martintmv-git / sdxl-cinematic
SDXL Fine-tune on cinematic shots
- Public
- 348 runs
-
L40S
- SDXL fine-tune
Prediction
martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2IDu7obsalbnxy2f5goxmicvzlyauStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 512
- prompt
- A close-up of a scientist's face, intelligent and inquisitive, with a laboratory setting subtly out of focus behind, in the style of TOK, crisp, sharp, photorealistic, movie scene
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.8
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- cropped, worst quality, low quality, glitch, deformed, mutated, disfigured
- prompt_strength
- 0.8
- num_inference_steps
- 70
{ "width": 1024, "height": 512, "prompt": "A close-up of a scientist's face, intelligent and inquisitive, with a laboratory setting subtly out of focus behind, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run martintmv-git/sdxl-cinematic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", { input: { width: 1024, height: 512, prompt: "A close-up of a scientist's face, intelligent and inquisitive, with a laboratory setting subtly out of focus behind, in the style of TOK, crisp, sharp, photorealistic, movie scene", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.8, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", prompt_strength: 0.8, num_inference_steps: 70 } } ); // 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 martintmv-git/sdxl-cinematic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", input={ "width": 1024, "height": 512, "prompt": "A close-up of a scientist's face, intelligent and inquisitive, with a laboratory setting subtly out of focus behind, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run martintmv-git/sdxl-cinematic 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": "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", "input": { "width": 1024, "height": 512, "prompt": "A close-up of a scientist\'s face, intelligent and inquisitive, with a laboratory setting subtly out of focus behind, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-12-19T11:05:11.158424Z", "created_at": "2023-12-19T11:04:57.988341Z", "data_removed": false, "error": null, "id": "u7obsalbnxy2f5goxmicvzlyau", "input": { "width": 1024, "height": 512, "prompt": "A close-up of a scientist's face, intelligent and inquisitive, with a laboratory setting subtly out of focus behind, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 }, "logs": "Using seed: 3604\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A close-up of a scientist's face, intelligent and inquisitive, with a laboratory setting subtly out of focus behind, in the style of <s0><s1>, crisp, sharp, photorealistic, movie scene\ntxt2img mode\n 0%| | 0/44 [00:00<?, ?it/s]\n 2%|▏ | 1/44 [00:00<00:06, 6.49it/s]\n 5%|▍ | 2/44 [00:00<00:06, 6.92it/s]\n 7%|▋ | 3/44 [00:00<00:05, 7.06it/s]\n 9%|▉ | 4/44 [00:00<00:05, 7.12it/s]\n 11%|█▏ | 5/44 [00:00<00:05, 7.16it/s]\n 14%|█▎ | 6/44 [00:00<00:05, 7.18it/s]\n 16%|█▌ | 7/44 [00:00<00:05, 7.20it/s]\n 18%|█▊ | 8/44 [00:01<00:04, 7.23it/s]\n 20%|██ | 9/44 [00:01<00:04, 7.25it/s]\n 23%|██▎ | 10/44 [00:01<00:04, 7.26it/s]\n 25%|██▌ | 11/44 [00:01<00:04, 7.27it/s]\n 27%|██▋ | 12/44 [00:01<00:04, 7.28it/s]\n 30%|██▉ | 13/44 [00:01<00:04, 7.27it/s]\n 32%|███▏ | 14/44 [00:01<00:04, 7.27it/s]\n 34%|███▍ | 15/44 [00:02<00:03, 7.27it/s]\n 36%|███▋ | 16/44 [00:02<00:03, 7.28it/s]\n 39%|███▊ | 17/44 [00:02<00:03, 7.27it/s]\n 41%|████ | 18/44 [00:02<00:03, 7.27it/s]\n 43%|████▎ | 19/44 [00:02<00:03, 7.28it/s]\n 45%|████▌ | 20/44 [00:02<00:03, 7.27it/s]\n 48%|████▊ | 21/44 [00:02<00:03, 7.27it/s]\n 50%|█████ | 22/44 [00:03<00:03, 7.26it/s]\n 52%|█████▏ | 23/44 [00:03<00:02, 7.26it/s]\n 55%|█████▍ | 24/44 [00:03<00:02, 7.26it/s]\n 57%|█████▋ | 25/44 [00:03<00:02, 7.26it/s]\n 59%|█████▉ | 26/44 [00:03<00:02, 7.26it/s]\n 61%|██████▏ | 27/44 [00:03<00:02, 7.27it/s]\n 64%|██████▎ | 28/44 [00:03<00:02, 7.28it/s]\n 66%|██████▌ | 29/44 [00:04<00:02, 7.27it/s]\n 68%|██████▊ | 30/44 [00:04<00:01, 7.27it/s]\n 70%|███████ | 31/44 [00:04<00:01, 7.26it/s]\n 73%|███████▎ | 32/44 [00:04<00:01, 7.26it/s]\n 75%|███████▌ | 33/44 [00:04<00:01, 7.26it/s]\n 77%|███████▋ | 34/44 [00:04<00:01, 7.26it/s]\n 80%|███████▉ | 35/44 [00:04<00:01, 7.27it/s]\n 82%|████████▏ | 36/44 [00:04<00:01, 7.27it/s]\n 84%|████████▍ | 37/44 [00:05<00:00, 7.27it/s]\n 86%|████████▋ | 38/44 [00:05<00:00, 7.27it/s]\n 89%|████████▊ | 39/44 [00:05<00:00, 7.26it/s]\n 91%|█████████ | 40/44 [00:05<00:00, 7.21it/s]\n 93%|█████████▎| 41/44 [00:05<00:00, 7.23it/s]\n 95%|█████████▌| 42/44 [00:05<00:00, 7.24it/s]\n 98%|█████████▊| 43/44 [00:05<00:00, 7.25it/s]\n100%|██████████| 44/44 [00:06<00:00, 7.25it/s]\n100%|██████████| 44/44 [00:06<00:00, 7.24it/s]\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:00<00:01, 8.77it/s]\n 13%|█▎ | 2/15 [00:00<00:01, 8.68it/s]\n 20%|██ | 3/15 [00:00<00:01, 8.63it/s]\n 27%|██▋ | 4/15 [00:00<00:01, 8.60it/s]\n 33%|███▎ | 5/15 [00:00<00:01, 8.59it/s]\n 40%|████ | 6/15 [00:00<00:01, 8.59it/s]\n 47%|████▋ | 7/15 [00:00<00:00, 8.58it/s]\n 53%|█████▎ | 8/15 [00:00<00:00, 8.59it/s]\n 60%|██████ | 9/15 [00:01<00:00, 8.58it/s]\n 67%|██████▋ | 10/15 [00:01<00:00, 8.58it/s]\n 73%|███████▎ | 11/15 [00:01<00:00, 8.59it/s]\n 80%|████████ | 12/15 [00:01<00:00, 8.60it/s]\n 87%|████████▋ | 13/15 [00:01<00:00, 8.59it/s]\n 93%|█████████▎| 14/15 [00:01<00:00, 8.58it/s]\n100%|██████████| 15/15 [00:01<00:00, 8.56it/s]\n100%|██████████| 15/15 [00:01<00:00, 8.59it/s]", "metrics": { "predict_time": 9.84424, "total_time": 13.170083 }, "output": [ "https://replicate.delivery/pbxt/mAhvprs35c5mA1A86iZQPg8Ra6njucDolHb48mF29ut5q8gE/out-0.png" ], "started_at": "2023-12-19T11:05:01.314184Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/u7obsalbnxy2f5goxmicvzlyau", "cancel": "https://api.replicate.com/v1/predictions/u7obsalbnxy2f5goxmicvzlyau/cancel" }, "version": "40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2" }
