fszotyi / sdxl-car
- Public
- 114 runs
-
L40S
- SDXL fine-tune
Prediction
fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169IDh2d00hfex5rgj0cfbfyvwbb830StatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a photo of TOK car, in f1 race
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.7
- num_outputs
- 1
- refine_steps
- 0
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.95
- negative_prompt
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "a photo of TOK car, in f1 race", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }
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 fszotyi/sdxl-car using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", { input: { width: 1024, height: 1024, prompt: "a photo of TOK car, in f1 race", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.7, num_outputs: 1, refine_steps: 0, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.95, negative_prompt: "", 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 replicate
Import the client:import replicate
Run fszotyi/sdxl-car using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", input={ "width": 1024, "height": 1024, "prompt": "a photo of TOK car, in f1 race", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.95, "negative_prompt": "", "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 fszotyi/sdxl-car 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": "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", "input": { "width": 1024, "height": 1024, "prompt": "a photo of TOK car, in f1 race", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-05-09T06:15:57.115440Z", "created_at": "2024-05-09T06:15:19.529000Z", "data_removed": false, "error": null, "id": "h2d00hfex5rgj0cfbfyvwbb830", "input": { "width": 1024, "height": 1024, "prompt": "a photo of TOK car, in f1 race", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 16105\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a photo of <s0><s1> car, in f1 race\ntxt2img mode\n 0%| | 0/47 [00:00<?, ?it/s]\n 2%|▏ | 1/47 [00:00<00:12, 3.67it/s]\n 4%|▍ | 2/47 [00:00<00:12, 3.66it/s]\n 6%|▋ | 3/47 [00:00<00:12, 3.66it/s]\n 9%|▊ | 4/47 [00:01<00:11, 3.64it/s]\n 11%|█ | 5/47 [00:01<00:11, 3.65it/s]\n 13%|█▎ | 6/47 [00:01<00:11, 3.65it/s]\n 15%|█▍ | 7/47 [00:01<00:10, 3.65it/s]\n 17%|█▋ | 8/47 [00:02<00:10, 3.65it/s]\n 19%|█▉ | 9/47 [00:02<00:10, 3.65it/s]\n 21%|██▏ | 10/47 [00:02<00:10, 3.65it/s]\n 23%|██▎ | 11/47 [00:03<00:09, 3.65it/s]\n 26%|██▌ | 12/47 [00:03<00:09, 3.65it/s]\n 28%|██▊ | 13/47 [00:03<00:09, 3.65it/s]\n 30%|██▉ | 14/47 [00:03<00:09, 3.65it/s]\n 32%|███▏ | 15/47 [00:04<00:08, 3.65it/s]\n 34%|███▍ | 16/47 [00:04<00:08, 3.65it/s]\n 36%|███▌ | 17/47 [00:04<00:08, 3.65it/s]\n 38%|███▊ | 18/47 [00:04<00:07, 3.64it/s]\n 40%|████ | 19/47 [00:05<00:07, 3.64it/s]\n 43%|████▎ | 20/47 [00:05<00:07, 3.64it/s]\n 45%|████▍ | 21/47 [00:05<00:07, 3.64it/s]\n 47%|████▋ | 22/47 [00:06<00:06, 3.64it/s]\n 49%|████▉ | 23/47 [00:06<00:06, 3.64it/s]\n 51%|█████ | 24/47 [00:06<00:06, 3.64it/s]\n 53%|█████▎ | 25/47 [00:06<00:06, 3.64it/s]\n 55%|█████▌ | 26/47 [00:07<00:05, 3.64it/s]\n 57%|█████▋ | 27/47 [00:07<00:05, 3.64it/s]\n 60%|█████▉ | 28/47 [00:07<00:05, 3.64it/s]\n 62%|██████▏ | 29/47 [00:07<00:04, 3.64it/s]\n 64%|██████▍ | 30/47 [00:08<00:04, 3.64it/s]\n 66%|██████▌ | 31/47 [00:08<00:04, 3.64it/s]\n 68%|██████▊ | 32/47 [00:08<00:04, 3.64it/s]\n 70%|███████ | 33/47 [00:09<00:03, 3.63it/s]\n 72%|███████▏ | 34/47 [00:09<00:03, 3.63it/s]\n 74%|███████▍ | 35/47 [00:09<00:03, 3.63it/s]\n 77%|███████▋ | 36/47 [00:09<00:03, 3.63it/s]\n 79%|███████▊ | 37/47 [00:10<00:02, 3.63it/s]\n 81%|████████ | 38/47 [00:10<00:02, 3.63it/s]\n 83%|████████▎ | 39/47 [00:10<00:02, 3.64it/s]\n 85%|████████▌ | 40/47 [00:10<00:01, 3.63it/s]\n 87%|████████▋ | 41/47 [00:11<00:01, 3.63it/s]\n 89%|████████▉ | 42/47 [00:11<00:01, 3.63it/s]\n 91%|█████████▏| 43/47 [00:11<00:01, 3.63it/s]\n 94%|█████████▎| 44/47 [00:12<00:00, 3.63it/s]\n 96%|█████████▌| 45/47 [00:12<00:00, 3.63it/s]\n 98%|█████████▊| 46/47 [00:12<00:00, 3.63it/s]\n100%|██████████| 47/47 [00:12<00:00, 3.63it/s]\n100%|██████████| 47/47 [00:12<00:00, 3.64it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 4.01it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 4.12it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.14it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.12it/s]", "metrics": { "predict_time": 15.441804, "total_time": 37.58644 }, "output": [ "https://replicate.delivery/pbxt/cqpTvlWWr74TLJ39p5nA0Nqs8sidxSBjrUsI416Vm0JHcosE/out-0.png" ], "started_at": "2024-05-09T06:15:41.673636Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/h2d00hfex5rgj0cfbfyvwbb830", "cancel": "https://api.replicate.com/v1/predictions/h2d00hfex5rgj0cfbfyvwbb830/cancel" }, "version": "91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169" }
Generated inUsing seed: 16105 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: a photo of <s0><s1> car, in f1 race txt2img mode 0%| | 0/47 [00:00<?, ?it/s] 2%|▏ | 1/47 [00:00<00:12, 3.67it/s] 4%|▍ | 2/47 [00:00<00:12, 3.66it/s] 6%|▋ | 3/47 [00:00<00:12, 3.66it/s] 9%|▊ | 4/47 [00:01<00:11, 3.64it/s] 11%|█ | 5/47 [00:01<00:11, 3.65it/s] 13%|█▎ | 6/47 [00:01<00:11, 3.65it/s] 15%|█▍ | 7/47 [00:01<00:10, 3.65it/s] 17%|█▋ | 8/47 [00:02<00:10, 3.65it/s] 19%|█▉ | 9/47 [00:02<00:10, 3.65it/s] 21%|██▏ | 10/47 [00:02<00:10, 3.65it/s] 23%|██▎ | 11/47 [00:03<00:09, 3.65it/s] 26%|██▌ | 12/47 [00:03<00:09, 3.65it/s] 28%|██▊ | 13/47 [00:03<00:09, 3.65it/s] 30%|██▉ | 14/47 [00:03<00:09, 3.65it/s] 32%|███▏ | 15/47 [00:04<00:08, 3.65it/s] 34%|███▍ | 16/47 [00:04<00:08, 3.65it/s] 36%|███▌ | 17/47 [00:04<00:08, 3.65it/s] 38%|███▊ | 18/47 [00:04<00:07, 3.64it/s] 40%|████ | 19/47 [00:05<00:07, 3.64it/s] 43%|████▎ | 20/47 [00:05<00:07, 3.64it/s] 45%|████▍ | 21/47 [00:05<00:07, 3.64it/s] 47%|████▋ | 22/47 [00:06<00:06, 3.64it/s] 49%|████▉ | 23/47 [00:06<00:06, 3.64it/s] 51%|█████ | 24/47 [00:06<00:06, 3.64it/s] 53%|█████▎ | 25/47 [00:06<00:06, 3.64it/s] 55%|█████▌ | 26/47 [00:07<00:05, 3.64it/s] 57%|█████▋ | 27/47 [00:07<00:05, 3.64it/s] 60%|█████▉ | 28/47 [00:07<00:05, 3.64it/s] 62%|██████▏ | 29/47 [00:07<00:04, 3.64it/s] 64%|██████▍ | 30/47 [00:08<00:04, 3.64it/s] 66%|██████▌ | 31/47 [00:08<00:04, 3.64it/s] 68%|██████▊ | 32/47 [00:08<00:04, 3.64it/s] 70%|███████ | 33/47 [00:09<00:03, 3.63it/s] 72%|███████▏ | 34/47 [00:09<00:03, 3.63it/s] 74%|███████▍ | 35/47 [00:09<00:03, 3.63it/s] 77%|███████▋ | 36/47 [00:09<00:03, 3.63it/s] 79%|███████▊ | 37/47 [00:10<00:02, 3.63it/s] 81%|████████ | 38/47 [00:10<00:02, 3.63it/s] 83%|████████▎ | 39/47 [00:10<00:02, 3.64it/s] 85%|████████▌ | 40/47 [00:10<00:01, 3.63it/s] 87%|████████▋ | 41/47 [00:11<00:01, 3.63it/s] 89%|████████▉ | 42/47 [00:11<00:01, 3.63it/s] 91%|█████████▏| 43/47 [00:11<00:01, 3.63it/s] 94%|█████████▎| 44/47 [00:12<00:00, 3.63it/s] 96%|█████████▌| 45/47 [00:12<00:00, 3.63it/s] 98%|█████████▊| 46/47 [00:12<00:00, 3.63it/s] 100%|██████████| 47/47 [00:12<00:00, 3.63it/s] 100%|██████████| 47/47 [00:12<00:00, 3.64it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 4.01it/s] 67%|██████▋ | 2/3 [00:00<00:00, 4.12it/s] 100%|██████████| 3/3 [00:00<00:00, 4.14it/s] 100%|██████████| 3/3 [00:00<00:00, 4.12it/s]
Prediction
fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169IDcy7e9s6pt1rgj0cfbfzv6adta0StatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a photo of TOK car, on the highway in hawaii
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.7
- num_outputs
- 1
- refine_steps
- 0
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.95
- negative_prompt
