00<00:25, 3.68it/s] 4%|▍ | 4/95 [00:01<00:24, 3.67it/s] 5%|▌ | 5/95 [00:01<00:24, 3.67it/s] 6%|▋ | 6/95 [00:01<00:24, 3.68it/s] 7%|▋ | 7/95 [00:01<00:23, 3.68it/s] 8%|▊ | 8/95 [00:02<00:23, 3.67it/s] 9%|▉ | 9/95 [00:02<00:23, 3.67it/s] 11%|█ | 10/95 [00:02<00:23, 3.67it/s] 12%|█▏ | 11/95 [00:02<00:22, 3.67it/s] 13%|█▎ | 12/95 [00:03<00:22, 3.67it/s] 14%|█▎ | 13/95 [00:03<00:22, 3.67it/s] 15%|█▍ | 14/95 [00:03<00:22, 3.67it/s] 16%|█▌ | 15/95 [00:04<00:21, 3.67it/s] 17%|█▋ | 16/95 [00:04<00:21, 3.67it/s] 18%|█▊ | 17/95 [00:04<00:21, 3.67it/s] 19%|█▉ | 18/95 [00:04<00:20, 3.67it/s] 20%|██ | 19/95 [00:05<00:20, 3.67it/s] 21%|██ | 20/95 [00:05<00:20, 3.67it/s] 22%|██▏ | 21/95 [00:05<00:20, 3.66it/s] 23%|██▎ | 22/95 [00:05<00:19, 3.66it/s] 24%|██▍ | 23/95 [00:06<00:19, 3.66it/s] 25%|██▌ | 24/95 [00:06<00:19, 3.66it/s] 26%|██▋ | 25/95 [00:06<00:19, 3.66it/s] 27%|██▋ | 26/95 [00:07<00:18, 3.66it/s] 28%|██▊ | 27/95 [00:07<00:18, 3.66it/s] 29%|██▉ | 28/95 [00:07<00:18, 3.66it/s] 31%|███ | 29/95 [00:07<00:18, 3.66it/s] 32%|███▏ | 30/95 [00:08<00:17, 3.66it/s] 33%|███▎ | 31/95 [00:08<00:17, 3.65it/s] 34%|███▎ | 32/95 [00:08<00:17, 3.66it/s] 35%|███▍ | 33/95 [00:09<00:16, 3.65it/s] 36%|███▌ | 34/95 [00:09<00:16, 3.65it/s] 37%|███▋ | 35/95 [00:09<00:16, 3.65it/s] 38%|███▊ | 36/95 [00:09<00:16, 3.65it/s] 39%|███▉ | 37/95 [00:10<00:15, 3.65it/s] 40%|████ | 38/95 [00:10<00:15, 3.65it/s] 41%|████ | 39/95 [00:10<00:15, 3.65it/s] 42%|████▏ | 40/95 [00:10<00:15, 3.65it/s] 43%|████▎ | 41/95 [00:11<00:14, 3.65it/s] 44%|████▍ | 42/95 [00:11<00:14, 3.65it/s] 45%|████▌ | 43/95 [00:11<00:14, 3.65it/s] 46%|████▋ | 44/95 [00:12<00:13, 3.65it/s] 47%|████▋ | 45/95 [00:12<00:13, 3.65it/s] 48%|████▊ | 46/95 [00:12<00:13, 3.65it/s] 49%|████▉ | 47/95 [00:12<00:13, 3.65it/s] 51%|█████ | 48/95 [00:13<00:12, 3.65it/s] 52%|█████▏ | 49/95 [00:13<00:12, 3.65it/s] 53%|█████▎ | 50/95 [00:13<00:12, 3.65it/s] 54%|█████▎ | 51/95 [00:13<00:12, 3.65it/s] 55%|█████▍ | 52/95 [00:14<00:11, 3.64it/s] 56%|█████▌ | 53/95 [00:14<00:11, 3.64it/s] 57%|█████▋ | 54/95 [00:14<00:11, 3.65it/s] 58%|█████▊ | 55/95 [00:15<00:10, 3.65it/s] 59%|█████▉ | 56/95 [00:15<00:10, 3.64it/s] 60%|██████ | 57/95 [00:15<00:10, 3.64it/s] 61%|██████ | 58/95 [00:15<00:10, 3.64it/s] 62%|██████▏ | 59/95 [00:16<00:09, 3.64it/s] 63%|██████▎ | 60/95 [00:16<00:09, 3.65it/s] 64%|██████▍ | 61/95 [00:16<00:09, 3.64it/s] 65%|██████▌ | 62/95 [00:16<00:09, 3.64it/s] 66%|██████▋ | 63/95 [00:17<00:08, 3.64it/s] 67%|██████▋ | 64/95 [00:17<00:08, 3.64it/s] 68%|██████▊ | 65/95 [00:17<00:08, 3.64it/s] 69%|██████▉ | 66/95 [00:18<00:07, 3.64it/s] 71%|███████ | 67/95 [00:18<00:07, 3.64it/s] 72%|███████▏ | 68/95 [00:18<00:07, 3.64it/s] 73%|███████▎ | 69/95 [00:18<00:07, 3.64it/s] 74%|███████▎ | 70/95 [00:19<00:06, 3.64it/s] 75%|███████▍ | 71/95 [00:19<00:06, 3.64it/s] 76%|███████▌ | 72/95 [00:19<00:06, 3.64it/s] 77%|███████▋ | 73/95 [00:19<00:06, 3.64it/s] 78%|███████▊ | 74/95 [00:20<00:05, 3.64it/s] 79%|███████▉ | 75/95 [00:20<00:05, 3.64it/s] 80%|████████ | 76/95 [00:20<00:05, 3.64it/s] 81%|████████ | 77/95 [00:21<00:04, 3.64it/s] 82%|████████▏ | 78/95 [00:21<00:04, 3.63it/s] 83%|████████▎ | 79/95 [00:21<00:04, 3.64it/s] 84%|████████▍ | 80/95 [00:21<00:04, 3.64it/s] 85%|████████▌ | 81/95 [00:22<00:03, 3.64it/s] 86%|████████▋ | 82/95 [00:22<00:03, 3.64it/s] 87%|████████▋ | 83/95 [00:22<00:03, 3.63it/s] 88%|████████▊ | 84/95 [00:23<00:03, 3.63it/s] 89%|████████▉ | 85/95 [00:23<00:02, 3.64it/s] 91%|█████████ | 86/95 [00:23<00:02, 3.64it/s] 92%|█████████▏| 87/95 [00:23<00:02, 3.64it/s] 93%|█████████▎| 88/95 [00:24<00:01, 3.64it/s] 94%|█████████▎| 89/95 [00:24<00:01, 3.64it/s] 95%|█████████▍| 90/95 [00:24<00:01, 3.64it/s] 96%|█████████▌| 91/95 [00:24<00:01, 3.64it/s] 97%|█████████▋| 92/95 [00:25<00:00, 3.64it/s] 98%|█████████▊| 93/95 [00:25<00:00, 3.64it/s] 99%|█████████▉| 94/95 [00:25<00:00, 3.64it/s] 100%|██████████| 95/95 [00:26<00:00, 3.64it/s] 100%|██████████| 95/95 [00:26<00:00, 3.65it/s] 0%| | 0/5 [00:00<?, ?it/s] 20%|██ | 1/5 [00:00<00:00, 4.25it/s] 40%|████ | 2/5 [00:00<00:00, 4.22it/s] 60%|██████ | 3/5 [00:00<00:00, 4.21it/s] 80%|████████ | 4/5 [00:00<00:00, 4.21it/s] 100%|██████████| 5/5 [00:01<00:00, 4.20it/s] 100%|██████████| 5/5 [00:01<00:00, 4.21it/s]Prediction
gileslerockeur/mbappe:b838a04a475885971f77e3a58946f1e95c1519b2d53dbd361d4f09789c4bd450IDxkghr3lbh2xf3hxoweu53rsdxyStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- A photo of TOK, in press room, wearing a tuxedo.