Generated inUsing seed: 3604 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A close-up of a scientist's face, intelligent and inquisitive, with a laboratory setting subtly out of focus behind, in the style of <s0><s1>, crisp, sharp, photorealistic, movie scene txt2img mode 0%| | 0/44 [00:00<?, ?it/s] 2%|▏ | 1/44 [00:00<00:06, 6.49it/s] 5%|▍ | 2/44 [00:00<00:06, 6.92it/s] 7%|▋ | 3/44 [00:00<00:05, 7.06it/s] 9%|▉ | 4/44 [00:00<00:05, 7.12it/s] 11%|█▏ | 5/44 [00:00<00:05, 7.16it/s] 14%|█▎ | 6/44 [00:00<00:05, 7.18it/s] 16%|█▌ | 7/44 [00:00<00:05, 7.20it/s] 18%|█▊ | 8/44 [00:01<00:04, 7.23it/s] 20%|██ | 9/44 [00:01<00:04, 7.25it/s] 23%|██▎ | 10/44 [00:01<00:04, 7.26it/s] 25%|██▌ | 11/44 [00:01<00:04, 7.27it/s] 27%|██▋ | 12/44 [00:01<00:04, 7.28it/s] 30%|██▉ | 13/44 [00:01<00:04, 7.27it/s] 32%|███▏ | 14/44 [00:01<00:04, 7.27it/s] 34%|███▍ | 15/44 [00:02<00:03, 7.27it/s] 36%|███▋ | 16/44 [00:02<00:03, 7.28it/s] 39%|███▊ | 17/44 [00:02<00:03, 7.27it/s] 41%|████ | 18/44 [00:02<00:03, 7.27it/s] 43%|████▎ | 19/44 [00:02<00:03, 7.28it/s] 45%|████▌ | 20/44 [00:02<00:03, 7.27it/s] 48%|████▊ | 21/44 [00:02<00:03, 7.27it/s] 50%|█████ | 22/44 [00:03<00:03, 7.26it/s] 52%|█████▏ | 23/44 [00:03<00:02, 7.26it/s] 55%|█████▍ | 24/44 [00:03<00:02, 7.26it/s] 57%|█████▋ | 25/44 [00:03<00:02, 7.26it/s] 59%|█████▉ | 26/44 [00:03<00:02, 7.26it/s] 61%|██████▏ | 27/44 [00:03<00:02, 7.27it/s] 64%|██████▎ | 28/44 [00:03<00:02, 7.28it/s] 66%|██████▌ | 29/44 [00:04<00:02, 7.27it/s] 68%|██████▊ | 30/44 [00:04<00:01, 7.27it/s] 70%|███████ | 31/44 [00:04<00:01, 7.26it/s] 73%|███████▎ | 32/44 [00:04<00:01, 7.26it/s] 75%|███████▌ | 33/44 [00:04<00:01, 7.26it/s] 77%|███████▋ | 34/44 [00:04<00:01, 7.26it/s] 80%|███████▉ | 35/44 [00:04<00:01, 7.27it/s] 82%|████████▏ | 36/44 [00:04<00:01, 7.27it/s] 84%|████████▍ | 37/44 [00:05<00:00, 7.27it/s] 86%|████████▋ | 38/44 [00:05<00:00, 7.27it/s] 89%|████████▊ | 39/44 [00:05<00:00, 7.26it/s] 91%|█████████ | 40/44 [00:05<00:00, 7.21it/s] 93%|█████████▎| 41/44 [00:05<00:00, 7.23it/s] 95%|█████████▌| 42/44 [00:05<00:00, 7.24it/s] 98%|█████████▊| 43/44 [00:05<00:00, 7.25it/s] 100%|██████████| 44/44 [00:06<00:00, 7.25it/s] 100%|██████████| 44/44 [00:06<00:00, 7.24it/s] 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:00<00:01, 8.77it/s] 13%|█▎ | 2/15 [00:00<00:01, 8.68it/s] 20%|██ | 3/15 [00:00<00:01, 8.63it/s] 27%|██▋ | 4/15 [00:00<00:01, 8.60it/s] 33%|███▎ | 5/15 [00:00<00:01, 8.59it/s] 40%|████ | 6/15 [00:00<00:01, 8.59it/s] 47%|████▋ | 7/15 [00:00<00:00, 8.58it/s] 53%|█████▎ | 8/15 [00:00<00:00, 8.59it/s] 60%|██████ | 9/15 [00:01<00:00, 8.58it/s] 67%|██████▋ | 10/15 [00:01<00:00, 8.58it/s] 73%|███████▎ | 11/15 [00:01<00:00, 8.59it/s] 80%|████████ | 12/15 [00:01<00:00, 8.60it/s] 87%|████████▋ | 13/15 [00:01<00:00, 8.59it/s] 93%|█████████▎| 14/15 [00:01<00:00, 8.58it/s] 100%|██████████| 15/15 [00:01<00:00, 8.56it/s] 100%|██████████| 15/15 [00:01<00:00, 8.59it/s]
Prediction
martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2IDs6d265tb2naexpkhprtwm4hwo4StatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 512
- prompt
- old man outside, farmer, gray hair, casual clothes, late afternoon light, in the style of TOK, crisp, sharp, photorealistic, movie scene
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.8
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- cropped, worst quality, low quality, glitch, deformed, mutated, disfigured
- prompt_strength
- 0.8
- num_inference_steps
- 70
{ "width": 1024, "height": 512, "prompt": "old man outside, farmer, gray hair, casual clothes, late afternoon light, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run martintmv-git/sdxl-cinematic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", { input: { width: 1024, height: 512, prompt: "old man outside, farmer, gray hair, casual clothes, late afternoon light, in the style of TOK, crisp, sharp, photorealistic, movie scene", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.8, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", prompt_strength: 0.8, num_inference_steps: 70 } } ); // 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 martintmv-git/sdxl-cinematic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", input={ "width": 1024, "height": 512, "prompt": "old man outside, farmer, gray hair, casual clothes, late afternoon light, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run martintmv-git/sdxl-cinematic 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": "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", "input": { "width": 1024, "height": 512, "prompt": "old man outside, farmer, gray hair, casual clothes, late afternoon light, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-12-18T21:51:04.890906Z", "created_at": "2023-12-18T21:50:50.111224Z", "data_removed": false, "error": null, "id": "s6d265tb2naexpkhprtwm4hwo4", "input": { "width": 1024, "height": 512, "prompt": "old man outside, farmer, gray hair, casual clothes, late afternoon light, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 }, "logs": "Using seed: 35059\nEnsuring enough disk space...\nFree disk space: 2578913357824\nDownloading weights: https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar\n2023-12-18T21:50:53Z | INFO | [ Initiating ] dest=/src/weights-cache/ff016a5a915406b1 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar\n2023-12-18T21:50:54Z | INFO | [ Complete ] dest=/src/weights-cache/ff016a5a915406b1 size=\"186 MB\" total_elapsed=0.787s url=https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar\nb''\nDownloaded weights in 0.9149889945983887 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: old man outside, farmer, gray hair, casual clothes, late afternoon light, in the style of <s0><s1>, crisp, sharp, photorealistic, movie scene\ntxt2img mode\n 0%| | 0/44 [00:00<?, ?it/s]\n 2%|▏ | 1/44 [00:00<00:07, 5.55it/s]\n 5%|▍ | 2/44 [00:00<00:06, 6.45it/s]\n 7%|▋ | 3/44 [00:00<00:06, 6.76it/s]\n 9%|▉ | 4/44 [00:00<00:05, 6.92it/s]\n 11%|█▏ | 5/44 [00:00<00:05, 7.02it/s]\n 14%|█▎ | 6/44 [00:00<00:05, 7.08it/s]\n 16%|█▌ | 7/44 [00:01<00:05, 7.12it/s]\n 18%|█▊ | 8/44 [00:01<00:05, 7.16it/s]\n 20%|██ | 9/44 [00:01<00:04, 7.17it/s]\n 23%|██▎ | 10/44 [00:01<00:04, 7.18it/s]\n 25%|██▌ | 11/44 [00:01<00:04, 7.19it/s]\n 27%|██▋ | 12/44 [00:01<00:04, 7.19it/s]\n 30%|██▉ | 13/44 [00:01<00:04, 7.20it/s]\n 32%|███▏ | 14/44 [00:01<00:04, 7.20it/s]\n 34%|███▍ | 15/44 [00:02<00:04, 7.20it/s]\n 36%|███▋ | 16/44 [00:02<00:03, 