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "a photo of TOK car, on the highway in hawaii", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }
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 fszotyi/sdxl-car using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", { input: { width: 1024, height: 1024, prompt: "a photo of TOK car, on the highway in hawaii", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.7, num_outputs: 1, refine_steps: 0, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.95, negative_prompt: "", 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 replicate
Import the client:import replicate
Run fszotyi/sdxl-car using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", input={ "width": 1024, "height": 1024, "prompt": "a photo of TOK car, on the highway in hawaii", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.95, "negative_prompt": "", "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 fszotyi/sdxl-car 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": "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", "input": { "width": 1024, "height": 1024, "prompt": "a photo of TOK car, on the highway in hawaii", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-05-09T06:17:42.962095Z", "created_at": "2024-05-09T06:17:24.432000Z", "data_removed": false, "error": null, "id": "cy7e9s6pt1rgj0cfbfzv6adta0", "input": { "width": 1024, "height": 1024, "prompt": "a photo of TOK car, on the highway in hawaii", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 24597\nskipping loading .. weights already loaded\nPrompt: a photo of <s0><s1> car, on the highway in hawaii\ntxt2img mode\n 0%| | 0/47 [00:00<?, ?it/s]\n 2%|▏ | 1/47 [00:00<00:12, 3.67it/s]\n 4%|▍ | 2/47 [00:00<00:12, 3.66it/s]\n 6%|▋ | 3/47 [00:00<00:12, 3.67it/s]\n 9%|▊ | 4/47 [00:01<00:11, 3.67it/s]\n 11%|█ | 5/47 [00:01<00:11, 3.66it/s]\n 13%|█▎ | 6/47 [00:01<00:11, 3.66it/s]\n 15%|█▍ | 7/47 [00:01<00:10, 3.66it/s]\n 17%|█▋ | 8/47 [00:02<00:10, 3.66it/s]\n 19%|█▉ | 9/47 [00:02<00:10, 3.66it/s]\n 21%|██▏ | 10/47 [00:02<00:10, 3.66it/s]\n 23%|██▎ | 11/47 [00:03<00:09, 3.66it/s]\n 26%|██▌ | 12/47 [00:03<00:09, 3.66it/s]\n 28%|██▊ | 13/47 [00:03<00:09, 3.66it/s]\n 30%|██▉ | 14/47 [00:03<00:09, 3.66it/s]\n 32%|███▏ | 15/47 [00:04<00:08, 3.66it/s]\n 34%|███▍ | 16/47 [00:04<00:08, 3.66it/s]\n 36%|███▌ | 17/47 [00:04<00:08, 3.66it/s]\n 38%|███▊ | 18/47 [00:04<00:07, 3.65it/s]\n 40%|████ | 19/47 [00:05<00:07, 3.65it/s]\n 43%|████▎ | 20/47 [00:05<00:07, 3.65it/s]\n 45%|████▍ | 21/47 [00:05<00:07, 3.65it/s]\n 47%|████▋ | 22/47 [00:06<00:06, 3.65it/s]\n 49%|████▉ | 23/47 [00:06<00:06, 3.65it/s]\n 51%|█████ | 24/47 [00:06<00:06, 3.65it/s]\n 53%|█████▎ | 25/47 [00:06<00:06, 3.64it/s]\n 55%|█████▌ | 26/47 [00:07<00:05, 3.64it/s]\n 57%|█████▋ | 27/47 [00:07<00:05, 3.64it/s]\n 60%|█████▉ | 28/47 [00:07<00:05, 3.65it/s]\n 62%|██████▏ | 29/47 [00:07<00:04, 3.64it/s]\n 64%|██████▍ | 30/47 [00:08<00:04, 3.64it/s]\n 66%|██████▌ | 31/47 [00:08<00:04, 3.65it/s]\n 68%|██████▊ | 32/47 [00:08<00:04, 3.65it/s]\n 70%|███████ | 33/47 [00:09<00:03, 3.64it/s]\n 72%|███████▏ | 34/47 [00:09<00:03, 3.64it/s]\n 74%|███████▍ | 35/47 [00:09<00:03, 3.65it/s]\n 77%|███████▋ | 36/47 [00:09<00:03, 3.64it/s]\n 79%|███████▊ | 37/47 [00:10<00:02, 3.64it/s]\n 81%|████████ | 38/47 [00:10<00:02, 3.64it/s]\n 83%|████████▎ | 39/47 [00:10<00:02, 3.64it/s]\n 85%|████████▌ | 40/47 [00:10<00:01, 3.64it/s]\n 87%|████████▋ | 41/47 [00:11<00:01, 3.64it/s]\n 89%|████████▉ | 42/47 [00:11<00:01, 3.64it/s]\n 91%|█████████▏| 43/47 [00:11<00:01, 3.64it/s]\n 94%|█████████▎| 44/47 [00:12<00:00, 3.64it/s]\n 96%|█████████▌| 45/47 [00:12<00:00, 3.64it/s]\n 98%|█████████▊| 46/47 [00:12<00:00, 3.64it/s]\n100%|██████████| 47/47 [00:12<00:00, 3.64it/s]\n100%|██████████| 47/47 [00:12<00:00, 3.65it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 4.24it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 4.22it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.22it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.22it/s]", "metrics": { "predict_time": 14.97355, "total_time": 18.530095 }, "output": [ "https://replicate.delivery/pbxt/X8M694CvARIXB51B5wEai3c7j4YjmHjdh17jOXtIc9jhcosE/out-0.png" ], "started_at": "2024-05-09T06:17:27.988545Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/cy7e9s6pt1rgj0cfbfzv6adta0", "cancel": "https://api.replicate.com/v1/predictions/cy7e9s6pt1rgj0cfbfzv6adta0/cancel" }, "version": "91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169" }
Generated inUsing seed: 24597 skipping loading .. weights already loaded Prompt: a photo of <s0><s1> car, on the highway in hawaii txt2img mode 0%| | 0/47 [00:00<?, ?it/s] 2%|▏ | 1/47 [00:00<00:12, 3.67it/s] 4%|▍ | 2/47 [00:00<00:12, 3.66it/s] 6%|▋ | 3/47 [00:00<00:12, 3.67it/s] 9%|▊ | 4/47 [00:01<00:11, 3.67it/s] 11%|█ | 5/47 [00:01<00:11, 3.66it/s] 13%|█▎ | 6/47 [00:01<00:11, 3.66it/s] 15%|█▍ | 7/47 [00:01<00:10, 3.66it/s] 17%|█▋ | 8/47 [00:02<00:10, 3.66it/s] 19%|█▉ | 9/47 [00:02<00:10, 3.66it/s] 21%|██▏ | 10/47 [00:02<00:10, 3.66it/s] 23%|██▎ | 11/47 [00:03<00:09, 3.66it/s] 26%|██▌ | 12/47 [00:03<00:09, 3.66it/s] 28%|██▊ | 13/47 [00:03<00:09, 3.66it/s] 30%|██▉ | 14/47 [00:03<00:09, 3.66it/s] 32%|███▏ | 15/47 [00:04<00:08, 3.66it/s] 34%|███▍ | 16/47 [00:04<00:08, 3.66it/s] 36%|███▌ | 17/47 [00:04<00:08, 3.66it/s] 38%|███▊ | 18/47 [00:04<00:07, 3.65it/s] 40%|████ | 19/47 [00:05<00:07, 3.65it/s] 43%|████▎ | 20/47 [00:05<00:07, 3.65it/s] 45%|████▍ | 21/47 [00:05<00:07, 3.65it/s] 47%|████▋ | 22/47 [00:06<00:06, 3.65it/s] 49%|████▉ | 23/47 [00:06<00:06, 3.65it/s] 51%|█████ | 24/47 [00:06<00:06, 3.65it/s] 53%|█████▎ | 25/47 [00:06<00:06, 3.64it/s] 55%|█████▌ | 26/47 [00:07<00:05, 3.64it/s] 57%|█████▋ | 27/47 [00:07<00:05, 3.64it/s] 60%|█████▉ | 28/47 [00:07<00:05, 3.65it/s] 62%|██████▏ | 29/47 [00:07<00:04, 3.64it/s] 64%|██████▍ | 30/47 [00:08<00:04, 3.64it/s] 66%|██████▌ | 31/47 [00:08<00:04, 3.65it/s] 68%|██████▊ | 32/47 [00:08<00:04, 3.65it/s] 70%|███████ | 33/47 [00:09<00:03, 3.64it/s] 72%|███████▏ | 34/47 [00:09<00:03, 3.64it/s] 74%|███████▍ | 35/47 [00:09<00:03, 3.65it/s] 77%|███████▋ | 36/47 [00:09<00:03, 3.64it/s] 79%|███████▊ | 37/47 [00:10<00:02, 3.64it/s] 81%|████████ | 38/47 [00:10<00:02, 3.64it/s] 83%|████████▎ | 39/47 [00:10<00:02, 3.64it/s] 85%|████████▌ | 40/47 [00:10<00:01, 3.64it/s] 87%|████████▋ | 41/47 [00:11<00:01, 3.64it/s] 89%|████████▉ | 42/47 [00:11<00:01, 3.64it/s] 91%|█████████▏| 43/47 [00:11<00:01, 3.64it/s] 94%|█████████▎| 44/47 [00:12<00:00, 3.64it/s] 96%|█████████▌| 45/47 [00:12<00:00, 3.64it/s] 98%|█████████▊| 46/47 [00:12<00:00, 3.64it/s] 100%|██████████| 47/47 [00:12<00:00, 3.64it/s] 100%|██████████| 47/47 [00:12<00:00, 3.65it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 4.24it/s] 67%|██████▋ | 2/3 [00:00<00:00, 4.22it/s] 100%|██████████| 3/3 [00:00<00:00, 4.22it/s] 100%|██████████| 3/3 [00:00<00:00, 4.22it/s]
Prediction
fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169ID3z0tge2jwxrgp0cfbg1b19wcccStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a photo of TOK car, racing other cars
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.7
- num_outputs
- 1
- refine_steps
- 0
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.95
- negative_prompt
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "a photo of TOK car, racing other cars", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }
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 fszotyi/sdxl-car using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", { input: { width: 1024, height: 1024, prompt: "a photo of TOK car, racing other cars", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.7, num_outputs: 1, refine_steps: 0, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.95, negative_prompt: "", 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 replicate
Import the client:import replicate
Run fszotyi/sdxl-car using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", input={ "width": 1024, "height": 1024, "prompt": "a photo of TOK car, racing other cars", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.95, "negative_prompt": "", "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 fszotyi/sdxl-car 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": "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", "input": { "width": 1024, "height": 1024, "prompt": "a photo of TOK car, racing other cars", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-05-09T06:20:28.063937Z", "created_at": "2024-05-09T06:20:07.271000Z", "data_removed": false, "error": null, "id": "3z0tge2jwxrgp0cfbg1b19wccc", "input": { "width": 1024, "height": 1024, "prompt": "a photo of TOK car, racing other cars", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 10353\nEnsuring enough disk space...\nFree disk space: 2063356452864\nDownloading weights: https://replicate.delivery/pbxt/YFUPzbCukZIHIJc8sznL8AWfmYSXVL7fMGPgGG3gGUTe7CllA/trained_model.tar\n2024-05-09T06:20:08Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/3102d728bde11c70 url=https://replicate.delivery/pbxt/YFUPzbCukZIHIJc8sznL8AWfmYSXVL7fMGPgGG3gGUTe7CllA/trained_model.tar\n2024-05-09T06:20:10Z | INFO | [ Complete ] dest=/src/weights-cache/3102d728bde11c70 size=\"186 MB\" total_elapsed=1.586s url=https://replicate.delivery/pbxt/YFUPzbCukZIHIJc8sznL8AWfmYSXVL7fMGPgGG3gGUTe7CllA/trained_model.tar\nb''\nDownloaded weights in 1.7163019180297852 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a photo of <s0><s1> car, racing other cars\ntxt2img mode\n 0%| | 0/47 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/torch/nn/modules/conv.py:459: UserWarning: Applied workaround for CuDNN issue, install nvrtc.so (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:80.)\nreturn F.conv2d(input, weight, bias, self.stride,\n 2%|▏ | 1/47 [00:00<00:30, 1.52it/s]\n 4%|▍ | 2/47 [00:00<00:19, 2.31it/s]\n 6%|▋ | 3/47 [00:01<00:15, 2.77it/s]\n 9%|▊ | 4/47 [00:01<00:14, 3.06it/s]\n 11%|█ | 5/47 [00:01<00:12, 3.25it/s]\n 13%|█▎ | 6/47 [00:02<00:12, 3.37it/s]\n 15%|█▍ | 7/47 [00:02<00:11, 3.45it/s]\n 17%|█▋ | 8/47 [00:02<00:11, 3.51it/s]\n 19%|█▉ | 9/47 [00:02<00:10, 3.55it/s]\n 21%|██▏ | 10/47 [00:03<00:10, 3.58it/s]\n 23%|██▎ | 11/47 [00:03<00:09, 3.61it/s]\n 26%|██▌ | 12/47 [00:03<00:09, 3.62it/s]\n 28%|██▊ | 13/47 [00:03<00:09, 3.64it/s]\n 30%|██▉ | 14/47 [00:04<00:09, 3.64it/s]\n 32%|███▏ | 15/47 [00:04<00:08, 3.65it/s]\n 34%|███▍ | 16/47 [00:04<00:08, 3.65it/s]\n 36%|███▌ | 17/47 [00:05<00:08, 3.65it/s]\n 38%|███▊ | 18/47 [00:05<00:07, 3.65it/s]\n 40%|████ | 19/47 [00:05<00:07, 3.65it/s]\n 43%|████▎ | 20/47 [00:05<00:07, 3.66it/s]\n 45%|████▍ | 21/47 [00:06<00:07, 3.65it/s]\n 47%|████▋ | 22/47 [00:06<00:06, 3.65it/s]\n 49%|████▉ | 23/47 [00:06<00:06, 3.65it/s]\n 51%|█████ | 24/47 [00:06<00:06, 3.65it/s]\n 53%|█████▎ | 25/47 [00:07<00:06, 3.65it/s]\n 55%|█████▌ | 26/47 [00:07<00:05, 3.65it/s]\n 57%|█████▋ | 27/47 [00:07<00:05, 3.65it/s]\n 60%|█████▉ | 28/47 [00:08<00:05, 3.65it/s]\n 62%|██████▏ | 29/47 [00:08<00:04, 3.65it/s]\n 64%|██████▍ | 30/47 [00:08<00:04, 3.65it/s]\n 66%|██████▌ | 31/47 [00:08<00:04, 3.65it/s]\n 68%|██████▊ | 32/47 [00:09<00:04, 3.65it/s]\n 70%|███████ | 33/47 [00:09<00:03, 3.64it/s]\n 72%|███████▏ | 34/47 [00:09<00:03, 3.64it/s]\n 74%|███████▍ | 35/47 [00:09<00:03, 3.64it/s]\n 77%|███████▋ | 36/47 [00:10<00:03, 3.65it/s]\n 79%|███████▊ | 37/47 [00:10<00:02, 3.65it/s]\n 81%|████████ | 38/47 [00:10<00:02, 3.65it/s]\n 83%|████████▎ | 39/47 [00:11<00:02, 3.65it/s]\n 85%|████████▌ | 40/47 [00:11<00:01, 3.65it/s]\n 87%|████████▋ | 41/47 [00:11<00:01, 3.65it/s]\n 89%|████████▉ | 42/47 [00:11<00:01, 3.64it/s]\n 91%|█████████▏| 43/47 [00:12<00:01, 3.64it/s]\n 94%|█████████▎| 44/47 [00:12<00:00, 3.64it/s]\n 96%|█████████▌| 45/47 [00:12<00:00, 3.64it/s]\n 98%|█████████▊| 46/47 [00:12<00:00, 3.65it/s]\n100%|██████████| 47/47 [00:13<00:00, 3.64it/s]\n100%|██████████| 47/47 [00:13<00:00, 3.54it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 3.90it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 4.08it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.14it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.10it/s]", "metrics": { "predict_time": 19.250594, "total_time": 20.792937 }, "output": [ "https://replicate.delivery/pbxt/j47zQMM9oeX2TaWx2U5QHl7CF4kqZNtlasH4Qki45QLV6QZJA/out-0.png" ], "started_at": "2024-05-09T06:20:08.813343Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/3z0tge2jwxrgp0cfbg1b19wccc", "cancel": "https://api.replicate.com/v1/predictions/3z0tge2jwxrgp0cfbg1b19wccc/cancel" }, "version": "91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169" }
Generated inUsing seed: 10353 Ensuring enough disk space... Free disk space: 2063356452864 Downloading weights: https://replicate.delivery/pbxt/YFUPzbCukZIHIJc8sznL8AWfmYSXVL7fMGPgGG3gGUTe7CllA/trained_model.tar 2024-05-09T06:20:08Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/3102d728bde11c70 url=https://replicate.delivery/pbxt/YFUPzbCukZIHIJc8sznL8AWfmYSXVL7fMGPgGG3gGUTe7CllA/trained_model.tar 2024-05-09T06:20:10Z | INFO | [ Complete ] dest=/src/weights-cache/3102d728bde11c70 size="186 MB" total_elapsed=1.586s url=https://replicate.delivery/pbxt/YFUPzbCukZIHIJc8sznL8AWfmYSXVL7fMGPgGG3gGUTe7CllA/trained_model.tar b'' Downloaded weights in 1.7163019180297852 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: a photo of <s0><s1> car, racing other cars txt2img mode 0%| | 0/47 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/torch/nn/modules/conv.py:459: UserWarning: Applied workaround for CuDNN issue, install nvrtc.so (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:80.) return F.conv2d(input, weight, bias, self.stride, 2%|▏ | 1/47 [00:00<00:30, 1.52it/s] 4%|▍ | 2/47 [00:00<00:19, 2.31it/s] 6%|▋ | 3/47 [00:01<00:15, 2.77it/s] 9%|▊ | 4/47 [00:01<00:14, 3.06it/s] 11%|█ | 5/47 [00:01<00:12, 3.25it/s] 13%|█▎ | 6/47 [00:02<00:12, 3.37it/s] 15%|█▍ | 7/47 [00:02<00:11, 3.45it/s] 17%|█▋ | 8/47 [00:02<00:11, 3.51it/s] 19%|█▉ | 9/47 [00:02<00:10, 3.55it/s] 21%|██▏ | 10/47 [00:03<00:10, 3.58it/s] 23%|██▎ | 11/47 [00:03<00:09, 3.61it/s] 26%|██▌ | 12/47 [00:03<00:09, 3.62it/s] 28%|██▊ | 13/47 [00:03<00:09, 3.64it/s] 30%|██▉ | 14/47 [00:04<00:09, 3.64it/s] 32%|███▏ | 15/47 [00:04<00:08, 3.65it/s] 34%|███▍ | 16/47 [00:04<00:08, 3.65it/s] 36%|███▌ | 17/47 [00:05<00:08, 3.65it/s] 38%|███▊ | 18/47 [00:05<00:07, 3.65it/s] 40%|████ | 19/47 [00:05<00:07, 3.65it/s] 43%|████▎ | 20/47 [00:05<00:07, 3.66it/s] 45%|████▍ | 21/47 [00:06<00:07, 3.65it/s] 47%|████▋ | 22/47 [00:06<00:06, 3.65it/s] 49%|████▉ | 23/47 [00:06<00:06, 3.65it/s] 51%|█████ | 24/47 [00:06<00:06, 3.65it/s] 53%|█████▎ | 25/47 [00:07<00:06, 3.65it/s] 55%|█████▌ | 26/47 [00:07<00:05, 3.65it/s] 57%|█████▋ | 27/47 [00:07<00:05, 3.65it/s] 60%|█████▉ | 28/47 [00:08<00:05, 3.65it/s] 62%|██████▏ | 29/47 [00:08<00:04, 3.65it/s] 64%|██████▍ | 30/47 [00:08<00:04, 3.65it/s] 66%|██████▌ | 31/47 [00:08<00:04, 3.65it/s] 68%|██████▊ | 32/47 [00:09<00:04, 3.65it/s] 70%|███████ | 33/47 [00:09<00:03, 3.64it/s] 72%|███████▏ | 34/47 [00:09<00:03, 3.64it/s] 74%|███████▍ | 35/47 [00:09<00:03, 3.64it/s] 77%|███████▋ | 36/47 [00:10<00:03, 3.65it/s] 79%|███████▊ | 37/47 [00:10<00:02, 3.65it/s] 81%|████████ | 38/47 [00:10<00:02, 3.65it/s] 83%|████████▎ | 39/47 [00:11<00:02, 3.65it/s] 85%|████████▌ | 40/47 [00:11<00:01, 3.65it/s] 87%|████████▋ | 41/47 [00:11<00:01, 3.65it/s] 89%|████████▉ | 42/47 [00:11<00:01, 3.64it/s] 91%|█████████▏| 43/47 [00:12<00:01, 3.64it/s] 94%|█████████▎| 44/47 [00:12<00:00, 3.64it/s] 96%|█████████▌| 45/47 [00:12<00:00, 3.64it/s] 98%|█████████▊| 46/47 [00:12<00:00, 3.65it/s] 100%|██████████| 47/47 [00:13<00:00, 3.64it/s] 100%|██████████| 47/47 [00:13<00:00, 3.54it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 3.90it/s] 67%|██████▋ | 2/3 [00:00<00:00, 4.08it/s] 100%|██████████| 3/3 [00:00<00:00, 4.14it/s] 100%|██████████| 3/3 [00:00<00:00, 4.10it/s]