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.85
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.95
- negative_prompt
- PSG Paris Saint Germain Dark blue jersey
- prompt_strength
- 0.8
- num_inference_steps
- 100
{ "width": 1024, "height": 1024, "prompt": "A photo of TOK, in press room, wearing a tuxedo.", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.85, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.95, "negative_prompt": "PSG\nParis Saint Germain\nDark blue jersey", "prompt_strength": 0.8, "num_inference_steps": 100 }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 gileslerockeur/mbappe using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "gileslerockeur/mbappe:b838a04a475885971f77e3a58946f1e95c1519b2d53dbd361d4f09789c4bd450", { input: { width: 1024, height: 1024, prompt: "A photo of TOK, in press room, wearing a tuxedo.", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.85, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.95, negative_prompt: "PSG\nParis Saint Germain\nDark blue jersey", prompt_strength: 0.8, num_inference_steps: 100 } } ); // 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 gileslerockeur/mbappe using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "gileslerockeur/mbappe:b838a04a475885971f77e3a58946f1e95c1519b2d53dbd361d4f09789c4bd450", input={ "width": 1024, "height": 1024, "prompt": "A photo of TOK, in press room, wearing a tuxedo.", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.85, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.95, "negative_prompt": "PSG\nParis Saint Germain\nDark blue jersey", "prompt_strength": 0.8, "num_inference_steps": 100 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run gileslerockeur/mbappe 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": "b838a04a475885971f77e3a58946f1e95c1519b2d53dbd361d4f09789c4bd450", "input": { "width": 1024, "height": 1024, "prompt": "A photo of TOK, in press room, wearing a tuxedo.", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.85, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.95, "negative_prompt": "PSG\\nParis Saint Germain\\nDark blue jersey", "prompt_strength": 0.8, "num_inference_steps": 100 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-02-15T23:07:05.950861Z", "created_at": "2024-02-15T23:06:31.288555Z", "data_removed": false, "error": null, "id": "xkghr3lbh2xf3hxoweu53rsdxy", "input": { "width": 1024, "height": 1024, "prompt": "A photo of TOK, in press room, wearing a tuxedo.", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.85, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.95, "negative_prompt": "PSG\nParis Saint Germain\nDark blue jersey", "prompt_strength": 0.8, "num_inference_steps": 100 }, "logs": "Using seed: 17059\nEnsuring enough disk space...\nFree disk space: 2127447154688\nDownloading weights: https://replicate.delivery/pbxt/YDOmKBNclz5bFpPC8mKcB6zUZHLjmbArJcxNYJnMHuXHBxlE/trained_model.tar\n2024-02-15T23:06:34Z | INFO | [ Initiating ] dest=/src/weights-cache/0eda00f750189c5b minimum_chunk_size=150M url=https://replicate.delivery/pbxt/YDOmKBNclz5bFpPC8mKcB6zUZHLjmbArJcxNYJnMHuXHBxlE/trained_model.tar\n2024-02-15T23:06:35Z | INFO | [ Complete ] dest=/src/weights-cache/0eda00f750189c5b size=\"186 MB\" total_elapsed=0.591s url=https://replicate.delivery/pbxt/YDOmKBNclz5bFpPC8mKcB6zUZHLjmbArJcxNYJnMHuXHBxlE/trained_model.tar\nb''\nDownloaded weights in 0.7422995567321777 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A photo of <s0><s1>, in press room, wearing a tuxedo.