7.19it/s]\n 39%|███▊ | 17/44 [00:02<00:03, 7.18it/s]\n 41%|████ | 18/44 [00:02<00:03, 7.18it/s]\n 43%|████▎ | 19/44 [00:02<00:03, 7.18it/s]\n 45%|████▌ | 20/44 [00:02<00:03, 7.18it/s]\n 48%|████▊ | 21/44 [00:02<00:03, 7.19it/s]\n 50%|█████ | 22/44 [00:03<00:03, 7.21it/s]\n 52%|█████▏ | 23/44 [00:03<00:02, 7.22it/s]\n 55%|█████▍ | 24/44 [00:03<00:02, 7.23it/s]\n 57%|█████▋ | 25/44 [00:03<00:02, 7.23it/s]\n 59%|█████▉ | 26/44 [00:03<00:02, 7.24it/s]\n 61%|██████▏ | 27/44 [00:03<00:02, 7.24it/s]\n 64%|██████▎ | 28/44 [00:03<00:02, 7.24it/s]\n 66%|██████▌ | 29/44 [00:04<00:02, 7.24it/s]\n 68%|██████▊ | 30/44 [00:04<00:01, 7.24it/s]\n 70%|███████ | 31/44 [00:04<00:01, 7.24it/s]\n 73%|███████▎ | 32/44 [00:04<00:01, 7.23it/s]\n 75%|███████▌ | 33/44 [00:04<00:01, 7.23it/s]\n 77%|███████▋ | 34/44 [00:04<00:01, 7.23it/s]\n 80%|███████▉ | 35/44 [00:04<00:01, 7.23it/s]\n 82%|████████▏ | 36/44 [00:05<00:01, 7.23it/s]\n 84%|████████▍ | 37/44 [00:05<00:00, 7.24it/s]\n 86%|████████▋ | 38/44 [00:05<00:00, 7.23it/s]\n 89%|████████▊ | 39/44 [00:05<00:00, 7.24it/s]\n 91%|█████████ | 40/44 [00:05<00:00, 7.24it/s]\n 93%|█████████▎| 41/44 [00:05<00:00, 7.24it/s]\n 95%|█████████▌| 42/44 [00:05<00:00, 7.23it/s]\n 98%|█████████▊| 43/44 [00:05<00:00, 7.23it/s]\n100%|██████████| 44/44 [00:06<00:00, 7.23it/s]\n100%|██████████| 44/44 [00:06<00:00, 7.17it/s]\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:00<00:01, 7.29it/s]\n 13%|█▎ | 2/15 [00:00<00:01, 7.99it/s]\n 20%|██ | 3/15 [00:00<00:01, 8.23it/s]\n 27%|██▋ | 4/15 [00:00<00:01, 8.36it/s]\n 33%|███▎ | 5/15 [00:00<00:01, 8.43it/s]\n 40%|████ | 6/15 [00:00<00:01, 8.46it/s]\n 47%|████▋ | 7/15 [00:00<00:00, 8.47it/s]\n 53%|█████▎ | 8/15 [00:00<00:00, 8.49it/s]\n 60%|██████ | 9/15 [00:01<00:00, 8.51it/s]\n 67%|██████▋ | 10/15 [00:01<00:00, 8.52it/s]\n 73%|███████▎ | 11/15 [00:01<00:00, 8.53it/s]\n 80%|████████ | 12/15 [00:01<00:00, 8.54it/s]\n 87%|████████▋ | 13/15 [00:01<00:00, 8.53it/s]\n 93%|█████████▎| 14/15 [00:01<00:00, 8.52it/s]\n100%|██████████| 15/15 [00:01<00:00, 8.52it/s]\n100%|██████████| 15/15 [00:01<00:00, 8.44it/s]", "metrics": { "predict_time": 11.277611, "total_time": 14.779682 }, "output": [ "https://replicate.delivery/pbxt/cCKNz72I9MqhA1lS240OZ2aLC1Dk6C05zjHODjxdSn4xw5gE/out-0.png" ], "started_at": "2023-12-18T21:50:53.613295Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/s6d265tb2naexpkhprtwm4hwo4", "cancel": "https://api.replicate.com/v1/predictions/s6d265tb2naexpkhprtwm4hwo4/cancel" }, "version": "40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2" }
Generated inUsing seed: 35059 Ensuring enough disk space... Free disk space: 2578913357824 Downloading weights: https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar 2023-12-18T21:50:53Z | INFO | [ Initiating ] dest=/src/weights-cache/ff016a5a915406b1 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar 2023-12-18T21:50:54Z | INFO | [ Complete ] dest=/src/weights-cache/ff016a5a915406b1 size="186 MB" total_elapsed=0.787s url=https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar b'' Downloaded weights in 0.9149889945983887 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: old man outside, farmer, gray hair, casual clothes, late afternoon light, in the style of <s0><s1>, crisp, sharp, photorealistic, movie scene txt2img mode 0%| | 0/44 [00:00<?, ?it/s] 2%|▏ | 1/44 [00:00<00:07, 5.55it/s] 5%|▍ | 2/44 [00:00<00:06, 6.45it/s] 7%|▋ | 3/44 [00:00<00:06, 6.76it/s] 9%|▉ | 4/44 [00:00<00:05, 6.92it/s] 11%|█▏ | 5/44 [00:00<00:05, 7.02it/s] 14%|█▎ | 6/44 [00:00<00:05, 7.08it/s] 16%|█▌ | 7/44 [00:01<00:05, 7.12it/s] 18%|█▊ | 8/44 [00:01<00:05, 7.16it/s] 20%|██ | 9/44 [00:01<00:04, 7.17it/s] 23%|██▎ | 10/44 [00:01<00:04, 7.18it/s] 25%|██▌ | 11/44 [00:01<00:04, 7.19it/s] 27%|██▋ | 12/44 [00:01<00:04, 7.19it/s] 30%|██▉ | 13/44 [00:01<00:04, 7.20it/s] 32%|███▏ | 14/44 [00:01<00:04, 7.20it/s] 34%|███▍ | 15/44 [00:02<00:04, 7.20it/s] 36%|███▋ | 16/44 [00:02<00:03, 7.19it/s] 39%|███▊ | 17/44 [00:02<00:03, 7.18it/s] 41%|████ | 18/44 [00:02<00:03, 7.18it/s] 43%|████▎ | 19/44 [00:02<00:03, 7.18it/s] 45%|████▌ | 20/44 [00:02<00:03, 7.18it/s] 48%|████▊ | 21/44 [00:02<00:03, 7.19it/s] 50%|█████ | 22/44 [00:03<00:03, 7.21it/s] 52%|█████▏ | 23/44 [00:03<00:02, 7.22it/s] 55%|█████▍ | 24/44 [00:03<00:02, 7.23it/s] 57%|█████▋ | 25/44 [00:03<00:02, 7.23it/s] 59%|█████▉ | 26/44 [00:03<00:02, 7.24it/s] 61%|██████▏ | 27/44 [00:03<00:02, 7.24it/s] 64%|██████▎ | 28/44 [00:03<00:02, 7.24it/s] 66%|██████▌ | 29/44 [00:04<00:02, 7.24it/s] 68%|██████▊ | 30/44 [00:04<00:01, 7.24it/s] 70%|███████ | 31/44 [00:04<00:01, 7.24it/s] 73%|███████▎ | 32/44 [00:04<00:01, 7.23it/s] 75%|███████▌ | 33/44 [00:04<00:01, 7.23it/s] 77%|███████▋ | 34/44 [00:04<00:01, 7.23it/s] 80%|███████▉ | 35/44 [00:04<00:01, 7.23it/s] 82%|████████▏ | 36/44 [00:05<00:01, 7.23it/s] 84%|████████▍ | 37/44 [00:05<00:00, 7.24it/s] 86%|████████▋ | 38/44 [00:05<00:00, 7.23it/s] 89%|████████▊ | 39/44 [00:05<00:00, 7.24it/s] 91%|█████████ | 40/44 [00:05<00:00, 7.24it/s] 93%|█████████▎| 41/44 [00:05<00:00, 7.24it/s] 95%|█████████▌| 42/44 [00:05<00:00, 7.23it/s] 98%|█████████▊| 43/44 [00:05<00:00, 7.23it/s] 100%|██████████| 44/44 [00:06<00:00, 7.23it/s] 100%|██████████| 44/44 [00:06<00:00, 7.17it/s] 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:00<00:01, 7.29it/s] 13%|█▎ | 2/15 [00:00<00:01, 7.99it/s] 20%|██ | 3/15 [00:00<00:01, 8.23it/s] 27%|██▋ | 4/15 [00:00<00:01, 8.36it/s] 33%|███▎ | 5/15 [00:00<00:01, 8.43it/s] 40%|████ | 6/15 [00:00<00:01, 8.46it/s] 47%|████▋ | 7/15 [00:00<00:00, 8.47it/s] 53%|█████▎ | 8/15 [00:00<00:00, 8.49it/s] 60%|██████ | 9/15 [00:01<00:00, 8.51it/s] 67%|██████▋ | 10/15 [00:01<00:00, 8.52it/s] 73%|███████▎ | 11/15 [00:01<00:00, 8.53it/s] 80%|████████ | 12/15 [00:01<00:00, 8.54it/s] 87%|████████▋ | 13/15 [00:01<00:00, 8.53it/s] 93%|█████████▎| 14/15 [00:01<00:00, 8.52it/s] 100%|██████████| 15/15 [00:01<00:00, 8.52it/s] 100%|██████████| 15/15 [00:01<00:00, 8.44it/s]
Prediction
martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2IDuncgzjdb7zcig7wsct26xmeoeqStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 512
- prompt
- Woman in a cafe, dim light, in the style of TOK, crisp, sharp, photorealistic, movie scene