Prediction
fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169IDq11hgq58xnrgm0cfbg38j3xk00StatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a photo of TOK car, leading on a racetrack
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.7
- num_outputs
- 1
- refine_steps
- 0
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.95
- negative_prompt
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "a photo of TOK car, leading on a racetrack", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }
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 fszotyi/sdxl-car using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", { input: { width: 1024, height: 1024, prompt: "a photo of TOK car, leading on a racetrack", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.7, num_outputs: 1, refine_steps: 0, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.95, negative_prompt: "", 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 replicate
Import the client:import replicate
Run fszotyi/sdxl-car using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", input={ "width": 1024, "height": 1024, "prompt": "a photo of TOK car, leading on a racetrack", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.95, "negative_prompt": "", "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 fszotyi/sdxl-car 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": "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", "input": { "width": 1024, "height": 1024, "prompt": "a photo of TOK car, leading on a racetrack", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-05-09T06:25:05.516321Z", "created_at": "2024-05-09T06:24:51.437000Z", "data_removed": false, "error": null, "id": "q11hgq58xnrgm0cfbg38j3xk00", "input": { "width": 1024, "height": 1024, "prompt": "a photo of TOK car, leading on a racetrack", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 6764\nskipping loading .. weights already loaded\nPrompt: a photo of <s0><s1> car, leading on a racetrack\ntxt2img mode\n 0%| | 0/39 [00:00<?, ?it/s]\n 3%|▎ | 1/39 [00:00<00:10, 3.66it/s]\n 5%|▌ | 2/39 [00:00<00:10, 3.66it/s]\n 8%|▊ | 3/39 [00:00<00:09, 3.66it/s]\n 10%|█ | 4/39 [00:01<00:09, 3.66it/s]\n 13%|█▎ | 5/39 [00:01<00:09, 3.65it/s]\n 15%|█▌ | 6/39 [00:01<00:09, 3.65it/s]\n 18%|█▊ | 7/39 [00:01<00:08, 3.65it/s]\n 21%|██ | 8/39 [00:02<00:08, 3.65it/s]\n 23%|██▎ | 9/39 [00:02<00:08, 3.65it/s]\n 26%|██▌ | 10/39 [00:02<00:07, 3.64it/s]\n 28%|██▊ | 11/39 [00:03<00:07, 3.64it/s]\n 31%|███ | 12/39 [00:03<00:07, 3.64it/s]\n 33%|███▎ | 13/39 [00:03<00:07, 3.64it/s]\n 36%|███▌ | 14/39 [00:03<00:06, 3.64it/s]\n 38%|███▊ | 15/39 [00:04<00:06, 3.63it/s]\n 41%|████ | 16/39 [00:04<00:06, 3.63it/s]\n 44%|████▎ | 17/39 [00:04<00:06, 3.63it/s]\n 46%|████▌ | 18/39 [00:04<00:05, 3.63it/s]\n 49%|████▊ | 19/39 [00:05<00:05, 3.63it/s]\n 51%|█████▏ | 20/39 [00:05<00:05, 3.63it/s]\n 54%|█████▍ | 21/39 [00:05<00:04, 3.63it/s]\n 56%|█████▋ | 22/39 [00:06<00:04, 3.63it/s]\n 59%|█████▉ | 23/39 [00:06<00:04, 3.63it/s]\n 62%|██████▏ | 24/39 [00:06<00:04, 3.63it/s]\n 64%|██████▍ | 25/39 [00:06<00:03, 3.63it/s]\n 67%|██████▋ | 26/39 [00:07<00:03, 3.63it/s]\n 69%|██████▉ | 27/39 [00:07<00:03, 3.63it/s]\n 72%|███████▏ | 28/39 [00:07<00:03, 3.63it/s]\n 74%|███████▍ | 29/39 [00:07<00:02, 3.63it/s]\n 77%|███████▋ | 30/39 [00:08<00:02, 3.63it/s]\n 79%|███████▉ | 31/39 [00:08<00:02, 3.63it/s]\n 82%|████████▏ | 32/39 [00:08<00:01, 3.63it/s]\n 85%|████████▍ | 33/39 [00:09<00:01, 3.63it/s]\n 87%|████████▋ | 34/39 [00:09<00:01, 3.63it/s]\n 90%|████████▉ | 35/39 [00:09<00:01, 3.63it/s]\n 92%|█████████▏| 36/39 [00:09<00:00, 3.63it/s]\n 95%|█████████▍| 37/39 [00:10<00:00, 3.63it/s]\n 97%|█████████▋| 38/39 [00:10<00:00, 3.63it/s]\n100%|██████████| 39/39 [00:10<00:00, 3.63it/s]\n100%|██████████| 39/39 [00:10<00:00, 3.63it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 4.22it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 4.21it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.20it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.20it/s]", "metrics": { "predict_time": 14.041444, "total_time": 14.079321 }, "output": [ "https://replicate.delivery/pbxt/CKrZVlnFF26vGpDKff3pKdCEkUslGE0PzxDxkcokIGVA5hySA/out-0.png" ], "started_at": "2024-05-09T06:24:51.474877Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/q11hgq58xnrgm0cfbg38j3xk00", "cancel": "https://api.replicate.com/v1/predictions/q11hgq58xnrgm0cfbg38j3xk00/cancel" }, "version": "91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169" }
Generated inUsing seed: 6764 skipping loading .. weights already loaded Prompt: a photo of <s0><s1> car, leading on a racetrack txt2img mode 0%| | 0/39 [00:00<?, ?it/s] 3%|▎ | 1/39 [00:00<00:10, 3.66it/s] 5%|▌ | 2/39 [00:00<00:10, 3.66it/s] 8%|▊ | 3/39 [00:00<00:09, 3.66it/s] 10%|█ | 4/39 [00:01<00:09, 3.66it/s] 13%|█▎ | 5/39 [00:01<00:09, 3.65it/s] 15%|█▌ | 6/39 [00:01<00:09, 3.65it/s] 18%|█▊ | 7/39 [00:01<00:08, 3.65it/s] 21%|██ | 8/39 [00:02<00:08, 3.65it/s] 23%|██▎ | 9/39 [00:02<00:08, 3.65it/s] 26%|██▌ | 10/39 [00:02<00:07, 3.64it/s] 28%|██▊ | 11/39 [00:03<00:07, 3.64it/s] 31%|███ | 12/39 [00:03<00:07, 3.64it/s] 33%|███▎ | 13/39 [00:03<00:07, 3.64it/s] 36%|███▌ | 14/39 [00:03<00:06, 3.64it/s] 38%|███▊ | 15/39 [00:04<00:06, 3.63it/s] 41%|████ | 16/39 [00:04<00:06, 3.63it/s] 44%|████▎ | 17/39 [00:04<00:06, 3.63it/s] 46%|████▌ | 18/39 [00:04<00:05, 3.63it/s] 49%|████▊ | 19/39 [00:05<00:05, 3.63it/s] 51%|█████▏ | 20/39 [00:05<00:05, 3.63it/s] 54%|█████▍ | 21/39 [00:05<00:04, 3.63it/s] 56%|█████▋ | 22/39 [00:06<00:04, 3.63it/s] 59%|█████▉ | 23/39 [00:06<00:04, 3.63it/s] 62%|██████▏ | 24/39 [00:06<00:04, 3.63it/s] 64%|██████▍ | 25/39 [00:06<00:03, 3.63it/s] 67%|██████▋ | 26/39 [00:07<00:03, 3.63it/s] 69%|██████▉ | 27/39 [00:07<00:03, 3.63it/s] 72%|███████▏ | 28/39 [00:07<00:03, 3.63it/s] 74%|███████▍ | 29/39 [00:07<00:02, 3.63it/s] 77%|███████▋ | 30/39 [00:08<00:02, 3.63it/s] 79%|███████▉ | 31/39 [00:08<00:02, 3.63it/s] 82%|████████▏ | 32/39 [00:08<00:01, 3.63it/s] 85%|████████▍ | 33/39 [00:09<00:01, 3.63it/s] 87%|████████▋ | 34/39 [00:09<00:01, 3.63it/s] 90%|████████▉ | 35/39 [00:09<00:01, 3.63it/s] 92%|█████████▏| 36/39 [00:09<00:00, 3.63it/s] 95%|█████████▍| 37/39 [00:10<00:00, 3.63it/s] 97%|█████████▋| 38/39 [00:10<00:00, 3.63it/s] 100%|██████████| 39/39 [00:10<00:00, 3.63it/s] 100%|██████████| 39/39 [00:10<00:00, 3.63it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 4.22it/s] 67%|██████▋ | 2/3 [00:00<00:00, 4.21it/s] 100%|██████████| 3/3 [00:00<00:00, 4.20it/s] 100%|██████████| 3/3 [00:00<00:00, 4.20it/s]
Prediction
fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169IDt0cx9139kxrgj0cfbg3rk46etmStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a photo of TOK car, on a road in malibu
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.7
- num_outputs
- 1
- refine_steps