\ntxt2img mode\n 0%| | 0/95 [00:00<?, ?it/s]\n 1%| | 1/95 [00:00<00:25, 3.69it/s]\n 2%|▏ | 2/95 [00:00<00:25, 3.67it/s]\n 3%|▎ | 3/95 [00:00<00:25, 3.66it/s]\n 4%|▍ | 4/95 [00:01<00:24, 3.65it/s]\n 5%|▌ | 5/95 [00:01<00:24, 3.65it/s]\n 6%|▋ | 6/95 [00:01<00:24, 3.64it/s]\n 7%|▋ | 7/95 [00:01<00:24, 3.64it/s]\n 8%|▊ | 8/95 [00:02<00:23, 3.65it/s]\n 9%|▉ | 9/95 [00:02<00:23, 3.64it/s]\n 11%|█ | 10/95 [00:02<00:23, 3.65it/s]\n 12%|█▏ | 11/95 [00:03<00:22, 3.66it/s]\n 13%|█▎ | 12/95 [00:03<00:22, 3.66it/s]\n 14%|█▎ | 13/95 [00:03<00:22, 3.66it/s]\n 15%|█▍ | 14/95 [00:03<00:22, 3.66it/s]\n 16%|█▌ | 15/95 [00:04<00:21, 3.66it/s]\n 17%|█▋ | 16/95 [00:04<00:21, 3.66it/s]\n 18%|█▊ | 17/95 [00:04<00:21, 3.66it/s]\n 19%|█▉ | 18/95 [00:04<00:21, 3.66it/s]\n 20%|██ | 19/95 [00:05<00:20, 3.66it/s]\n 21%|██ | 20/95 [00:05<00:20, 3.66it/s]\n 22%|██▏ | 21/95 [00:05<00:20, 3.66it/s]\n 23%|██▎ | 22/95 [00:06<00:19, 3.66it/s]\n 24%|██▍ | 23/95 [00:06<00:19, 3.65it/s]\n 25%|██▌ | 24/95 [00:06<00:19, 3.65it/s]\n 26%|██▋ | 25/95 [00:06<00:19, 3.65it/s]\n 27%|██▋ | 26/95 [00:07<00:18, 3.65it/s]\n 28%|██▊ | 27/95 [00:07<00:18, 3.65it/s]\n 29%|██▉ | 28/95 [00:07<00:18, 3.65it/s]\n 31%|███ | 29/95 [00:07<00:18, 3.65it/s]\n 32%|███▏ | 30/95 [00:08<00:17, 3.65it/s]\n 33%|███▎ | 31/95 [00:08<00:17, 3.65it/s]\n 34%|███▎ | 32/95 [00:08<00:17, 3.65it/s]\n 35%|███▍ | 33/95 [00:09<00:16, 3.65it/s]\n 36%|███▌ | 34/95 [00:09<00:16, 3.65it/s]\n 37%|███▋ | 35/95 [00:09<00:16, 3.65it/s]\n 38%|███▊ | 36/95 [00:09<00:16, 3.66it/s]\n 39%|███▉ | 37/95 [00:10<00:15, 3.66it/s]\n 40%|████ | 38/95 [00:10<00:15, 3.65it/s]\n 41%|████ | 39/95 [00:10<00:15, 3.65it/s]\n 42%|████▏ | 40/95 [00:10<00:15, 3.66it/s]\n 43%|████▎ | 41/95 [00:11<00:14, 3.65it/s]\n 44%|████▍ | 42/95 [00:11<00:14, 3.65it/s]\n 45%|████▌ | 43/95 [00:11<00:14, 3.65it/s]\n 46%|████▋ | 44/95 [00:12<00:13, 3.65it/s]\n 47%|████▋ | 45/95 [00:12<00:13, 3.65it/s]\n 48%|████▊ | 46/95 [00:12<00:13, 3.65it/s]\n 49%|████▉ | 47/95 [00:12<00:13, 3.65it/s]\n 51%|█████ | 48/95 [00:13<00:12, 3.65it/s]\n 52%|█████▏ | 49/95 [00:13<00:12, 3.65it/s]\n 53%|█████▎ | 50/95 [00:13<00:12, 3.65it/s]\n 54%|█████▎ | 51/95 [00:13<00:12, 3.65it/s]\n 55%|█████▍ | 52/95 [00:14<00:11, 3.65it/s]\n 56%|█████▌ | 53/95 [00:14<00:11, 3.64it/s]\n 57%|█████▋ | 54/95 [00:14<00:11, 3.64it/s]\n 58%|█████▊ | 55/95 [00:15<00:10, 3.64it/s]\n 59%|█████▉ | 56/95 [00:15<00:10, 3.64it/s]\n 60%|██████ | 57/95 [00:15<00:10, 3.64it/s]\n 61%|██████ | 58/95 [00:15<00:10, 3.64it/s]\n 62%|██████▏ | 59/95 [00:16<00:09, 3.64it/s]\n 63%|██████▎ | 60/95 [00:16<00:09, 3.63it/s]\n 64%|██████▍ | 61/95 [00:16<00:09, 3.64it/s]\n 65%|██████▌ | 62/95 [00:16<00:09, 3.64it/s]\n 66%|██████▋ | 63/95 [00:17<00:08, 3.64it/s]\n 67%|██████▋ | 64/95 [00:17<00:08, 3.64it/s]\n 68%|██████▊ | 65/95 [00:17<00:08, 3.64it/s]\n 69%|██████▉ | 66/95 [00:18<00:07, 3.64it/s]\n 71%|███████ | 67/95 [00:18<00:07, 3.64it/s]\n 72%|███████▏ | 68/95 [00:18<00:07, 3.63it/s]\n 73%|███████▎ | 69/95 [00:18<00:07, 3.64it/s]\n 74%|███████▎ | 70/95 [00:19<00:06, 3.64it/s]\n 75%|███████▍ | 71/95 [00:19<00:06, 3.63it/s]\n 76%|███████▌ | 72/95 [00:19<00:06, 3.63it/s]\n 77%|███████▋ | 73/95 [00:20<00:06, 3.63it/s]\n 78%|███████▊ | 74/95 [00:20<00:05, 3.63it/s]\n 79%|███████▉ | 75/95 [00:20<00:05, 3.63it/s]\n 80%|████████ | 76/95 [00:20<00:05, 3.63it/s]\n 81%|████████ | 77/95 [00:21<00:04, 3.63it/s]\n 82%|████████▏ | 78/95 [00:21<00:04, 3.63it/s]\n 83%|████████▎ | 79/95 [00:21<00:04, 3.63it/s]\n 