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.8
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- cropped, worst quality, low quality, glitch, deformed, mutated, disfigured
- prompt_strength
- 0.8
- num_inference_steps
- 70
{ "width": 1024, "height": 512, "prompt": "Woman in a cafe, dim light, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run martintmv-git/sdxl-cinematic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", { input: { width: 1024, height: 512, prompt: "Woman in a cafe, dim light, in the style of TOK, crisp, sharp, photorealistic, movie scene", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.8, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", prompt_strength: 0.8, num_inference_steps: 70 } } ); // 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 martintmv-git/sdxl-cinematic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", input={ "width": 1024, "height": 512, "prompt": "Woman in a cafe, dim light, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run martintmv-git/sdxl-cinematic 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": "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", "input": { "width": 1024, "height": 512, "prompt": "Woman in a cafe, dim light, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-12-18T21:58:49.520919Z", "created_at": "2023-12-18T21:58:31.605910Z", "data_removed": false, "error": null, "id": "uncgzjdb7zcig7wsct26xmeoeq", "input": { "width": 1024, "height": 512, "prompt": "Woman in a cafe, dim light, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 }, "logs": "Using seed: 21325\nEnsuring enough disk space...\nFree disk space: 3212019421184\nDownloading weights: https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar\n2023-12-18T21:58:37Z | INFO | [ Initiating ] dest=/src/weights-cache/ff016a5a915406b1 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar\n2023-12-18T21:58:38Z | INFO | [ Complete ] dest=/src/weights-cache/ff016a5a915406b1 size=\"186 MB\" total_elapsed=0.476s url=https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar\nb''\nDownloaded weights in 0.6030163764953613 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: Woman in a cafe, dim light, in the style of <s0><s1>, crisp, sharp, photorealistic, movie scene\ntxt2img mode\n 0%| | 0/55 [00:00<?, ?it/s]\n 2%|▏ | 1/55 [00:00<00:10, 5.22it/s]\n 4%|▎ | 2/55 [00:00<00:08, 6.14it/s]\n 5%|▌ | 3/55 [00:00<00:08, 6.49it/s]\n 7%|▋ | 4/55 [00:00<00:07, 6.68it/s]\n 9%|▉ | 5/55 [00:00<00:07, 6.79it/s]\n 11%|█ | 6/55 [00:00<00:07, 6.85it/s]\n 13%|█▎ | 7/55 [00:01<00:06, 6.88it/s]\n 15%|█▍ | 8/55 [00:01<00:06, 6.90it/s]\n 16%|█▋ | 9/55 [00:01<00:06, 6.92it/s]\n 18%|█▊ | 10/55 [00:01<00:06, 6.94it/s]\n 20%|██ | 11/55 [00:01<00:06, 6.94it/s]\n 22%|██▏ | 12/55 [00:01<00:06, 6.94it/s]\n 24%|██▎ | 13/55 [00:01<00:06, 6.95it/s]\n 25%|██▌ | 14/55 [00:02<00:05, 6.96it/s]\n 27%|██▋ | 15/55 [00:02<00:05, 6.96it/s]\n 29%|██▉ | 16/55 [00:02<00:05, 6.96it/s]\n 31%|███ | 17/55 [00:02<00:05, 6.96it/s]\n 33%|███▎ | 18/55 [00:02<00:05, 6.96it/s]\n 35%|███▍ | 19/55 [00:02<00:05, 6.96it/s]\n 36%|███▋ | 20/55 [00:02<00:05, 6.96it/s]\n 38%|███▊ | 21/55 [00:03<00:04, 6.96it/s]\n 40%|████ | 22/55 [00:03<00:04, 6.95it/s]\n 42%|████▏ | 23/55 [00:03<00:04, 6.96it/s]\n 44%|████▎ | 24/55 [00:03<00:04, 6.96it/s]\n 45%|████▌ | 25/55 [00:03<00:04, 6.96it/s]\n 47%|████▋ | 26/55 [00:03<00:04, 6.96it/s]\n 49%|████▉ | 27/55 [00:03<00:04, 6.95it/s]\n 51%|█████ | 28/55 [00:04<00:03, 6.95it/s]\n 53%|█████▎ | 29/55 [00:04<00:03, 6.95it/s]\n 55%|█████▍ | 30/55 [00:04<00:03, 6.95it/s]\n 56%|█████▋ | 31/55 [00:04<00:03, 6.95it/s]\n 58%|█████▊ | 32/55 [00:04<00:03, 6.95it/s]\n 60%|██████ | 33/55 [00:04<00:03, 6.95it/s]\n 62%|██████▏ | 34/55 [00:04<00:03, 6.95it/s]\n 64%|██████▎ | 35/55 [00:05<00:02, 6.95it/s]\n 65%|██████▌ | 36/55 [00:05<00:02, 6.95it/s]\n 67%|██████▋ | 37/55 [00:05<00:02, 6.96it/s]\n 69%|██████▉ | 38/55 [00:05<00:02, 6.95it/s]\n 71%|███████ | 39/55 [00:05<00:02, 6.95it/s]\n 73%|███████▎ | 40/55 [00:05<00:02, 6.95it/s]\n 75%|███████▍ | 41/55 [00:05<00:02, 6.95it/s]\n 76%|███████▋ | 42/55 [00:06<00:01, 6.95it/s]\n 78%|███████▊ | 43/55 [00:06<00:01, 6.94it/s]\n 80%|████████ | 44/55 [00:06<00:01, 6.94it/s]\n 82%|████████▏ | 45/55 [00:06<00:01, 6.94it/s]\n 84%|████████▎ | 46/55 [00:06<00:01, 6.94it/s]\n 85%|████████▌ | 47/55 [00:06<00:01, 6.94it/s]\n 87%|████████▋ | 48/55 [00:06<00:01, 6.93it/s]\n 89%|████████▉ | 49/55 [00:07<00:00, 6.93it/s]\n 91%|█████████ | 50/55 [00:07<00:00, 6.93it/s]\n 93%|█████████▎| 51/55 [00:07<00:00, 6.92it/s]\n 95%|█████████▍| 52/55 [00:07<00:00, 6.92it/s]\n 96%|█████████▋| 53/55 [00:07<00:00, 6.93it/s]\n 98%|█████████▊| 54/55 [00:07<00:00, 6.93it/s]\n100%|██████████| 55/55 [00:07<00:00, 6.93it/s]\n100%|██████████| 55/55 [00:07<00:00, 6.91it/s]\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:00<00:01, 7.16it/s]\n 13%|█▎ | 2/15 [00:00<00:01, 7.73it/s]\n 20%|██ | 3/15 [00:00<00:01, 7.94it/s]\n 27%|██▋ | 4/15 [00:00<00:01, 8.04it/s]\n 33%|███▎ | 5/15 [00:00<00:01, 8.11it/s]\n 40%|████ | 6/15 [00:00<00:01, 8.15it/s]\n 47%|████▋ | 7/15 [00:00<00:00, 8.18it/s]\n 53%|█████▎ | 8/15 [00:00<00:00, 8.19it/s]\n 60%|██████ | 9/15 [00:01<00:00, 8.20it/s]\n 67%|██████▋ | 10/15 [00:01<00:00, 8.20it/s]\n 73%|███████▎ | 11/15 [00:01<00:00, 8.20it/s]\n 80%|████████ | 12/15 [00:01<00:00, 8.21it/s]\n 87%|████████▋ | 13/15 [00:01<00:00, 8.22it/s]\n 93%|█████████▎| 14/15 [00:01<00:00, 8.21it/s]\n100%|██████████| 15/15 [00:01<00:00, 8.21it/s]\n100%|██████████| 15/15 [00:01<00:00, 8.13it/s]", "metrics": { "predict_time": 11.943408, "total_time": 17.915009 }, "output": [ "https://replicate.delivery/pbxt/gUfRvXgXyH3aUKPDgw4CbX2PvaQfQnf908dNTPFXiwHyUOHkA/out-0.png" ], "started_at": "2023-12-18T21:58:37.577511Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/uncgzjdb7zcig7wsct26xmeoeq", "cancel": "https://api.replicate.com/v1/predictions/uncgzjdb7zcig7wsct26xmeoeq/cancel" }, "version": "40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2" }