- 0
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.95
- negative_prompt
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "a photo of TOK car, on a road in malibu", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }
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 fszotyi/sdxl-car using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", { input: { width: 1024, height: 1024, prompt: "a photo of TOK car, on a road in malibu", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.7, num_outputs: 1, refine_steps: 0, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.95, negative_prompt: "", 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 replicate
Import the client:import replicate
Run fszotyi/sdxl-car using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", input={ "width": 1024, "height": 1024, "prompt": "a photo of TOK car, on a road in malibu", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.95, "negative_prompt": "", "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 fszotyi/sdxl-car 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": "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", "input": { "width": 1024, "height": 1024, "prompt": "a photo of TOK car, on a road in malibu", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-05-09T06:26:05.791043Z", "created_at": "2024-05-09T06:25:40.767000Z", "data_removed": false, "error": null, "id": "t0cx9139kxrgj0cfbg3rk46etm", "input": { "width": 1024, "height": 1024, "prompt": "a photo of TOK car, on a road in malibu", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 12537\nEnsuring enough disk space...\nFree disk space: 2250122362880\nDownloading weights: https://replicate.delivery/pbxt/YFUPzbCukZIHIJc8sznL8AWfmYSXVL7fMGPgGG3gGUTe7CllA/trained_model.tar\n2024-05-09T06:25:48Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/3102d728bde11c70 url=https://replicate.delivery/pbxt/YFUPzbCukZIHIJc8sznL8AWfmYSXVL7fMGPgGG3gGUTe7CllA/trained_model.tar\n2024-05-09T06:25:49Z | INFO | [ Complete ] dest=/src/weights-cache/3102d728bde11c70 size=\"186 MB\" total_elapsed=0.680s url=https://replicate.delivery/pbxt/YFUPzbCukZIHIJc8sznL8AWfmYSXVL7fMGPgGG3gGUTe7CllA/trained_model.tar\nb''\nDownloaded weights in 0.7925825119018555 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a photo of <s0><s1> car, on a road in malibu\ntxt2img mode\n 0%| | 0/47 [00:00<?, ?it/s]\n 2%|▏ | 1/47 [00:00<00:12, 3.69it/s]\n 4%|▍ | 2/47 [00:00<00:12, 3.68it/s]\n 6%|▋ | 3/47 [00:00<00:11, 3.67it/s]\n 9%|▊ | 4/47 [00:01<00:11, 3.66it/s]\n 11%|█ | 5/47 [00:01<00:11, 3.66it/s]\n 13%|█▎ | 6/47 [00:01<00:11, 3.66it/s]\n 15%|█▍ | 7/47 [00:01<00:10, 3.66it/s]\n 17%|█▋ | 8/47 [00:02<00:10, 3.65it/s]\n 19%|█▉ | 9/47 [00:02<00:10, 3.65it/s]\n 21%|██▏ | 10/47 [00:02<00:10, 3.65it/s]\n 23%|██▎ | 11/47 [00:03<00:09, 3.65it/s]\n 26%|██▌ | 12/47 [00:03<00:09, 3.64it/s]\n 28%|██▊ | 13/47 [00:03<00:09, 3.64it/s]\n 30%|██▉ | 14/47 [00:03<00:09, 3.64it/s]\n 32%|███▏ | 15/47 [00:04<00:08, 3.64it/s]\n 34%|███▍ | 16/47 [00:04<00:08, 3.64it/s]\n 36%|███▌ | 17/47 [00:04<00:08, 3.64it/s]\n 38%|███▊ | 18/47 [00:04<00:07, 3.64it/s]\n 40%|████ | 19/47 [00:05<00:07, 3.64it/s]\n 43%|████▎ | 20/47 [00:05<00:07, 3.63it/s]\n 45%|████▍ | 21/47 [00:05<00:07, 3.64it/s]\n 47%|████▋ | 22/47 [00:06<00:06, 3.64it/s]\n 49%|████▉ | 23/47 [00:06<00:06, 3.63it/s]\n 51%|█████ | 24/47 [00:06<00:06, 3.63it/s]\n 53%|█████▎ | 25/47 [00:06<00:06, 3.63it/s]\n 55%|█████▌ | 26/47 [00:07<00:05, 3.63it/s]\n 57%|█████▋ | 27/47 [00:07<00:05, 3.63it/s]\n 60%|█████▉ | 28/47 [00:07<00:05, 3.63it/s]\n 62%|██████▏ | 29/47 [00:07<00:04, 3.63it/s]\n 64%|██████▍ | 30/47 [00:08<00:04, 3.63it/s]\n 66%|██████▌ | 31/47 [00:08<00:04, 3.63it/s]\n 68%|██████▊ | 32/47 [00:08<00:04, 3.63it/s]\n 70%|███████ | 33/47 [00:09<00:03, 3.63it/s]\n 72%|███████▏ | 34/47 [00:09<00:03, 3.62it/s]\n 74%|███████▍ | 35/47 [00:09<00:03, 3.62it/s]\n 77%|███████▋ | 36/47 [00:09<00:03, 3.62it/s]\n 79%|███████▊ | 37/47 [00:10<00:02, 3.62it/s]\n 81%|████████ | 38/47 [00:10<00:02, 3.62it/s]\n 83%|████████▎ | 39/47 [00:10<00:02, 3.62it/s]\n 85%|████████▌ | 40/47 [00:10<00:01, 3.62it/s]\n 87%|████████▋ | 41/47 [00:11<00:01, 3.62it/s]\n 89%|████████▉ | 42/47 [00:11<00:01, 3.62it/s]\n 91%|█████████▏| 43/47 [00:11<00:01, 3.62it/s]\n 94%|█████████▎| 44/47 [00:12<00:00, 3.62it/s]\n 96%|█████████▌| 45/47 [00:12<00:00, 3.62it/s]\n 98%|█████████▊| 46/47 [00:12<00:00, 3.62it/s]\n100%|██████████| 47/47 [00:12<00:00, 3.63it/s]\n100%|██████████| 47/47 [00:12<00:00, 3.64it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 4.19it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 4.18it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.18it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.18it/s]", "metrics": { "predict_time": 17.399088, "total_time": 25.024043 }, "output": [ "https://replicate.delivery/pbxt/eFiitFanAzQLDSpFDWSsazvs4ICyZDQjxFnLAFLRebf5zDllA/out-0.png" ], "started_at": "2024-05-09T06:25:48.391955Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/t0cx9139kxrgj0cfbg3rk46etm", "cancel": "https://api.replicate.com/v1/predictions/t0cx9139kxrgj0cfbg3rk46etm/cancel" }, "version": "91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169" }
Generated inUsing seed: 12537 Ensuring enough disk space... Free disk space: 2250122362880 Downloading weights: https://replicate.delivery/pbxt/YFUPzbCukZIHIJc8sznL8AWfmYSXVL7fMGPgGG3gGUTe7CllA/trained_model.tar 2024-05-09T06:25:48Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/3102d728bde11c70 url=https://replicate.delivery/pbxt/YFUPzbCukZIHIJc8sznL8AWfmYSXVL7fMGPgGG3gGUTe7CllA/trained_model.tar 2024-05-09T06:25:49Z | INFO | [ Complete ] dest=/src/weights-cache/3102d728bde11c70 size="186 MB" total_elapsed=0.680s url=https://replicate.delivery/pbxt/YFUPzbCukZIHIJc8sznL8AWfmYSXVL7fMGPgGG3gGUTe7CllA/trained_model.tar b'' Downloaded weights in 0.7925825119018555 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: a photo of <s0><s1> car, on a road in malibu txt2img mode 0%| | 0/47 [00:00<?, ?it/s] 2%|▏ | 1/47 [00:00<00:12, 3.69it/s] 4%|▍ | 2/47 [00:00<00:12, 3.68it/s] 6%|▋ | 3/47 [00:00<00:11, 3.67it/s] 9%|▊ | 4/47 [00:01<00:11, 3.66it/s] 11%|█ | 5/47 [00:01<00:11, 3.66it/s] 13%|█▎ | 6/47 [00:01<00:11, 3.66it/s] 15%|█▍ | 7/47 [00:01<00:10, 3.66it/s] 17%|█▋ | 8/47 [00:02<00:10, 3.65it/s] 19%|█▉ | 9/47 [00:02<00:10, 3.65it/s] 21%|██▏ | 10/47 [00:02<00:10, 3.65it/s] 23%|██▎ | 11/47 [00:03<00:09, 3.65it/s] 26%|██▌ | 12/47 [00:03<00:09, 3.64it/s] 28%|██▊ | 13/47 [00:03<00:09, 3.64it/s] 30%|██▉ | 14/47 [00:03<00:09, 3.64it/s] 32%|███▏ | 15/47 [00:04<00:08, 3.64it/s] 34%|███▍ | 16/47 [00:04<00:08, 3.64it/s] 36%|███▌ | 17/47 [00:04<00:08, 3.64it/s] 38%|███▊ | 18/47 [00:04<00:07, 3.64it/s] 40%|████ | 19/47 [00:05<00:07, 3.64it/s] 43%|████▎ | 20/47 [00:05<00:07, 3.63it/s] 45%|████▍ | 21/47 [00:05<00:07, 3.64it/s] 47%|████▋ | 22/47 [00:06<00:06, 3.64it/s] 49%|████▉ | 23/47 [00:06<00:06, 3.63it/s] 51%|█████ | 24/47 [00:06<00:06, 3.63it/s] 53%|█████▎ | 25/47 [00:06<00:06, 3.63it/s] 55%|█████▌ | 26/47 [00:07<00:05, 3.63it/s] 57%|█████▋ | 27/47 [00:07<00:05, 3.63it/s] 60%|█████▉ | 28/47 [00:07<00:05, 3.63it/s] 62%|██████▏ | 29/47 [00:07<00:04, 3.63it/s] 64%|██████▍ | 30/47 [00:08<00:04, 3.63it/s] 66%|██████▌ | 31/47 [00:08<00:04, 3.63it/s] 68%|██████▊ | 32/47 [00:08<00:04, 3.63it/s] 70%|███████ | 33/47 [00:09<00:03, 3.63it/s] 72%|███████▏ | 34/47 [00:09<00:03, 3.62it/s] 74%|███████▍ | 35/47 [00:09<00:03, 3.62it/s] 77%|███████▋ | 36/47 [00:09<00:03, 3.62it/s] 79%|███████▊ | 37/47 [00:10<00:02, 3.62it/s] 81%|████████ | 38/47 [00:10<00:02, 3.62it/s] 83%|████████▎ | 39/47 [00:10<00:02, 3.62it/s] 85%|████████▌ | 40/47 [00:10<00:01, 3.62it/s] 87%|████████▋ | 41/47 [00:11<00:01, 3.62it/s] 89%|████████▉ | 42/47 [00:11<00:01, 3.62it/s] 91%|█████████▏| 43/47 [00:11<00:01, 3.62it/s] 94%|█████████▎| 44/47 [00:12<00:00, 3.62it/s] 96%|█████████▌| 45/47 [00:12<00:00, 3.62it/s] 98%|█████████▊| 46/47 [00:12<00:00, 3.62it/s] 100%|██████████| 47/47 [00:12<00:00, 3.63it/s] 100%|██████████| 47/47 [00:12<00:00, 3.64it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 4.19it/s] 67%|██████▋ | 2/3 [00:00<00:00, 4.18it/s] 100%|██████████| 3/3 [00:00<00:00, 4.18it/s] 100%|██████████| 3/3 [00:00<00:00, 4.18it/s]