84%|████████▍ | 80/95 [00:21<00:04, 3.63it/s]\n 85%|████████▌ | 81/95 [00:22<00:03, 3.63it/s]\n 86%|████████▋ | 82/95 [00:22<00:03, 3.63it/s]\n 87%|████████▋ | 83/95 [00:22<00:03, 3.63it/s]\n 88%|████████▊ | 84/95 [00:23<00:03, 3.63it/s]\n 89%|████████▉ | 85/95 [00:23<00:02, 3.63it/s]\n 91%|█████████ | 86/95 [00:23<00:02, 3.63it/s]\n 92%|█████████▏| 87/95 [00:23<00:02, 3.63it/s]\n 93%|█████████▎| 88/95 [00:24<00:01, 3.63it/s]\n 94%|█████████▎| 89/95 [00:24<00:01, 3.63it/s]\n 95%|█████████▍| 90/95 [00:24<00:01, 3.62it/s]\n 96%|█████████▌| 91/95 [00:24<00:01, 3.62it/s]\n 97%|█████████▋| 92/95 [00:25<00:00, 3.63it/s]\n 98%|█████████▊| 93/95 [00:25<00:00, 3.62it/s]\n 99%|█████████▉| 94/95 [00:25<00:00, 3.63it/s]\n100%|██████████| 95/95 [00:26<00:00, 3.63it/s]\n100%|██████████| 95/95 [00:26<00:00, 3.64it/s]\n 0%| | 0/5 [00:00<?, ?it/s]\n 20%|██ | 1/5 [00:00<00:00, 4.22it/s]\n 40%|████ | 2/5 [00:00<00:00, 4.20it/s]\n 60%|██████ | 3/5 [00:00<00:00, 4.19it/s]\n 80%|████████ | 4/5 [00:00<00:00, 4.19it/s]\n100%|██████████| 5/5 [00:01<00:00, 4.19it/s]\n100%|██████████| 5/5 [00:01<00:00, 4.19it/s]", "metrics": { "predict_time": 31.086349, "total_time": 34.662306 }, "output": [ "https://replicate.delivery/pbxt/bPVm216kseUNBys5XexqEufVwLPw158fiR5j9J6qB8ShxScJB/out-0.png" ], "started_at": "2024-02-15T23:06:34.864512Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/xkghr3lbh2xf3hxoweu53rsdxy", "cancel": "https://api.replicate.com/v1/predictions/xkghr3lbh2xf3hxoweu53rsdxy/cancel" }, "version": "b838a04a475885971f77e3a58946f1e95c1519b2d53dbd361d4f09789c4bd450" }Generated inUsing seed: 17059 Ensuring enough disk space... Free disk space: 2127447154688 Downloading weights: https://replicate.delivery/pbxt/YDOmKBNclz5bFpPC8mKcB6zUZHLjmbArJcxNYJnMHuXHBxlE/trained_model.tar 2024-02-15T23:06:34Z | INFO | [ Initiating ] dest=/src/weights-cache/0eda00f750189c5b minimum_chunk_size=150M url=https://replicate.delivery/pbxt/YDOmKBNclz5bFpPC8mKcB6zUZHLjmbArJcxNYJnMHuXHBxlE/trained_model.tar 2024-02-15T23:06:35Z | INFO | [ Complete ] dest=/src/weights-cache/0eda00f750189c5b size="186 MB" total_elapsed=0.591s url=https://replicate.delivery/pbxt/YDOmKBNclz5bFpPC8mKcB6zUZHLjmbArJcxNYJnMHuXHBxlE/trained_model.tar b'' Downloaded weights in 0.7422995567321777 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A photo of <s0><s1>, in press room, wearing a tuxedo. txt2img mode 0%| | 0/95 [00:00<?, ?it/s] 1%| | 1/95 [00:00<00:25, 3.69it/s] 2%|▏ | 2/95 [00:00<00:25, 3.67it/s] 3%|▎ | 3/95 [00:00<00:25, 3.66it/s] 4%|▍ | 4/95 [00:01<00:24, 3.65it/s] 5%|▌ | 5/95 [00:01<00:24, 3.65it/s] 6%|▋ | 6/95 [00:01<00:24, 3.64it/s] 7%|▋ | 7/95 [00:01<00:24, 3.64it/s] 8%|▊ | 8/95 [00:02<00:23, 3.65it/s] 9%|▉ | 9/95 [00:02<00:23, 3.64it/s] 11%|█ | 10/95 [00:02<00:23, 3.65it/s] 12%|█▏ | 11/95 [00:03<00:22, 3.66it/s] 13%|█▎ | 12/95 [00:03<00:22, 3.66it/s] 14%|█▎ | 13/95 [00:03<00:22, 3.66it/s] 15%|█▍ | 14/95 [00:03<00:22, 3.66it/s] 16%|█▌ | 15/95 [00:04<00:21, 3.66it/s] 17%|█▋ | 16/95 [00:04<00:21, 3.66it/s] 18%|█▊ | 17/95 [00:04<00:21, 3.66it/s] 19%|█▉ | 18/95 [00:04<00:21, 3.66it/s] 20%|██ | 19/95 [00:05<00:20, 3.66it/s] 21%|██ | 20/95 [00:05<00:20, 3.66it/s] 22%|██▏ | 21/95 [00:05<00:20, 3.66it/s] 23%|██▎ | 22/95 [00:06<00:19, 3.66it/s] 24%|██▍ | 23/95 [00:06<00:19, 3.65it/s] 25%|██▌ | 24/95 [00:06<00:19, 3.65it/s] 26%|██▋ | 25/95 [00:06<00:19, 3.65it/s] 27%|██▋ | 26/95 [00:07<00:18, 3.65it/s] 28%|██▊ | 27/95 [00:07<00:18, 3.65it/s] 29%|██▉ | 28/95 [00:07<00:18, 3.65it/s] 31%|███ | 29/95 [00:07<00:18, 3.65it/s] 32%|███▏ | 30/95 [00:08<00:17, 3.65it/s] 33%|███▎ | 31/95 [00:08<00:17, 3.65it/s] 34%|███▎ | 32/95 [00:08<00:17, 3.65it/s] 35%|███▍ | 33/95 [00:09<00:16, 3.65it/s] 36%|███▌ | 34/95 [00:09<00:16, 3.65it/s] 37%|███▋ | 35/95 [00:09<00:16, 3.65it/s] 38%|███▊ | 36/95 [00:09<00:16, 3.66it/s] 39%|███▉ | 37/95 [00:10<00:15, 3.66it/s] 40%|████ | 38/95 [00:10<00:15, 3.65it/s] 41%|████ | 39/95 [00:10<00:15, 3.65it/s] 42%|████▏ | 40/95 [00:10<00:15, 3.66it/s] 43%|████▎ | 41/95 [00:11<00:14, 3.65it/s] 44%|████▍ | 42/95 [00:11<00:14, 3.65it/s] 45%|████▌ | 43/95 [00:11<00:14, 3.65it/s] 46%|████▋ | 44/95 [00:12<00:13, 3.65it/s] 47%|████▋ | 45/95 [00:12<00:13, 3.65it/s] 48%|████▊ | 46/95 [00:12<00:13, 3.65it/s] 49%|████▉ | 47/95 [00:12<00:13, 3.65it/s] 51%|█████ | 48/95 [00:13<00:12, 3.65it/s] 52%|█████▏ | 49/95 [00:13<00:12, 3.65it/s] 53%|█████▎ | 50/95 [00:13<00:12, 3.65it/s] 54%|█████▎ | 51/95 [00:13<00:12, 3.65it/s] 55%|█████▍ | 52/95 [00:14<00:11, 3.65it/s] 56%|█████▌ | 53/95 [00:14<00:11, 3.64it/s] 57%|█████▋ | 54/95 [00:14<00:11, 3.64it/s] 58%|█████▊ | 55/95 [00:15<00:10, 3.64it/s] 59%|█████▉ | 56/95 [00:15<00:10, 3.64it/s] 60%|██████ | 57/95 [00:15<00:10, 3.64it/s] 61%|██████ | 58/95 [00:15<00:10, 3.64it/s] 62%|██████▏ | 59/95 [00:16<00:09, 3.64it/s] 63%|██████▎ | 60/95 [00:16<00:09, 3.63it/s] 64%|██████▍ | 61/95 [00:16<00:09, 3.64it/s] 65%|██████▌ | 62/95 [00:16<00:09, 3.64it/s] 66%|██████▋ | 63/95 [00:17<00:08, 3.64it/s] 67%|██████▋ | 64/95 [00:17<00:08, 3.64it/s] 68%|██████▊ | 65/95 [00:17<00:08, 3.64it/s] 69%|██████▉ | 66/95 [00:18<00:07, 3.64it/s] 71%|███████ | 67/95 [00:18<00:07, 3.64it/s] 72%|███████▏ | 68/95 [00:18<00:07, 3.63it/s] 73%|███████▎ | 69/95 [00:18<00:07, 3.64it/s] 74%|███████▎ | 70/95 [00:19<00:06, 3.64it/s] 75%|███████▍ | 71/95 [00:19<00:06, 3.63it/s] 76%|███████▌ | 72/95 [00:19<00:06, 3.63it/s] 77%|███████▋ | 73/95 [00:20<00:06, 3.63it/s] 78%|███████▊ | 74/95 [00:20<00:05, 3.63it/s] 79%|███████▉ | 75/95 [00:20<00:05, 3.63it/s] 80%|████████ | 76/95 [00:20<00:05, 3.63it/s] 81%|████████ | 77/95 [00:21<00:04, 3.63it/s] 82%|████████▏ | 78/95 [00:21<00:04, 3.63it/s] 83%|████████▎ | 79/95 [00:21<00:04, 3.63it/s] 84%|████████▍ | 80/95 [00:21<00:04, 3.63it/s] 85%|████████▌ | 81/95 [00:22<00:03, 3.63it/s] 86%|████████▋ | 82/95 [00:22<00:03, 3.63it/s] 87%|████████▋ | 83/95 [00:22<00:03, 3.63it/s] 88%|████████▊ | 84/95 [00:23<00:03, 3.63it/s] 89%|████████▉ | 85/95 [00:23<00:02, 3.63it/s] 91%|█████████ | 86/95 [00:23<00:02, 3.63it/s] 92%|█████████▏| 87/95 [00:23<00:02, 3.63it/s] 93%|█████████▎| 88/95 [00:24<00:01, 3.63it/s] 94%|█████████▎| 89/95 [00:24<00:01, 3.63it/s] 95%|█████████▍| 90/95 [00:24<00:01, 3.62it/s] 96%|█████████▌| 91/95 [00:24<00:01, 3.62it/s] 97%|█████████▋| 92/95 [00:25<00:00, 3.63it/s] 98%|█████████▊| 93/95 [00:25<00:00, 3.62it/s] 99%|█████████▉| 94/95 [00:25<00:00, 3.63it/s] 100%|██████████| 95/95 [00:26<00:00, 3.63it/s] 100%|██████████| 95/95 [00:26<00:00, 3.64it/s] 0%| | 0/5 [00:00<?, ?it/s] 20%|██ | 1/5 [00:00<00:00, 4.22it/s] 40%|████ | 2/5 [00:00<00:00, 4.20it/s] 60%|██████ | 3/5 [00:00<00:00, 4.19it/s] 80%|████████ | 4/5 [00:00<00:00, 4.19it/s] 100%|██████████| 5/5 [00:01<00:00, 4.19it/s] 100%|██████████| 5/5 [00:01<00:00, 4.19it/s]Prediction
gileslerockeur/mbappe:b838a04a475885971f77e3a58946f1e95c1519b2d53dbd361d4f09789c4bd450ID4cjn5alby4fr7zmkokx6sfjsbaStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- A photo of TOK, in a press room, wearing a dark blue suit, soccer awards ceremony.