Generated inUsing seed: 21325 Ensuring enough disk space... Free disk space: 3212019421184 Downloading weights: https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar 2023-12-18T21:58:37Z | INFO | [ Initiating ] dest=/src/weights-cache/ff016a5a915406b1 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar 2023-12-18T21:58:38Z | INFO | [ Complete ] dest=/src/weights-cache/ff016a5a915406b1 size="186 MB" total_elapsed=0.476s url=https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar b'' Downloaded weights in 0.6030163764953613 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: Woman in a cafe, dim light, in the style of <s0><s1>, crisp, sharp, photorealistic, movie scene txt2img mode 0%| | 0/55 [00:00<?, ?it/s] 2%|▏ | 1/55 [00:00<00:10, 5.22it/s] 4%|▎ | 2/55 [00:00<00:08, 6.14it/s] 5%|▌ | 3/55 [00:00<00:08, 6.49it/s] 7%|▋ | 4/55 [00:00<00:07, 6.68it/s] 9%|▉ | 5/55 [00:00<00:07, 6.79it/s] 11%|█ | 6/55 [00:00<00:07, 6.85it/s] 13%|█▎ | 7/55 [00:01<00:06, 6.88it/s] 15%|█▍ | 8/55 [00:01<00:06, 6.90it/s] 16%|█▋ | 9/55 [00:01<00:06, 6.92it/s] 18%|█▊ | 10/55 [00:01<00:06, 6.94it/s] 20%|██ | 11/55 [00:01<00:06, 6.94it/s] 22%|██▏ | 12/55 [00:01<00:06, 6.94it/s] 24%|██▎ | 13/55 [00:01<00:06, 6.95it/s] 25%|██▌ | 14/55 [00:02<00:05, 6.96it/s] 27%|██▋ | 15/55 [00:02<00:05, 6.96it/s] 29%|██▉ | 16/55 [00:02<00:05, 6.96it/s] 31%|███ | 17/55 [00:02<00:05, 6.96it/s] 33%|███▎ | 18/55 [00:02<00:05, 6.96it/s] 35%|███▍ | 19/55 [00:02<00:05, 6.96it/s] 36%|███▋ | 20/55 [00:02<00:05, 6.96it/s] 38%|███▊ | 21/55 [00:03<00:04, 6.96it/s] 40%|████ | 22/55 [00:03<00:04, 6.95it/s] 42%|████▏ | 23/55 [00:03<00:04, 6.96it/s] 44%|████▎ | 24/55 [00:03<00:04, 6.96it/s] 45%|████▌ | 25/55 [00:03<00:04, 6.96it/s] 47%|████▋ | 26/55 [00:03<00:04, 6.96it/s] 49%|████▉ | 27/55 [00:03<00:04, 6.95it/s] 51%|█████ | 28/55 [00:04<00:03, 6.95it/s] 53%|█████▎ | 29/55 [00:04<00:03, 6.95it/s] 55%|█████▍ | 30/55 [00:04<00:03, 6.95it/s] 56%|█████▋ | 31/55 [00:04<00:03, 6.95it/s] 58%|█████▊ | 32/55 [00:04<00:03, 6.95it/s] 60%|██████ | 33/55 [00:04<00:03, 6.95it/s] 62%|██████▏ | 34/55 [00:04<00:03, 6.95it/s] 64%|██████▎ | 35/55 [00:05<00:02, 6.95it/s] 65%|██████▌ | 36/55 [00:05<00:02, 6.95it/s] 67%|██████▋ | 37/55 [00:05<00:02, 6.96it/s] 69%|██████▉ | 38/55 [00:05<00:02, 6.95it/s] 71%|███████ | 39/55 [00:05<00:02, 6.95it/s] 73%|███████▎ | 40/55 [00:05<00:02, 6.95it/s] 75%|███████▍ | 41/55 [00:05<00:02, 6.95it/s] 76%|███████▋ | 42/55 [00:06<00:01, 6.95it/s] 78%|███████▊ | 43/55 [00:06<00:01, 6.94it/s] 80%|████████ | 44/55 [00:06<00:01, 6.94it/s] 82%|████████▏ | 45/55 [00:06<00:01, 6.94it/s] 84%|████████▎ | 46/55 [00:06<00:01, 6.94it/s] 85%|████████▌ | 47/55 [00:06<00:01, 6.94it/s] 87%|████████▋ | 48/55 [00:06<00:01, 6.93it/s] 89%|████████▉ | 49/55 [00:07<00:00, 6.93it/s] 91%|█████████ | 50/55 [00:07<00:00, 6.93it/s] 93%|█████████▎| 51/55 [00:07<00:00, 6.92it/s] 95%|█████████▍| 52/55 [00:07<00:00, 6.92it/s] 96%|█████████▋| 53/55 [00:07<00:00, 6.93it/s] 98%|█████████▊| 54/55 [00:07<00:00, 6.93it/s] 100%|██████████| 55/55 [00:07<00:00, 6.93it/s] 100%|██████████| 55/55 [00:07<00:00, 6.91it/s] 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:00<00:01, 7.16it/s] 13%|█▎ | 2/15 [00:00<00:01, 7.73it/s] 20%|██ | 3/15 [00:00<00:01, 7.94it/s] 27%|██▋ | 4/15 [00:00<00:01, 8.04it/s] 33%|███▎ | 5/15 [00:00<00:01, 8.11it/s] 40%|████ | 6/15 [00:00<00:01, 8.15it/s] 47%|████▋ | 7/15 [00:00<00:00, 8.18it/s] 53%|█████▎ | 8/15 [00:00<00:00, 8.19it/s] 60%|██████ | 9/15 [00:01<00:00, 8.20it/s] 67%|██████▋ | 10/15 [00:01<00:00, 8.20it/s] 73%|███████▎ | 11/15 [00:01<00:00, 8.20it/s] 80%|████████ | 12/15 [00:01<00:00, 8.21it/s] 87%|████████▋ | 13/15 [00:01<00:00, 8.22it/s] 93%|█████████▎| 14/15 [00:01<00:00, 8.21it/s] 100%|██████████| 15/15 [00:01<00:00, 8.21it/s] 100%|██████████| 15/15 [00:01<00:00, 8.13it/s]
Prediction
martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2ID3pb3yelbyyua2pzgb74z6tsi6uStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 512
- prompt
- Figure walking in a cornfield, vibrant colours, in the style of TOK, crisp, sharp, photorealistic, movie scene
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.8
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- cropped, worst quality, low quality, glitch, deformed, mutated, disfigured
- prompt_strength
- 0.8
- num_inference_steps
- 70
{ "width": 1024, "height": 512, "prompt": "Figure walking in a cornfield, vibrant colours, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run martintmv-git/sdxl-cinematic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", { input: { width: 1024, height: 512, prompt: "Figure walking in a cornfield, vibrant colours, in the style of TOK, crisp, sharp, photorealistic, movie scene", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.8, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", prompt_strength: 0.8, num_inference_steps: 70 } } ); // 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 martintmv-git/sdxl-cinematic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", input={ "width": 1024, "height": 512, "prompt": "Figure walking in a cornfield, vibrant colours, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run martintmv-git/sdxl-cinematic 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": "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", "input": { "width": 1024, "height": 512, "prompt": "Figure walking in a cornfield, vibrant colours, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-12-18T22:09:21.172817Z", "created_at": "2023-12-18T22:08:54.447376Z", "data_removed": false, "error": null, "id": "3pb3yelbyyua2pzgb74z6tsi6u", "input": { "width": 1024, "height": 512, "prompt": "Figure walking in a cornfield, vibrant colours, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 }, "logs": "Using seed: 62058\nEnsuring enough disk space...