Prediction
fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169ID0xzmdvwg6hrgg0cfbg49zqdhx4StatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a photo of TOK car, on a road in malibu full of palm trees
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.7
- num_outputs
- 1
- refine_steps
- 0
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.95
- negative_prompt
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "a photo of TOK car, on a road in malibu full of palm trees", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }
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 fszotyi/sdxl-car using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", { input: { width: 1024, height: 1024, prompt: "a photo of TOK car, on a road in malibu full of palm trees", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.7, num_outputs: 1, refine_steps: 0, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.95, negative_prompt: "", 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 replicate
Import the client:import replicate
Run fszotyi/sdxl-car using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", input={ "width": 1024, "height": 1024, "prompt": "a photo of TOK car, on a road in malibu full of palm trees", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.95, "negative_prompt": "", "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 fszotyi/sdxl-car 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": "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", "input": { "width": 1024, "height": 1024, "prompt": "a photo of TOK car, on a road in malibu full of palm trees", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-05-09T06:27:15.497795Z", "created_at": "2024-05-09T06:26:56.180000Z", "data_removed": false, "error": null, "id": "0xzmdvwg6hrgg0cfbg49zqdhx4", "input": { "width": 1024, "height": 1024, "prompt": "a photo of TOK car, on a road in malibu full of palm trees", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 1880\nEnsuring enough disk space...\nFree disk space: 1753550262272\nDownloading weights: https://replicate.delivery/pbxt/YFUPzbCukZIHIJc8sznL8AWfmYSXVL7fMGPgGG3gGUTe7CllA/trained_model.tar\n2024-05-09T06:26:58Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/3102d728bde11c70 url=https://replicate.delivery/pbxt/YFUPzbCukZIHIJc8sznL8AWfmYSXVL7fMGPgGG3gGUTe7CllA/trained_model.tar\n2024-05-09T06:26:59Z | INFO | [ Complete ] dest=/src/weights-cache/3102d728bde11c70 size=\"186 MB\" total_elapsed=0.652s url=https://replicate.delivery/pbxt/YFUPzbCukZIHIJc8sznL8AWfmYSXVL7fMGPgGG3gGUTe7CllA/trained_model.tar\nb''\nDownloaded weights in 0.7809116840362549 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a photo of <s0><s1> car, on a road in malibu full of palm trees\ntxt2img mode\n 0%| | 0/47 [00:00<?, ?it/s]\n 2%|▏ | 1/47 [00:00<00:12, 3.65it/s]\n 4%|▍ | 2/47 [00:00<00:12, 3.64it/s]\n 6%|▋ | 3/47 [00:00<00:12, 3.64it/s]\n 9%|▊ | 4/47 [00:01<00:11, 3.64it/s]\n 11%|█ | 5/47 [00:01<00:11, 3.64it/s]\n 13%|█▎ | 6/47 [00:01<00:11, 3.64it/s]\n 15%|█▍ | 7/47 [00:01<00:10, 3.64it/s]\n 17%|█▋ | 8/47 [00:02<00:10, 3.64it/s]\n 19%|█▉ | 9/47 [00:02<00:10, 3.63it/s]\n 21%|██▏ | 10/47 [00:02<00:10, 3.63it/s]\n 23%|██▎ | 11/47 [00:03<00:09, 3.63it/s]\n 26%|██▌ | 12/47 [00:03<00:09, 3.63it/s]\n 28%|██▊ | 13/47 [00:03<00:09, 3.63it/s]\n 30%|██▉ | 14/47 [00:03<00:09, 3.63it/s]\n 32%|███▏ | 15/47 [00:04<00:08, 3.63it/s]\n 34%|███▍ | 16/47 [00:04<00:08, 3.63it/s]\n 36%|███▌ | 17/47 [00:04<00:08, 3.63it/s]\n 38%|███▊ | 18/47 [00:04<00:07, 3.63it/s]\n 40%|████ | 19/47 [00:05<00:07, 3.62it/s]\n 43%|████▎ | 20/47 [00:05<00:07, 3.62it/s]\n 45%|████▍ | 21/47 [00:05<00:07, 3.62it/s]\n 47%|████▋ | 22/47 [00:06<00:06, 3.62it/s]\n 49%|████▉ | 23/47 [00:06<00:06, 3.62it/s]\n 51%|█████ | 24/47 [00:06<00:06, 3.62it/s]\n 53%|█████▎ | 25/47 [00:06<00:06, 3.62it/s]\n 55%|█████▌ | 26/47 [00:07<00:05, 3.62it/s]\n 57%|█████▋ | 27/47 [00:07<00:05, 3.62it/s]\n 60%|█████▉ | 28/47 [00:07<00:05, 3.62it/s]\n 62%|██████▏ | 29/47 [00:07<00:04, 3.61it/s]\n 64%|██████▍ | 30/47 [00:08<00:04, 3.61it/s]\n 66%|██████▌ | 31/47 [00:08<00:04, 3.61it/s]\n 68%|██████▊ | 32/47 [00:08<00:04, 3.61it/s]\n 70%|███████ | 33/47 [00:09<00:03, 3.61it/s]\n 72%|███████▏ | 34/47 [00:09<00:03, 3.61it/s]\n 74%|███████▍ | 35/47 [00:09<00:03, 3.61it/s]\n 77%|███████▋ | 36/47 [00:09<00:03, 3.61it/s]\n 79%|███████▊ | 37/47 [00:10<00:02, 3.61it/s]\n 81%|████████ | 38/47 [00:10<00:02, 3.61it/s]\n 83%|████████▎ | 39/47 [00:10<00:02, 3.61it/s]\n 85%|████████▌ | 40/47 [00:11<00:01, 3.61it/s]\n 87%|████████▋ | 41/47 [00:11<00:01, 3.61it/s]\n 89%|████████▉ | 42/47 [00:11<00:01, 3.61it/s]\n 91%|█████████▏| 43/47 [00:11<00:01, 3.61it/s]\n 94%|█████████▎| 44/47 [00:12<00:00, 3.61it/s]\n 96%|█████████▌| 45/47 [00:12<00:00, 3.61it/s]\n 98%|█████████▊| 46/47 [00:12<00:00, 3.60it/s]\n100%|██████████| 47/47 [00:12<00:00, 3.60it/s]\n100%|██████████| 47/47 [00:12<00:00, 3.62it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 3.86it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 4.04it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.10it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.06it/s]", "metrics": { "predict_time": 17.249811, "total_time": 19.317795 }, "output": [ "https://replicate.delivery/pbxt/OBHzuk1BMEK5EZ2gKM1I650RAeH1F50S8ATay11SaIRh9QZJA/out-0.png" ], "started_at": "2024-05-09T06:26:58.247984Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/0xzmdvwg6hrgg0cfbg49zqdhx4", "cancel": "https://api.replicate.com/v1/predictions/0xzmdvwg6hrgg0cfbg49zqdhx4/cancel" }, "version": "91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169" }
Generated inUsing seed: 1880 Ensuring enough disk space... Free disk space: 1753550262272 Downloading weights: https://replicate.delivery/pbxt/YFUPzbCukZIHIJc8sznL8AWfmYSXVL7fMGPgGG3gGUTe7CllA/trained_model.tar 2024-05-09T06:26:58Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/3102d728bde11c70 url=https://replicate.delivery/pbxt/YFUPzbCukZIHIJc8sznL8AWfmYSXVL7fMGPgGG3gGUTe7CllA/trained_model.tar 2024-05-09T06:26:59Z | INFO | [ Complete ] dest=/src/weights-cache/3102d728bde11c70 size="186 MB" total_elapsed=0.652s url=https://replicate.delivery/pbxt/YFUPzbCukZIHIJc8sznL8AWfmYSXVL7fMGPgGG3gGUTe7CllA/trained_model.tar b'' Downloaded weights in 0.7809116840362549 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: a photo of <s0><s1> car, on a road in malibu full of palm trees txt2img mode 0%| | 0/47 [00:00<?, ?it/s] 2%|▏ | 1/47 [00:00<00:12, 3.65it/s] 4%|▍ | 2/47 [00:00<00:12, 3.64it/s] 6%|▋ | 3/47 [00:00<00:12, 3.64it/s] 9%|▊ | 4/47 [00:01<00:11, 3.64it/s] 11%|█ | 5/47 [00:01<00:11, 3.64it/s] 13%|█▎ | 6/47 [00:01<00:11, 3.64it/s] 15%|█▍ | 7/47 [00:01<00:10, 3.64it/s] 17%|█▋ | 8/47 [00:02<00:10, 3.64it/s] 19%|█▉ | 9/47 [00:02<00:10, 3.63it/s] 21%|██▏ | 10/47 [00:02<00:10, 3.63it/s] 23%|██▎ | 11/47 [00:03<00:09, 3.63it/s] 26%|██▌ | 12/47 [00:03<00:09, 3.63it/s] 