- refine
- no_refiner
- scheduler
- DDIM
- lora_scale
- 0.8
- num_outputs
- 2
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.95
- negative_prompt
- jersey soccer field
- prompt_strength
- 0.8
- num_inference_steps
- 100
{ "width": 1024, "height": 1024, "prompt": "A photo of TOK, in a press room, wearing a dark blue suit, soccer awards ceremony.", "refine": "no_refiner", "scheduler": "DDIM", "lora_scale": 0.8, "num_outputs": 2, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.95, "negative_prompt": "jersey\nsoccer field", "prompt_strength": 0.8, "num_inference_steps": 100 }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 gileslerockeur/mbappe using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "gileslerockeur/mbappe:b838a04a475885971f77e3a58946f1e95c1519b2d53dbd361d4f09789c4bd450", { input: { width: 1024, height: 1024, prompt: "A photo of TOK, in a press room, wearing a dark blue suit, soccer awards ceremony.", refine: "no_refiner", scheduler: "DDIM", lora_scale: 0.8, num_outputs: 2, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.95, negative_prompt: "jersey\nsoccer field", prompt_strength: 0.8, num_inference_steps: 100 } } ); // 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 gileslerockeur/mbappe using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "gileslerockeur/mbappe:b838a04a475885971f77e3a58946f1e95c1519b2d53dbd361d4f09789c4bd450", input={ "width": 1024, "height": 1024, "prompt": "A photo of TOK, in a press room, wearing a dark blue suit, soccer awards ceremony.", "refine": "no_refiner", "scheduler": "DDIM", "lora_scale": 0.8, "num_outputs": 2, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.95, "negative_prompt": "jersey\nsoccer field", "prompt_strength": 0.8, "num_inference_steps": 100 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run gileslerockeur/mbappe 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": "b838a04a475885971f77e3a58946f1e95c1519b2d53dbd361d4f09789c4bd450", "input": { "width": 1024, "height": 1024, "prompt": "A photo of TOK, in a press room, wearing a dark blue suit, soccer awards ceremony.", "refine": "no_refiner", "scheduler": "DDIM", "lora_scale": 0.8, "num_outputs": 2, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.95, "negative_prompt": "jersey\\nsoccer field", "prompt_strength": 0.8, "num_inference_steps": 100 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-02-15T23:26:33.980464Z", "created_at": "2024-02-15T23:25:14.843080Z", "data_removed": false, "error": null, "id": "4cjn5alby4fr7zmkokx6sfjsba", "input": { "width": 1024, "height": 1024, "prompt": "A photo of TOK, in a press room, wearing a dark blue suit, soccer awards ceremony.", "refine": "no_refiner", "scheduler": "DDIM", "lora_scale": 0.8, "num_outputs": 2, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.95, "negative_prompt": "jersey\nsoccer field", "prompt_strength": 0.8, "num_inference_steps": 100 }, "logs": "Using seed: 41644\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A photo of <s0><s1>, in a press room, wearing a dark blue suit, soccer awards ceremony.\ntxt2img mode\n 0%| | 0/100 [00:00<?, ?it/s]\n 1%| | 1/100 [00:00<00:52, 1.89it/s]\n 2%|▏ | 2/100 [00:01<00:51, 1.89it/s]\n 3%|▎ | 3/100 [00:01<00:51, 1.89it/s]\n 4%|▍ | 4/100 [00:02<00:50, 1.89it/s]\n 5%|▌ | 5/100 [00:02<00:50, 1.89it/s]\n 6%|▌ | 6/100 [00:03<00:49, 1.88it/s]\n 7%|▋ | 7/100 [00:03<00:49, 1.88it/s]\n 8%|▊ | 8/100 [00:04<00:48, 1.88it/s]\n 9%|▉ | 9/100 [00:04<00:48, 1.88it/s]\n 10%|█ | 10/100 [00:05<00:47, 1.88it/s]\n 11%|█ | 11/100 [00:05<00:47, 1.88it/s]\n 12%|█▏ | 12/100 [00:06<00:46, 1.88it/s]\n 13%|█▎ | 13/100 [00:06<00:46, 1.88it/s]\n 14%|█▍ | 14/100 [00:07<00:45, 1.88it/s]\n 15%|█▌ | 15/100 [00:07<00:45, 1.88it/s]\n 16%|█▌ | 16/100 [00:08<00:44, 1.88it/s]\n 17%|█▋ | 17/100 [00:09<00:44, 1.88it/s]\n 18%|█▊ | 18/100 [00:09<00:43, 1.88it/s]\n 19%|█▉ | 19/100 [00:10<00:43, 1.88it/s]\n 20%|██ | 20/100 [00:10<00:42, 1.88it/s]\n 21%|██ | 21/100 [00:11<00:42, 1.87it/s]\n 22%|██▏ | 22/100 [00:11<00:41, 1.87it/s]\n 23%|██▎ | 23/100 [00:12<00:41, 1.87it/s]\n 24%|██▍ | 24/100 [00:12<00:40, 1.87it/s]\n 25%|██▌ | 25/100 [00:13<00:40, 1.87it/s]\n 26%|██▌ | 26/100 [00:13<00:39, 1.87it/s]\n 27%|██▋ | 27/100 [00:14<00:39, 1.87it/s]\n 28%|██▊ | 28/100 [00:14<00:38, 1.86it/s]\n 29%|██▉ | 