\nFree disk space: 1880703610880\nDownloading weights: https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar\n2023-12-18T22:09:09Z | INFO | [ Initiating ] dest=/src/weights-cache/ff016a5a915406b1 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar\n2023-12-18T22:09:10Z | INFO | [ Complete ] dest=/src/weights-cache/ff016a5a915406b1 size=\"186 MB\" total_elapsed=0.471s url=https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar\nb''\nDownloaded weights in 0.6056108474731445 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: Figure walking in a cornfield, vibrant colours, in the style of <s0><s1>, crisp, sharp, photorealistic, movie scene\ntxt2img mode\n 0%| | 0/55 [00:00<?, ?it/s]\n 2%|▏ | 1/55 [00:00<00:10, 5.31it/s]\n 4%|▎ | 2/55 [00:00<00:08, 6.32it/s]\n 5%|▌ | 3/55 [00:00<00:07, 6.71it/s]\n 7%|▋ | 4/55 [00:00<00:07, 6.91it/s]\n 9%|▉ | 5/55 [00:00<00:07, 7.03it/s]\n 11%|█ | 6/55 [00:00<00:06, 7.10it/s]\n 13%|█▎ | 7/55 [00:01<00:06, 7.14it/s]\n 15%|█▍ | 8/55 [00:01<00:06, 7.17it/s]\n 16%|█▋ | 9/55 [00:01<00:06, 7.18it/s]\n 18%|█▊ | 10/55 [00:01<00:06, 7.19it/s]\n 20%|██ | 11/55 [00:01<00:06, 7.20it/s]\n 22%|██▏ | 12/55 [00:01<00:05, 7.21it/s]\n 24%|██▎ | 13/55 [00:01<00:05, 7.21it/s]\n 25%|██▌ | 14/55 [00:01<00:05, 7.21it/s]\n 27%|██▋ | 15/55 [00:02<00:05, 7.22it/s]\n 29%|██▉ | 16/55 [00:02<00:05, 7.22it/s]\n 31%|███ | 17/55 [00:02<00:05, 7.22it/s]\n 33%|███▎ | 18/55 [00:02<00:05, 7.23it/s]\n 35%|███▍ | 19/55 [00:02<00:04, 7.22it/s]\n 36%|███▋ | 20/55 [00:02<00:04, 7.22it/s]\n 38%|███▊ | 21/55 [00:02<00:04, 7.22it/s]\n 40%|████ | 22/55 [00:03<00:04, 7.22it/s]\n 42%|████▏ | 23/55 [00:03<00:04, 7.22it/s]\n 44%|████▎ | 24/55 [00:03<00:04, 7.22it/s]\n 45%|████▌ | 25/55 [00:03<00:04, 7.23it/s]\n 47%|████▋ | 26/55 [00:03<00:04, 7.22it/s]\n 49%|████▉ | 27/55 [00:03<00:03, 7.21it/s]\n 51%|█████ | 28/55 [00:03<00:03, 7.21it/s]\n 53%|█████▎ | 29/55 [00:04<00:03, 7.21it/s]\n 55%|█████▍ | 30/55 [00:04<00:03, 7.21it/s]\n 56%|█████▋ | 31/55 [00:04<00:03, 7.21it/s]\n 58%|█████▊ | 32/55 [00:04<00:03, 7.21it/s]\n 60%|██████ | 33/55 [00:04<00:03, 7.22it/s]\n 62%|██████▏ | 34/55 [00:04<00:02, 7.22it/s]\n 64%|██████▎ | 35/55 [00:04<00:02, 7.22it/s]\n 65%|██████▌ | 36/55 [00:05<00:02, 7.22it/s]\n 67%|██████▋ | 37/55 [00:05<00:02, 7.22it/s]\n 69%|██████▉ | 38/55 [00:05<00:02, 7.22it/s]\n 71%|███████ | 39/55 [00:05<00:02, 7.22it/s]\n 73%|███████▎ | 40/55 [00:05<00:02, 7.22it/s]\n 75%|███████▍ | 41/55 [00:05<00:01, 7.22it/s]\n 76%|███████▋ | 42/55 [00:05<00:01, 7.21it/s]\n 78%|███████▊ | 43/55 [00:06<00:01, 7.21it/s]\n 80%|████████ | 44/55 [00:06<00:01, 7.21it/s]\n 82%|████████▏ | 45/55 [00:06<00:01, 7.21it/s]\n 84%|████████▎ | 46/55 [00:06<00:01, 7.20it/s]\n 85%|████████▌ | 47/55 [00:06<00:01, 7.21it/s]\n 87%|████████▋ | 48/55 [00:06<00:00, 7.21it/s]\n 89%|████████▉ | 49/55 [00:06<00:00, 7.21it/s]\n 91%|█████████ | 50/55 [00:06<00:00, 7.22it/s]\n 93%|█████████▎| 51/55 [00:07<00:00, 7.22it/s]\n 95%|█████████▍| 52/55 [00:07<00:00, 7.22it/s]\n 96%|█████████▋| 53/55 [00:07<00:00, 7.22it/s]\n 98%|█████████▊| 54/55 [00:07<00:00, 7.22it/s]\n100%|██████████| 55/55 [00:07<00:00, 7.21it/s]\n100%|██████████| 55/55 [00:07<00:00, 7.17it/s]\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:00<00:01, 7.16it/s]\n 13%|█▎ | 2/15 [00:00<00:01, 7.91it/s]\n 20%|██ | 3/15 [00:00<00:01, 8.17it/s]\n 27%|██▋ | 4/15 [00:00<00:01, 8.31it/s]\n 33%|███▎ | 5/15 [00:00<00:01, 8.39it/s]\n 40%|████ | 6/15 [00:00<00:01, 8.44it/s]\n 47%|████▋ | 7/15 [00:00<00:00, 8.47it/s]\n 53%|█████▎ | 8/15 [00:00<00:00, 8.49it/s]\n 60%|██████ | 9/15 [00:01<00:00, 8.50it/s]\n 67%|██████▋ | 10/15 [00:01<00:00, 8.51it/s]\n 73%|███████▎ | 11/15 [00:01<00:00, 8.51it/s]\n 80%|████████ | 12/15 [00:01<00:00, 8.52it/s]\n 87%|████████▋ | 13/15 [00:01<00:00, 8.53it/s]\n 93%|█████████▎| 14/15 [00:01<00:00, 8.52it/s]\n100%|██████████| 15/15 [00:01<00:00, 8.52it/s]\n100%|██████████| 15/15 [00:01<00:00, 8.42it/s]", "metrics": { "predict_time": 11.593408, "total_time": 26.725441 }, "output": [ "https://replicate.delivery/pbxt/2IF553o9bqIfKigvM5NYaLYb3i4mfxI7H4xYwj1fDLMgoOHkA/out-0.png" ], "started_at": "2023-12-18T22:09:09.579409Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/3pb3yelbyyua2pzgb74z6tsi6u", "cancel": "https://api.replicate.com/v1/predictions/3pb3yelbyyua2pzgb74z6tsi6u/cancel" }, "version": "40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2" }
Generated inUsing seed: 62058 Ensuring enough disk space... Free disk space: 1880703610880 Downloading weights: https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar 2023-12-18T22:09:09Z | INFO | [ Initiating ] dest=/src/weights-cache/ff016a5a915406b1 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar 2023-12-18T22:09:10Z | INFO | [ Complete ] dest=/src/weights-cache/ff016a5a915406b1 size="186 MB" total_elapsed=0.471s url=https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar b'' Downloaded weights in 0.6056108474731445 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: Figure walking in a cornfield, vibrant colours, in the style of <s0><s1>, crisp, sharp, photorealistic, movie scene txt2img mode 0%| | 0/55 [00:00<?, ?it/s] 2%|▏ | 1/55 [00:00<00:10, 5.31it/s] 4%|▎ | 2/55 [00:00<00:08, 6.32it/s] 5%|▌ | 3/55 [00:00<00:07, 6.71it/s] 7%|▋ | 4/55 [00:00<00:07, 6.91it/s] 9%|▉ | 5/55 [00:00<00:07, 7.03it/s] 11%|█ | 6/55 [00:00<00:06, 7.10it/s] 13%|█▎ | 7/55 [00:01<00:06, 7.14it/s] 15%|█▍ | 8/55 [00:01<00:06, 7.17it/s] 16%|█▋ | 9/55 [00:01<00:06, 7.18it/s] 18%|█▊ | 10/55 [00:01<00:06, 7.19it/s] 20%|██ | 11/55 [00:01<00:06, 7.20it/s] 22%|██▏ | 12/55 [00:01<00:05, 7.21it/s] 24%|██▎ | 13/55 [00:01<00:05, 7.21it/s] 25%|██▌ | 14/55 [00:01<00:05, 7.21it/s] 27%|██▋ | 15/55 [00:02<00:05, 7.22it/s] 29%|██▉ | 16/55 [00:02<00:05, 7.22it/s] 31%|███ | 17/55 [00:02<00:05, 7.22it/s] 33%|███▎ | 18/55 [00:02<00:05, 7.23it/s] 35%|███▍ | 19/55 [00:02<00:04, 7.22it/s] 36%|███▋ | 20/55 [00:02<00:04, 7.22it/s] 38%|███▊ | 21/55 [00:02<00:04, 7.22it/s] 40%|████ | 22/55 [00:03<00:04, 7.22it/s] 42%|████▏ | 23/55 [00:03<00:04, 7.22it/s] 44%|████▎ | 24/55 [00:03<00:04, 7.22it/s] 45%|████▌ | 25/55 [00:03<00:04, 7.23it/s] 47%|████▋ | 26/55 [00:03<00:04, 7.22it/s] 49%|████▉ | 27/55 [00:03<00:03, 7.21it/s] 51%|█████ | 28/55 [00:03<00:03, 7.21it/s] 53%|█████▎ | 29/55 [00:04<00:03, 7.21it/s] 55%|█████▍ | 30/55 [00:04<00:03, 7.21it/s] 56%|█████▋ | 31/55 [00:04<00:03, 7.21it/s] 58%|█████▊ | 32/55 [00:04<00:03, 7.21it/s] 60%|██████ | 33/55 [00:04<00:03, 7.22it/s] 62%|██████▏ | 34/55 [00:04<00:02, 7.22it/s] 64%|██████▎ | 35/55 [00:04<00:02, 7.22it/s] 65%|██████▌ | 36/55 [00:05<00:02, 7.22it/s] 67%|██████▋ | 37/55 [00:05<00:02, 7.22it/s] 69%|██████▉ | 38/55 [00:05<00:02, 7.22it/s] 71%|███████ | 39/55 [00:05<00:02, 7.22it/s] 73%|███████▎ | 40/55 [00:05<00:02, 7.22it/s] 75%|███████▍ | 41/55 [00:05<00:01, 7.22it/s] 76%|███████▋ | 42/55 [00:05<00:01, 7.21it/s] 78%|███████▊ | 43/55 [00:06<00:01, 7.21it/s] 80%|████████ | 44/55 [00:06<00:01, 7.21it/s] 82%|████████▏ | 45/55 [00:06<00:01, 7.21it/s] 84%|████████▎ | 46/55 [00:06<00:01, 7.20it/s] 85%|████████▌ | 47/55 [00:06<00:01, 7.21it/s] 87%|████████▋ | 48/55 [00:06<00:00, 7.21it/s] 89%|████████▉ | 49/55 [00:06<00:00, 7.21it/s] 91%|█████████ | 50/55 [00:06<00:00, 7.22it/s] 93%|█████████▎| 51/55 [00:07<00:00, 7.22it/s] 95%|█████████▍| 52/55 [00:07<00:00, 7.22it/s] 96%|█████████▋| 53/55 [00:07<00:00, 7.22it/s] 98%|█████████▊| 54/55 [00:07<00:00, 7.22it/s] 100%|██████████| 55/55 [00:07<00:00, 7.21it/s] 100%|██████████| 55/55 [00:07<00:00, 7.17it/s] 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:00<00:01, 7.16it/s] 13%|█▎ | 2/15 [00:00<00:01, 7.91it/s] 20%|██ | 3/15 [00:00<00:01, 8.17it/s] 27%|██▋ | 4/15 [00:00<00:01, 8.31it/s] 33%|███▎ | 5/15 [00:00<00:01, 8.39it/s] 40%|████ | 6/15 [00:00<00:01, 8.44it/s] 47%|████▋ | 7/15 [00:00<00:00, 8.47it/s] 53%|█████▎ | 8/15 [00:00<00:00, 8.49it/s] 60%|██████ | 9/15 [00:01<00:00, 8.50it/s] 67%|██████▋ | 10/15 [00:01<00:00, 8.51it/s] 73%|███████▎ | 11/15 [00:01<00:00, 8.51it/s] 80%|████████ | 12/15 [00:01<00:00, 8.52it/s] 87%|████████▋ | 13/15 [00:01<00:00, 8.53it/s] 93%|█████████▎| 14/15 [00:01<00:00, 8.52it/s] 100%|██████████| 15/15 [00:01<00:00, 8.52it/s] 100%|██████████| 15/15 [00:01<00:00, 8.42it/s]
Prediction
martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2IDzh3rek3b464uvbicmr3jajgrnqStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 512
- prompt
- A medieval knight standing in a misty forest, with a castle visible in the distance, in the style of TOK, crisp, sharp, photorealistic, movie scene
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.8
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- cropped, worst quality, low quality, glitch, deformed, mutated, disfigured
- prompt_strength
- 0.8
- num_inference_steps
- 70
{ "width": 1024, "height": 512, "prompt": "A medieval knight standing in a misty forest, with a castle visible in the distance, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run martintmv-git/sdxl-cinematic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", { input: { width: 1024, height: 512, prompt: "A medieval knight standing in a misty forest, with a castle visible in the distance, in the style of TOK, crisp, sharp, photorealistic, movie scene", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.8, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", prompt_strength: 0.8, num_inference_steps: 70 } } ); // 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 martintmv-git/sdxl-cinematic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", input={ "width": 1024, "height": 512, "prompt": "A medieval knight standing in a misty forest, with a castle visible in the distance, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run martintmv-git/sdxl-cinematic 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": "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", "input": { "width": 1024, "height": 512, "prompt": "A medieval knight standing in a misty forest, with a castle visible in the distance, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-12-18T22:24:04.685958Z", "created_at": "2023-12-18T22:23:49.147331Z", "data_removed": false, "error": null, "id": "zh3rek3b464uvbicmr3jajgrnq", "input": { "width": 1024, "height": 512, "prompt": "A medieval knight standing in a misty forest, with a castle visible in the distance, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 }, "logs": "Using seed: 47266\nEnsuring enough disk space...\nFree disk space: 3213668261888\nDownloading weights: https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar\n2023-12-18T22:23:53Z | INFO | [ Initiating ] dest=/src/weights-cache/ff016a5a915406b1 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar\n2023-12-18T22:23:53Z | INFO | [ Complete ] dest=/src/weights-cache/ff016a5a915406b1 size=\"186 MB\" total_elapsed=0.500s url=https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar\nb''\nDownloaded weights in 0.6219019889831543 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A medieval knight standing in a misty forest, with a castle visible in the distance, in the style of <s0><s1>, crisp, sharp, photorealistic, movie scene\ntxt2img mode\n 0%| | 0/55 [00:00<?, ?it/s]\n 2%|▏ | 1/55 [00:00<00:10, 5.39it/s]\n 4%|▎ | 2/55 [00:00<00:08, 6.39it/s]\n 5%|▌ | 3/55 [00:00<00:07, 6.78it/s]\n 7%|▋ | 4/55 [00:00<00:07, 6.99it/s]\n 9%|▉ | 5/55 [00:00<00:07, 7.11it/s]\n 11%|█ | 6/55 [00:00<00:06, 7.18it/s]\n 13%|█▎ | 7/55 [00:01<00:06, 7.22it/s]\n 15%|█▍ | 8/55 [00:01<00:06, 7.24it/s]\n 16%|█▋ | 9/55 [00:01<00:06, 7.27it/s]\n 18%|█▊ | 10/55 [00:01<00:06, 7.28it/s]\n 20%|██ | 11/55 [00:01<00:06, 7.29it/s]\n 22%|██▏ | 12/55 [00:01<00:05, 7.30it/s]\n 24%|██▎ | 13/55 [00:01<00:05, 7.29it/s]\n 25%|██▌ | 14/55 [00:01<00:05, 7.30it/s]\n 27%|██▋ | 15/55 [00:02<00:05, 7.29it/s]\n 29%|██▉ | 16/55 [00:02<00:05, 7.30it/s]\n 31%|███ | 17/55 [00:02<00:05, 7.30it/s]\n 33%|███▎ | 18/55 [00:02<00:05, 7.30it/s]\n 35%|███▍ | 19/55 [00:02<00:04, 7.29it/s]\n 36%|███▋ | 20/55 [00:02<00:04, 7.29it/s]\n 38%|███▊ | 21/55 [00:02<00:04, 7.28it/s]\n 40%|████ | 22/55 [00:03<00:04, 7.28it/s]\n 42%|████▏ | 23/55 [00:03<00:04, 7.27it/s]\n 44%|████▎ | 24/55 [00:03<00:04, 7.28it/s]\n 45%|████▌ | 25/55 [00:03<00:04, 7.28it/s]\n 47%|████▋ | 26/55 [00:03<00:03, 7.28it/s]\n 49%|████▉ | 27/55 [00:03<00:03, 7.29it/s]\n 51%|█████ | 28/55 [00:03<00:03, 7.28it/s]\n 53%|█████▎ | 29/55 [00:04<00:03, 7.27it/s]\n 55%|█████▍ | 30/55 [00:04<00:03, 7.27it/s]\n 56%|█████▋ | 31/55 [00:04<00:03, 7.27it/s]\n 58%|█████▊ | 32/55 [00:04<00:03, 7.27it/s]\n 60%|██████ | 33/55 [00:04<00:03, 7.27it/s]\n 62%|██████▏ | 34/55 [00:04<00:02, 7.28it/s]\n 64%|██████▎ | 35/55 [00:04<00:02, 7.28it/s]\n 65%|██████▌ | 36/55 [00:04<00:02, 7.28it/s]\n 67%|██████▋ | 37/55 [00:05<00:02, 7.27it/s]\n 69%|██████▉ | 38/55 [00:05<00:02, 7.26it/s]\n 71%|███████ | 39/55 [00:05<00:02, 7.27it/s]\n 73%|███████▎ | 40/55 [00:05<00:02, 7.27it/s]\n 75%|███████▍ | 41/55 [00:05<00:01, 7.27it/s]\n 76%|███████▋ | 42/55 [00:05<00:01, 7.28it/s]\n 78%|███████▊ | 43/55 [00:05<00:01, 7.27it/s]\n 80%|████████ | 44/55 [00:06<00:01, 7.27it/s]\n 