28%|██▊ | 13/47 [00:03<00:09, 3.63it/s] 30%|██▉ | 14/47 [00:03<00:09, 3.63it/s] 32%|███▏ | 15/47 [00:04<00:08, 3.63it/s] 34%|███▍ | 16/47 [00:04<00:08, 3.63it/s] 36%|███▌ | 17/47 [00:04<00:08, 3.63it/s] 38%|███▊ | 18/47 [00:04<00:07, 3.63it/s] 40%|████ | 19/47 [00:05<00:07, 3.62it/s] 43%|████▎ | 20/47 [00:05<00:07, 3.62it/s] 45%|████▍ | 21/47 [00:05<00:07, 3.62it/s] 47%|████▋ | 22/47 [00:06<00:06, 3.62it/s] 49%|████▉ | 23/47 [00:06<00:06, 3.62it/s] 51%|█████ | 24/47 [00:06<00:06, 3.62it/s] 53%|█████▎ | 25/47 [00:06<00:06, 3.62it/s] 55%|█████▌ | 26/47 [00:07<00:05, 3.62it/s] 57%|█████▋ | 27/47 [00:07<00:05, 3.62it/s] 60%|█████▉ | 28/47 [00:07<00:05, 3.62it/s] 62%|██████▏ | 29/47 [00:07<00:04, 3.61it/s] 64%|██████▍ | 30/47 [00:08<00:04, 3.61it/s] 66%|██████▌ | 31/47 [00:08<00:04, 3.61it/s] 68%|██████▊ | 32/47 [00:08<00:04, 3.61it/s] 70%|███████ | 33/47 [00:09<00:03, 3.61it/s] 72%|███████▏ | 34/47 [00:09<00:03, 3.61it/s] 74%|███████▍ | 35/47 [00:09<00:03, 3.61it/s] 77%|███████▋ | 36/47 [00:09<00:03, 3.61it/s] 79%|███████▊ | 37/47 [00:10<00:02, 3.61it/s] 81%|████████ | 38/47 [00:10<00:02, 3.61it/s] 83%|████████▎ | 39/47 [00:10<00:02, 3.61it/s] 85%|████████▌ | 40/47 [00:11<00:01, 3.61it/s] 87%|████████▋ | 41/47 [00:11<00:01, 3.61it/s] 89%|████████▉ | 42/47 [00:11<00:01, 3.61it/s] 91%|█████████▏| 43/47 [00:11<00:01, 3.61it/s] 94%|█████████▎| 44/47 [00:12<00:00, 3.61it/s] 96%|█████████▌| 45/47 [00:12<00:00, 3.61it/s] 98%|█████████▊| 46/47 [00:12<00:00, 3.60it/s] 100%|██████████| 47/47 [00:12<00:00, 3.60it/s] 100%|██████████| 47/47 [00:12<00:00, 3.62it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 3.86it/s] 67%|██████▋ | 2/3 [00:00<00:00, 4.04it/s] 100%|██████████| 3/3 [00:00<00:00, 4.10it/s] 100%|██████████| 3/3 [00:00<00:00, 4.06it/s]
Prediction
fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169IDyjd7vmsdxdrgm0cfbg5vtx2crmStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a photo of TOK car, from behind in the sahara desert
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.7
- num_outputs
- 1
- refine_steps
- 0
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.95
- negative_prompt
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "a photo of TOK car, from behind in the sahara desert", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }
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 fszotyi/sdxl-car using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", { input: { width: 1024, height: 1024, prompt: "a photo of TOK car, from behind in the sahara desert", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.7, num_outputs: 1, refine_steps: 0, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.95, negative_prompt: "", 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 replicate
Import the client:import replicate
Run fszotyi/sdxl-car using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", input={ "width": 1024, "height": 1024, "prompt": "a photo of TOK car, from behind in the sahara desert", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.95, "negative_prompt": "", "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 fszotyi/sdxl-car 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": "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", "input": { "width": 1024, "height": 1024, "prompt": "a photo of TOK car, from behind in the sahara desert", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-05-09T06:30:02.973892Z", "created_at": "2024-05-09T06:29:47.627000Z", "data_removed": false, "error": null, "id": "yjd7vmsdxdrgm0cfbg5vtx2crm", "input": { "width": 1024, "height": 1024, "prompt": "a photo of TOK car, from behind in the sahara desert", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 18131\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a photo of <s0><s1> car, from behind in the sahara desert\ntxt2img mode\n 0%| | 0/39 [00:00<?, ?it/s]\n 3%|▎ | 1/39 [00:00<00:10, 3.69it/s]\n 5%|▌ | 2/39 [00:00<00:10, 3.68it/s]\n 8%|▊ | 3/39 [00:00<00:09, 3.67it/s]\n 10%|█ | 4/39 [00:01<00:09, 3.65it/s]\n 13%|█▎ | 5/39 [00:01<00:09, 3.66it/s]\n 15%|█▌ | 6/39 [00:01<00:09, 3.65it/s]\n 18%|█▊ | 7/39 [00:01<00:08, 3.65it/s]\n 21%|██ | 8/39 [00:02<00:08, 3.64it/s]\n 23%|██▎ | 9/39 [00:02<00:08, 3.65it/s]\n 26%|██▌ | 10/39 [00:02<00:07, 3.65it/s]\n 28%|██▊ | 11/39 [00:03<00:07, 3.64it/s]\n 31%|███ | 12/39 [00:03<00:07, 3.64it/s]\n 33%|███▎ | 13/39 [00:03<00:07, 3.64it/s]\n 36%|███▌ | 14/39 [00:03<00:06, 3.64it/s]\n 38%|███▊ | 15/39 [00:04<00:06, 3.64it/s]\n 41%|████ | 16/39 [00:04<00:06, 3.64it/s]\n 44%|████▎ | 17/39 [00:04<00:06, 3.64it/s]\n 46%|████▌ | 18/39 [00:04<00:05, 3.64it/s]\n 49%|████▊ | 19/39 [00:05<00:05, 3.63it/s]\n 51%|█████▏ | 20/39 [00:05<00:05, 3.64it/s]\n 54%|█████▍ | 21/39 [00:05<00:04, 3.64it/s]\n 56%|█████▋ | 22/39 [00:06<00:04, 3.64it/s]\n 59%|█████▉ | 23/39 [00:06<00:04, 3.64it/s]\n 62%|██████▏ | 24/39 [00:06<00:04, 3.65it/s]\n 64%|██████▍ | 25/39 [00:06<00:03, 3.65it/s]\n 67%|██████▋ | 26/39 [00:07<00:03, 3.65it/s]\n 69%|██████▉ | 27/39 [00:07<00:03, 3.66it/s]\n 72%|███████▏ | 28/39 [00:07<00:03, 3.66it/s]\n 74%|███████▍ | 29/39 [00:07<00:02, 3.66it/s]\n 77%|███████▋ | 30/39 [00:08<00:02, 3.66it/s]\n 79%|███████▉ | 31/39 [00:08<00:02, 3.66it/s]\n 82%|████████▏ | 32/39 [00:08<00:01, 3.66it/s]\n 85%|████████▍ | 33/39 [00:09<00:01, 3.66it/s]\n 87%|████████▋ | 34/39 [00:09<00:01, 3.65it/s]\n 90%|████████▉ | 35/39 [00:09<00:01, 3.65it/s]\n 92%|█████████▏| 36/39 [00:09<00:00, 3.65it/s]\n 95%|█████████▍| 37/39 [00:10<00:00, 3.65it/s]\n 97%|█████████▋| 38/39 [00:10<00:00, 3.66it/s]\n100%|██████████| 39/39 [00:10<00:00, 3.66it/s]\n100%|██████████| 39/39 [00:10<00:00, 3.65it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 4.26it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 4.23it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.21it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.22it/s]", "metrics": { "predict_time": 14.364846, "total_time": 15.346892 }, "output": [ "https://replicate.delivery/pbxt/84nvV0c946LXDxzUl9m1EDOenzcMQLcx5v5kqpBPGZv0ehySA/out-0.png" ], "started_at": "2024-05-09T06:29:48.609046Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/yjd7vmsdxdrgm0cfbg5vtx2crm", "cancel": "https://api.replicate.com/v1/predictions/yjd7vmsdxdrgm0cfbg5vtx2crm/cancel" }, "version": "91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169" }
Generated inUsing seed: 18131 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: a photo of <s0><s1> car, from behind in the sahara desert txt2img mode 0%| | 0/39 [00:00<?, ?it/s] 3%|▎ | 1/39 [00:00<00:10, 3.69it/s] 5%|▌ | 2/39 [00:00<00:10, 3.68it/s] 8%|▊ | 3/39 [00:00<00:09, 3.67it/s] 10%|█ | 4/39 [00:01<00:09, 3.65it/s] 13%|█▎ | 5/39 [00:01<00:09, 3.66it/s] 15%|█▌ | 6/39 [00:01<00:09, 3.65it/s] 18%|█▊ | 7/39 [00:01<00:08, 3.65it/s] 21%|██ | 8/39 [00:02<00:08, 3.64it/s] 23%|██▎ | 9/39 [00:02<00:08, 3.65it/s] 26%|██▌ | 10/39 [00:02<00:07, 3.65it/s] 28%|██▊ | 11/39 [00:03<00:07, 3.64it/s] 31%|███ | 12/39 [00:03<00:07, 3.64it/s] 33%|███▎ | 13/39 [00:03<00:07, 3.64it/s] 36%|███▌ | 14/39 [00:03<00:06, 3.64it/s] 38%|███▊ | 15/39 [00:04<00:06, 3.64it/s] 41%|████ | 16/39 [00:04<00:06, 3.64it/s] 44%|████▎ | 17/39 [00:04<00:06, 3.64it/s] 46%|████▌ | 18/39 [00:04<00:05, 3.64it/s] 49%|████▊ | 19/39 [00:05<00:05, 3.63it/s] 51%|█████▏ | 20/39 [00:05<00:05, 3.64it/s] 54%|█████▍ | 21/39 [00:05<00:04, 3.64it/s] 56%|█████▋ | 22/39 [00:06<00:04, 3.64it/s] 59%|█████▉ | 23/39 [00:06<00:04, 3.64it/s] 62%|██████▏ | 24/39 [00:06<00:04, 3.65it/s] 64%|██████▍ | 25/39 [00:06<00:03, 3.65it/s] 67%|██████▋ | 26/39 [00:07<00:03, 3.65it/s] 69%|██████▉ | 27/39 [00:07<00:03, 3.66it/s] 72%|███████▏ | 28/39 [00:07<00:03, 3.66it/s] 74%|███████▍ | 29/39 [00:07<00:02, 3.66it/s] 77%|███████▋ | 30/39 [00:08<00:02, 3.66it/s] 79%|███████▉ | 31/39 [00:08<00:02, 3.66it/s] 82%|████████▏ | 32/39 [00:08<00:01, 3.66it/s] 85%|████████▍ | 33/39 [00:09<00:01, 3.66it/s] 87%|████████▋ | 34/39 [00:09<00:01, 3.65it/s] 90%|████████▉ | 35/39 [00:09<00:01, 3.65it/s] 92%|█████████▏| 36/39 [00:09<00:00, 3.65it/s] 95%|█████████▍| 37/39 [00:10<00:00, 3.65it/s] 97%|█████████▋| 38/39 [00:10<00:00, 3.66it/s] 100%|██████████| 39/39 [00:10<00:00, 3.66it/s] 100%|██████████| 39/39 [00:10<00:00, 3.65it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 4.26it/s] 67%|██████▋ | 2/3 [00:00<00:00, 4.23it/s] 100%|██████████| 3/3 [00:00<00:00, 4.21it/s] 100%|██████████| 3/3 [00:00<00:00, 4.22it/s]