29/100 [00:15<00:38, 1.86it/s]\n 30%|███ | 30/100 [00:16<00:37, 1.86it/s]\n 31%|███ | 31/100 [00:16<00:36, 1.87it/s]\n 32%|███▏ | 32/100 [00:17<00:36, 1.87it/s]\n 33%|███▎ | 33/100 [00:17<00:35, 1.87it/s]\n 34%|███▍ | 34/100 [00:18<00:35, 1.87it/s]\n 35%|███▌ | 35/100 [00:18<00:34, 1.87it/s]\n 36%|███▌ | 36/100 [00:19<00:34, 1.87it/s]\n 37%|███▋ | 37/100 [00:19<00:33, 1.87it/s]\n 38%|███▊ | 38/100 [00:20<00:33, 1.87it/s]\n 39%|███▉ | 39/100 [00:20<00:32, 1.87it/s]\n 40%|████ | 40/100 [00:21<00:32, 1.87it/s]\n 41%|████ | 41/100 [00:21<00:31, 1.87it/s]\n 42%|████▏ | 42/100 [00:22<00:31, 1.86it/s]\n 43%|████▎ | 43/100 [00:22<00:30, 1.86it/s]\n 44%|████▍ | 44/100 [00:23<00:30, 1.86it/s]\n 45%|████▌ | 45/100 [00:24<00:29, 1.86it/s]\n 46%|████▌ | 46/100 [00:24<00:28, 1.86it/s]\n 47%|████▋ | 47/100 [00:25<00:28, 1.86it/s]\n 48%|████▊ | 48/100 [00:25<00:27, 1.87it/s]\n 49%|████▉ | 49/100 [00:26<00:27, 1.87it/s]\n 50%|█████ | 50/100 [00:26<00:26, 1.87it/s]\n 51%|█████ | 51/100 [00:27<00:26, 1.87it/s]\n 52%|█████▏ | 52/100 [00:27<00:25, 1.87it/s]\n 53%|█████▎ | 53/100 [00:28<00:25, 1.87it/s]\n 54%|█████▍ | 54/100 [00:28<00:24, 1.87it/s]\n 55%|█████▌ | 55/100 [00:29<00:24, 1.87it/s]\n 56%|█████▌ | 56/100 [00:29<00:23, 1.87it/s]\n 57%|█████▋ | 57/100 [00:30<00:22, 1.87it/s]\n 58%|█████▊ | 58/100 [00:31<00:22, 1.87it/s]\n 59%|█████▉ | 59/100 [00:31<00:21, 1.87it/s]\n 60%|██████ | 60/100 [00:32<00:21, 1.87it/s]\n 61%|██████ | 61/100 [00:32<00:20, 1.87it/s]\n 62%|██████▏ | 62/100 [00:33<00:20, 1.87it/s]\n 63%|██████▎ | 63/100 [00:33<00:19, 1.87it/s]\n 64%|██████▍ | 64/100 [00:34<00:19, 1.87it/s]\n 65%|██████▌ | 65/100 [00:34<00:18, 1.87it/s]\n 66%|██████▌ | 66/100 [00:35<00:18, 1.87it/s]\n 67%|██████▋ | 67/100 [00:35<00:17, 1.87it/s]\n 68%|██████▊ | 68/100 [00:36<00:17, 1.87it/s]\n 69%|██████▉ | 69/100 [00:36<00:16, 1.87it/s]\n 70%|███████ | 70/100 [00:37<00:16, 1.87it/s]\n 71%|███████ | 71/100 [00:37<00:15, 1.86it/s]\n 72%|███████▏ | 72/100 [00:38<00:15, 1.86it/s]\n 73%|███████▎ | 73/100 [00:39<00:14, 1.86it/s]\n 74%|███████▍ | 74/100 [00:39<00:13, 1.86it/s]\n 75%|███████▌ | 75/100 [00:40<00:13, 1.87it/s]\n 76%|███████▌ | 76/100 [00:40<00:12, 1.87it/s]\n 77%|███████▋ | 77/100 [00:41<00:12, 1.87it/s]\n 78%|███████▊ | 78/100 [00:41<00:11, 1.87it/s]\n 79%|███████▉ | 79/100 [00:42<00:11, 1.87it/s]\n 80%|████████ | 80/100 [00:42<00:10, 1.86it/s]\n 81%|████████ | 81/100 [00:43<00:10, 1.87it/s]\n 82%|████████▏ | 82/100 [00:43<00:09, 1.87it/s]\n 83%|████████▎ | 83/100 [00:44<00:09, 1.86it/s]\n 84%|████████▍ | 84/100 [00:44<00:08, 1.86it/s]\n 85%|████████▌ | 85/100 [00:45<00:08, 1.86it/s]\n 86%|████████▌ | 86/100 [00:46<00:07, 1.86it/s]\n 87%|████████▋ | 87/100 [00:46<00:06, 1.86it/s]\n 88%|████████▊ | 88/100 [00:47<00:06, 1.86it/s]\n 89%|████████▉ | 89/100 [00:47<00:05, 1.86it/s]\n 90%|█████████ | 90/100 [00:48<00:05, 1.86it/s]\n 91%|█████████ | 91/100 [00:48<00:04, 1.86it/s]\n 92%|█████████▏| 92/100 [00:49<00:04, 1.86it/s]\n 93%|█████████▎| 93/100 [00:49<00:03, 1.86it/s]\n 94%|█████████▍| 94/100 [00:50<00:03, 1.86it/s]\n 95%|█████████▌| 95/100 [00:50<00:02, 1.86it/s]\n 96%|█████████▌| 96/100 [00:51<00:02, 1.86it/s]\n 97%|█████████▋| 97/100 [00:51<00:01, 1.86it/s]\n 98%|█████████▊| 98/100 [00:52<00:01, 1.86it/s]\n 99%|█████████▉| 99/100 [00:52<00:00, 1.86it/s]\n100%|██████████| 100/100 [00:53<00:00, 1.86it/s]\n100%|██████████| 100/100 [00:53<00:00, 1.87it/s]", "metrics": { "predict_time": 58.28945, "total_time": 79.137384 }, "output": [ "https://replicate.delivery/pbxt/zTxo0pJKbLLPKN62ngiqM5KdLOgbtjaWkOQWvnmzrGNqPxlE/out-0.png", "https://replicate.delivery/pbxt/6CGPtZoF9QJzPRgvYakt3w05rny5d89Uqp4XdiDk0LZqPxlE/out-1.png" ], "started_at": "2024-02-15T23:25:35.691014Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/4cjn5alby4fr7zmkokx6sfjsba", "cancel": "https://api.replicate.com/v1/predictions/4cjn5alby4fr7zmkokx6sfjsba/cancel" }, "version": "b838a04a475885971f77e3a58946f1e95c1519b2d53dbd361d4f09789c4bd450" }Generated inUsing seed: 41644 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A photo of <s0><s1>, in a press room, wearing a dark blue suit, soccer awards ceremony. txt2img mode 0%| | 0/100 [00:00<?, ?it/s] 1%| | 1/100 [00:00<00:52, 1.89it/s] 2%|▏ | 2/100 [00:01<00:51, 1.89it/s] 3%|▎ | 3/100 [00:01<00:51, 1.89it/s] 4%|▍ | 4/100 [00:02<00:50, 1.89it/s] 5%|▌ | 5/100 [00:02<00:50, 1.89it/s] 6%|▌ | 6/100 [00:03<00:49, 1.88it/s] 7%|▋ | 7/100 [00:03<00:49, 1.88it/s] 8%|▊ | 8/100 [00:04<00:48, 1.88it/s] 9%|▉ | 9/100 [00:04<00:48, 1.88it/s] 10%|█ | 10/100 [00:05<00:47, 1.88it/s] 11%|█ | 11/100 [00:05<00:47, 1.88it/s] 12%|█▏ | 12/100 [00:06<00:46, 1.88it/s] 13%|█▎ | 13/100 [00:06<00:46, 1.88it/s] 14%|█▍ | 14/100 [00:07<00:45, 1.88it/s] 15%|█▌ | 15/100 [00:07<00:45, 1.88it/s] 16%|█▌ | 16/100 [00:08<00:44, 1.88it/s] 17%|█▋ | 17/100 [00:09<00:44, 1.88it/s] 18%|█▊ | 18/100 [00:09<00:43, 1.88it/s] 19%|█▉ | 19/100 [00:10<00:43, 1.88it/s] 20%|██ | 20/100 [00:10<00:42, 1.88it/s] 21%|██ | 21/100 [00:11<00:42, 1.87it/s] 22%|██▏ | 22/100 [00:11<00:41, 1.87it/s] 23%|██▎ | 23/100 [00:12<00:41, 1.87it/s] 24%|██▍ | 24/100 [00:12<00:40, 1.87it/s] 25%|██▌ | 25/100 [00:13<00:40, 1.87it/s] 26%|██▌ | 26/100 [00:13<00:39, 1.87it/s] 27%|██▋ | 27/100 [00:14<00:39, 1.87it/s] 28%|██▊ | 28/100 [00:14<00:38, 1.86it/s] 29%|██▉ | 29/100 [00:15<00:38, 1.86it/s] 30%|███ | 30/100 [00:16<00:37, 1.86it/s] 31%|███ | 31/100 [00:16<00:36, 1.87it/s] 32%|███▏ | 32/100 [00:17<00:36, 1.87it/s] 33%|███▎ | 33/100 [00:17<00:35, 1.87it/s] 34%|███▍ | 34/100 [00:18<00:35, 1.87it/s] 35%|███▌ | 35/100 [00:18<00:34, 1.87it/s] 36%|███▌ | 36/100 [00:19<00:34, 1.87it/s] 37%|███▋ | 37/100 [00:19<00:33, 1.87it/s] 38%|███▊ | 38/100 [00:20<00:33, 1.87it/s] 39%|███▉ | 39/100 [00:20<00:32, 1.87it/s] 40%|████ | 40/100 [00:21<00:32, 1.87it/s] 41%|████ | 41/100 [00:21<00:31, 1.87it/s] 42%|████▏ | 42/100 [00:22<00:31, 1.86it/s] 43%|████▎ | 43/100 [00:22<00:30, 1.86it/s] 44%|████▍ | 44/100 [00:23<00:30, 1.86it/s] 45%|████▌ | 45/100 [00:24<00:29, 1.86it/s] 46%|████▌ | 46/100 [00:24<00:28, 1.86it/s] 47%|████▋ | 47/100 [00:25<00:28, 1.86it/s] 48%|████▊ | 48/100 [00:25<00:27, 1.87it/s] 49%|████▉ | 49/100 [00:26<00:27, 1.87it/s] 50%|█████ | 50/100 [00:26<00:26, 1.87it/s] 51%|█████ | 51/100 [00:27<00:26, 1.87it/s] 52%|█████▏ | 52/100 [00:27<00:25, 1.87it/s] 53%|█████▎ | 53/100 [00:28<00:25, 1.87it/s] 54%|█████▍ | 54/100 [00:28<00:24, 1.87it/s] 55%|█████▌ | 55/100 [00:29<00:24, 1.87it/s] 56%|█████▌ | 56/100 [00:29<00:23, 1.87it/s] 57%|█████▋ | 57/100 [00:30<00:22, 1.87it/s] 58%|█████▊ | 58/100 [00:31<00:22, 1.87it/s] 59%|█████▉ | 59/100 [00:31<00:21, 1.87it/s] 60%|██████ | 60/100 [00:32<00:21, 1.87it/s] 61%|██████ | 61/100 [00:32<00:20, 1.87it/s] 62%|██████▏ | 62/100 [00:33<00:20, 1.87it/s] 63%|██████▎ | 63/100 [00:33<00:19, 1.87it/s] 64%|██████▍ | 64/100 [00:34<00:19, 1.87it/s] 65%|██████▌ | 65/100 [00:34<00:18, 1.87it/s] 66%|██████▌ | 66/100 [00:35<00:18, 1.87it/s] 67%|██████▋ | 67/100 [00:35<00:17, 1.87it/s] 68%|██████▊ | 68/100 [00:36<00:17, 1.87it/s] 69%|██████▉ | 69/100 [00:36<00:16, 1.87it/s] 70%|███████ | 70/100 [00:37<00:16, 1.87it/s] 71%|███████ | 71/100 [00:37<00:15, 1.86it/s] 72%|███████▏ | 72/100 [00:38<00:15, 1.86it/s] 73%|███████▎ | 73/100 [00:39<00:14, 1.86it/s] 74%|███████▍ | 74/100 [00:39<00:13, 1.86it/s] 75%|███████▌ | 75/100 [00:40<00:13, 1.87it/s] 76%|███████▌ | 76/100 [00:40<00:12, 1.87it/s] 77%|███████▋ | 77/100 [00:41<00:12, 1.87it/s] 78%|███████▊ | 78/100 [00:41<00:11, 1.87it/s] 79%|███████▉ | 79/100 [00:42<00:11, 1.87it/s] 80%|████████ | 80/100 [00:42<00:10, 1.86it/s] 81%|████████ | 81/100 [00:43<00:10, 1.87it/s] 82%|████████▏ | 82/100 [00:43<00:09, 1.87it/s] 83%|████████▎ | 83/100 [00:44<00:09, 1.86it/s] 84%|████████▍ | 84/100 [00:44<00:08, 1.86it/s] 85%|████████▌ | 85/100 [00:45<00:08, 1.86it/s] 86%|████████▌ | 86/100 [00:46<00:07, 1.86it/s] 87%|████████▋ | 87/100 [00:46<00:06, 1.86it/s] 88%|████████▊ | 88/100 [00:47<00:06, 1.86it/s] 89%|████████▉ | 89/100 [00:47<00:05, 1.86it/s] 90%|█████████ | 90/100 [00:48<00:05, 1.86it/s] 91%|█████████ | 91/100 [00:48<00:04, 1.86it/s] 92%|█████████▏| 92/100 [00:49<00:04, 1.86it/s] 93%|█████████▎| 93/100 [00:49<00:03, 1.86it/s] 94%|█████████▍| 94/100 [00:50<00:03, 1.86it/s] 95%|█████████▌| 95/100 [00:50<00:02, 1.86it/s] 96%|█████████▌| 96/100 [00:51<00:02, 1.86it/s] 97%|█████████▋| 97/100 [00:51<00:01, 1.86it/s] 98%|█████████▊| 98/100 [00:52<00:01, 1.86it/s] 99%|█████████▉| 99/100 [00:52<00:00, 1.86it/s] 100%|██████████| 100/100 [00:53<00:00, 1.86it/s] 100%|██████████| 100/100 [00:53<00:00, 1.87it/s]
Want to make some of these yourself?
Run this model