Prediction
fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169IDs3860zhk45rgm0cfbga85zwxawStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a photo of TOK car, on iceland near glaciers
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.7
- num_outputs
- 1
- refine_steps
- 0
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.95
- negative_prompt
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "a photo of TOK car, on iceland near glaciers", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }
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 fszotyi/sdxl-car using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", { input: { width: 1024, height: 1024, prompt: "a photo of TOK car, on iceland near glaciers", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.7, num_outputs: 1, refine_steps: 0, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.95, negative_prompt: "", 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 replicate
Import the client:import replicate
Run fszotyi/sdxl-car using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", input={ "width": 1024, "height": 1024, "prompt": "a photo of TOK car, on iceland near glaciers", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.95, "negative_prompt": "", "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 fszotyi/sdxl-car 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": "fszotyi/sdxl-car:91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169", "input": { "width": 1024, "height": 1024, "prompt": "a photo of TOK car, on iceland near glaciers", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-05-09T06:39:55.877918Z", "created_at": "2024-05-09T06:39:38.785000Z", "data_removed": false, "error": null, "id": "s3860zhk45rgm0cfbga85zwxaw", "input": { "width": 1024, "height": 1024, "prompt": "a photo of TOK car, on iceland near glaciers", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.7, "num_outputs": 1, "refine_steps": 0, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 63349\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a photo of <s0><s1> car, on iceland near glaciers\ntxt2img mode\n 0%| | 0/39 [00:00<?, ?it/s]\n 3%|▎ | 1/39 [00:00<00:10, 3.71it/s]\n 5%|▌ | 2/39 [00:00<00:10, 3.69it/s]\n 8%|▊ | 3/39 [00:00<00:09, 3.69it/s]\n 10%|█ | 4/39 [00:01<00:09, 3.68it/s]\n 13%|█▎ | 5/39 [00:01<00:09, 3.68it/s]\n 15%|█▌ | 6/39 [00:01<00:08, 3.68it/s]\n 18%|█▊ | 7/39 [00:01<00:08, 3.68it/s]\n 21%|██ | 8/39 [00:02<00:08, 3.68it/s]\n 23%|██▎ | 9/39 [00:02<00:08, 3.69it/s]\n 26%|██▌ | 10/39 [00:02<00:07, 3.70it/s]\n 28%|██▊ | 11/39 [00:02<00:07, 3.70it/s]\n 31%|███ | 12/39 [00:03<00:07, 3.69it/s]\n 33%|███▎ | 13/39 [00:03<00:07, 3.69it/s]\n 36%|███▌ | 14/39 [00:03<00:06, 3.70it/s]\n 38%|███▊ | 15/39 [00:04<00:06, 3.70it/s]\n 41%|████ | 16/39 [00:04<00:06, 3.70it/s]\n 44%|████▎ | 17/39 [00:04<00:05, 3.70it/s]\n 46%|████▌ | 18/39 [00:04<00:05, 3.70it/s]\n 49%|████▊ | 19/39 [00:05<00:05, 3.70it/s]\n 51%|█████▏ | 20/39 [00:05<00:05, 3.69it/s]\n 54%|█████▍ | 21/39 [00:05<00:04, 3.70it/s]\n 56%|█████▋ | 22/39 [00:05<00:04, 3.69it/s]\n 59%|█████▉ | 23/39 [00:06<00:04, 3.69it/s]\n 62%|██████▏ | 24/39 [00:06<00:04, 3.69it/s]\n 64%|██████▍ | 25/39 [00:06<00:03, 3.69it/s]\n 67%|██████▋ | 26/39 [00:07<00:03, 3.69it/s]\n 69%|██████▉ | 27/39 [00:07<00:03, 3.69it/s]\n 72%|███████▏ | 28/39 [00:07<00:02, 3.69it/s]\n 74%|███████▍ | 29/39 [00:07<00:02, 3.69it/s]\n 77%|███████▋ | 30/39 [00:08<00:02, 3.69it/s]\n 79%|███████▉ | 31/39 [00:08<00:02, 3.68it/s]\n 82%|████████▏ | 32/39 [00:08<00:01, 3.69it/s]\n 85%|████████▍ | 33/39 [00:08<00:01, 3.69it/s]\n 87%|████████▋ | 34/39 [00:09<00:01, 3.69it/s]\n 90%|████████▉ | 35/39 [00:09<00:01, 3.69it/s]\n 92%|█████████▏| 36/39 [00:09<00:00, 3.69it/s]\n 95%|█████████▍| 37/39 [00:10<00:00, 3.69it/s]\n 97%|█████████▋| 38/39 [00:10<00:00, 3.69it/s]\n100%|██████████| 39/39 [00:10<00:00, 3.69it/s]\n100%|██████████| 39/39 [00:10<00:00, 3.69it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 4.28it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 4.27it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.25it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.26it/s]", "metrics": { "predict_time": 14.44739, "total_time": 17.092918 }, "output": [ "https://replicate.delivery/pbxt/elxUTe3mGntGg0oriBgoC90Lc7dQ8Th4H4nnq0kVfLB1NEllA/out-0.png" ], "started_at": "2024-05-09T06:39:41.430528Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/s3860zhk45rgm0cfbga85zwxaw", "cancel": "https://api.replicate.com/v1/predictions/s3860zhk45rgm0cfbga85zwxaw/cancel" }, "version": "91fdae37502002f8b41d7c6b29037e0caa6787b0375e47a45afb01dfdf8f1169" }
Generated inUsing seed: 63349 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: a photo of <s0><s1> car, on iceland near glaciers txt2img mode 0%| | 0/39 [00:00<?, ?it/s] 3%|▎ | 1/39 [00:00<00:10, 3.71it/s] 5%|▌ | 2/39 [00:00<00:10, 3.69it/s] 8%|▊ | 3/39 [00:00<00:09, 3.69it/s] 10%|█ | 4/39 [00:01<00:09, 3.68it/s] 13%|█▎ | 5/39 [00:01<00:09, 3.68it/s] 15%|█▌ | 6/39 [00:01<00:08, 3.68it/s] 18%|█▊ | 7/39 [00:01<00:08, 3.68it/s] 21%|██ | 8/39 [00:02<00:08, 3.68it/s] 23%|██▎ | 9/39 [00:02<00:08, 3.69it/s] 26%|██▌ | 10/39 [00:02<00:07, 3.70it/s] 28%|██▊ | 11/39 [00:02<00:07, 3.70it/s] 31%|███ | 12/39 [00:03<00:07, 3.69it/s] 33%|███▎ | 13/39 [00:03<00:07, 3.69it/s] 36%|███▌ | 14/39 [00:03<00:06, 3.70it/s] 38%|███▊ | 15/39 [00:04<00:06, 3.70it/s] 41%|████ | 16/39 [00:04<00:06, 3.70it/s] 44%|████▎ | 17/39 [00:04<00:05, 3.70it/s] 46%|████▌ | 18/39 [00:04<00:05, 3.70it/s] 49%|████▊ | 19/39 [00:05<00:05, 3.70it/s] 51%|█████▏ | 20/39 [00:05<00:05, 3.69it/s] 54%|█████▍ | 21/39 [00:05<00:04, 3.70it/s] 56%|█████▋ | 22/39 [00:05<00:04, 3.69it/s] 59%|█████▉ | 23/39 [00:06<00:04, 3.69it/s] 62%|██████▏ | 24/39 [00:06<00:04, 3.69it/s] 64%|██████▍ | 25/39 [00:06<00:03, 3.69it/s] 67%|██████▋ | 26/39 [00:07<00:03, 3.69it/s] 69%|██████▉ | 27/39 [00:07<00:03, 3.69it/s] 72%|███████▏ | 28/39 [00:07<00:02, 3.69it/s] 74%|███████▍ | 29/39 [00:07<00:02, 3.69it/s] 77%|███████▋ | 30/39 [00:08<00:02, 3.69it/s] 79%|███████▉ | 31/39 [00:08<00:02, 3.68it/s] 82%|████████▏ | 32/39 [00:08<00:01, 3.69it/s] 85%|████████▍ | 33/39 [00:08<00:01, 3.69it/s] 87%|████████▋ | 34/39 [00:09<00:01, 3.69it/s] 90%|████████▉ | 35/39 [00:09<00:01, 3.69it/s] 92%|█████████▏| 36/39 [00:09<00:00, 3.69it/s] 95%|█████████▍| 37/39 [00:10<00:00, 3.69it/s] 97%|█████████▋| 38/39 [00:10<00:00, 3.69it/s] 100%|██████████| 39/39 [00:10<00:00, 3.69it/s] 100%|██████████| 39/39 [00:10<00:00, 3.69it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 4.28it/s] 67%|██████▋ | 2/3 [00:00<00:00, 4.27it/s] 100%|██████████| 3/3 [00:00<00:00, 4.25it/s] 100%|██████████| 3/3 [00:00<00:00, 4.26it/s]
Want to make some of these yourself?
Run this model