82%|████████▏ | 45/55 [00:06<00:01, 7.26it/s]\n 84%|████████▎ | 46/55 [00:06<00:01, 7.26it/s]\n 85%|████████▌ | 47/55 [00:06<00:01, 7.26it/s]\n 87%|████████▋ | 48/55 [00:06<00:00, 7.26it/s]\n 89%|████████▉ | 49/55 [00:06<00:00, 7.27it/s]\n 91%|█████████ | 50/55 [00:06<00:00, 7.27it/s]\n 93%|█████████▎| 51/55 [00:07<00:00, 7.27it/s]\n 95%|█████████▍| 52/55 [00:07<00:00, 7.27it/s]\n 96%|█████████▋| 53/55 [00:07<00:00, 7.26it/s]\n 98%|█████████▊| 54/55 [00:07<00:00, 7.26it/s]\n100%|██████████| 55/55 [00:07<00:00, 7.26it/s]\n100%|██████████| 55/55 [00:07<00:00, 7.23it/s]\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:00<00:01, 7.41it/s]\n 13%|█▎ | 2/15 [00:00<00:01, 8.07it/s]\n 20%|██ | 3/15 [00:00<00:01, 8.30it/s]\n 27%|██▋ | 4/15 [00:00<00:01, 8.41it/s]\n 33%|███▎ | 5/15 [00:00<00:01, 8.48it/s]\n 40%|████ | 6/15 [00:00<00:01, 8.52it/s]\n 47%|████▋ | 7/15 [00:00<00:00, 8.55it/s]\n 53%|█████▎ | 8/15 [00:00<00:00, 8.55it/s]\n 60%|██████ | 9/15 [00:01<00:00, 8.54it/s]\n 67%|██████▋ | 10/15 [00:01<00:00, 8.55it/s]\n 73%|███████▎ | 11/15 [00:01<00:00, 8.55it/s]\n 80%|████████ | 12/15 [00:01<00:00, 8.55it/s]\n 87%|████████▋ | 13/15 [00:01<00:00, 8.56it/s]\n 93%|█████████▎| 14/15 [00:01<00:00, 8.58it/s]\n100%|██████████| 15/15 [00:01<00:00, 8.58it/s]\n100%|██████████| 15/15 [00:01<00:00, 8.49it/s]", "metrics": { "predict_time": 11.489998, "total_time": 15.538627 }, "output": [ "https://replicate.delivery/pbxt/jVFMVKiPFSKeOafqhfsbQudz0UKQEKHewPtNE1sTwm8TIecQC/out-0.png" ], "started_at": "2023-12-18T22:23:53.195960Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/zh3rek3b464uvbicmr3jajgrnq", "cancel": "https://api.replicate.com/v1/predictions/zh3rek3b464uvbicmr3jajgrnq/cancel" }, "version": "40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2" }
Generated inUsing seed: 47266 Ensuring enough disk space... Free disk space: 3213668261888 Downloading weights: https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar 2023-12-18T22:23:53Z | INFO | [ Initiating ] dest=/src/weights-cache/ff016a5a915406b1 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar 2023-12-18T22:23:53Z | INFO | [ Complete ] dest=/src/weights-cache/ff016a5a915406b1 size="186 MB" total_elapsed=0.500s url=https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar b'' Downloaded weights in 0.6219019889831543 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A medieval knight standing in a misty forest, with a castle visible in the distance, in the style of <s0><s1>, crisp, sharp, photorealistic, movie scene txt2img mode 0%| | 0/55 [00:00<?, ?it/s] 2%|▏ | 1/55 [00:00<00:10, 5.39it/s] 4%|▎ | 2/55 [00:00<00:08, 6.39it/s] 5%|▌ | 3/55 [00:00<00:07, 6.78it/s] 7%|▋ | 4/55 [00:00<00:07, 6.99it/s] 9%|▉ | 5/55 [00:00<00:07, 7.11it/s] 11%|█ | 6/55 [00:00<00:06, 7.18it/s] 13%|█▎ | 7/55 [00:01<00:06, 7.22it/s] 15%|█▍ | 8/55 [00:01<00:06, 7.24it/s] 16%|█▋ | 9/55 [00:01<00:06, 7.27it/s] 18%|█▊ | 10/55 [00:01<00:06, 7.28it/s] 20%|██ | 11/55 [00:01<00:06, 7.29it/s] 22%|██▏ | 12/55 [00:01<00:05, 7.30it/s] 24%|██▎ | 13/55 [00:01<00:05, 7.29it/s] 25%|██▌ | 14/55 [00:01<00:05, 7.30it/s] 27%|██▋ | 15/55 [00:02<00:05, 7.29it/s] 29%|██▉ | 16/55 [00:02<00:05, 7.30it/s] 31%|███ | 17/55 [00:02<00:05, 7.30it/s] 33%|███▎ | 18/55 [00:02<00:05, 7.30it/s] 35%|███▍ | 19/55 [00:02<00:04, 7.29it/s] 36%|███▋ | 20/55 [00:02<00:04, 7.29it/s] 38%|███▊ | 21/55 [00:02<00:04, 7.28it/s] 40%|████ | 22/55 [00:03<00:04, 7.28it/s] 42%|████▏ | 23/55 [00:03<00:04, 7.27it/s] 44%|████▎ | 24/55 [00:03<00:04, 7.28it/s] 45%|████▌ | 25/55 [00:03<00:04, 7.28it/s] 47%|████▋ | 26/55 [00:03<00:03, 7.28it/s] 49%|████▉ | 27/55 [00:03<00:03, 7.29it/s] 51%|█████ | 28/55 [00:03<00:03, 7.28it/s] 53%|█████▎ | 29/55 [00:04<00:03, 7.27it/s] 55%|█████▍ | 30/55 [00:04<00:03, 7.27it/s] 56%|█████▋ | 31/55 [00:04<00:03, 7.27it/s] 58%|█████▊ | 32/55 [00:04<00:03, 7.27it/s] 60%|██████ | 33/55 [00:04<00:03, 7.27it/s] 62%|██████▏ | 34/55 [00:04<00:02, 7.28it/s] 64%|██████▎ | 35/55 [00:04<00:02, 7.28it/s] 65%|██████▌ | 36/55 [00:04<00:02, 7.28it/s] 67%|██████▋ | 37/55 [00:05<00:02, 7.27it/s] 69%|██████▉ | 38/55 [00:05<00:02, 7.26it/s] 71%|███████ | 39/55 [00:05<00:02, 7.27it/s] 73%|███████▎ | 40/55 [00:05<00:02, 7.27it/s] 75%|███████▍ | 41/55 [00:05<00:01, 7.27it/s] 76%|███████▋ | 42/55 [00:05<00:01, 7.28it/s] 78%|███████▊ | 43/55 [00:05<00:01, 7.27it/s] 80%|████████ | 44/55 [00:06<00:01, 7.27it/s] 82%|████████▏ | 45/55 [00:06<00:01, 7.26it/s] 84%|████████▎ | 46/55 [00:06<00:01, 7.26it/s] 85%|████████▌ | 47/55 [00:06<00:01, 7.26it/s] 87%|████████▋ | 48/55 [00:06<00:00, 7.26it/s] 89%|████████▉ | 49/55 [00:06<00:00, 7.27it/s] 91%|█████████ | 50/55 [00:06<00:00, 7.27it/s] 93%|█████████▎| 51/55 [00:07<00:00, 7.27it/s] 95%|█████████▍| 52/55 [00:07<00:00, 7.27it/s] 96%|█████████▋| 53/55 [00:07<00:00, 7.26it/s] 98%|█████████▊| 54/55 [00:07<00:00, 7.26it/s] 100%|██████████| 55/55 [00:07<00:00, 7.26it/s] 100%|██████████| 55/55 [00:07<00:00, 7.23it/s] 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:00<00:01, 7.41it/s] 13%|█▎ | 2/15 [00:00<00:01, 8.07it/s] 20%|██ | 3/15 [00:00<00:01, 8.30it/s] 27%|██▋ | 4/15 [00:00<00:01, 8.41it/s] 33%|███▎ | 5/15 [00:00<00:01, 8.48it/s] 40%|████ | 6/15 [00:00<00:01, 8.52it/s] 47%|████▋ | 7/15 [00:00<00:00, 8.55it/s] 53%|█████▎ | 8/15 [00:00<00:00, 8.55it/s] 60%|██████ | 9/15 [00:01<00:00, 8.54it/s] 67%|██████▋ | 10/15 [00:01<00:00, 8.55it/s] 73%|███████▎ | 11/15 [00:01<00:00, 8.55it/s] 80%|████████ | 12/15 [00:01<00:00, 8.55it/s] 87%|████████▋ | 13/15 [00:01<00:00, 8.56it/s] 93%|█████████▎| 14/15 [00:01<00:00, 8.58it/s] 100%|██████████| 15/15 [00:01<00:00, 8.58it/s] 100%|██████████| 15/15 [00:01<00:00, 8.49it/s]
Prediction
martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2IDjchtittbnqqmchlzllultw7y7yStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 512
- prompt
- A detective in a trench coat walking through a rainy, noir-style city street at night, in the style of TOK, crisp, sharp, photorealistic, movie scene
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.8
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- cropped, worst quality, low quality, glitch, deformed, mutated, disfigured
- prompt_strength
- 0.8
- num_inference_steps
- 70
{ "width": 1024, "height": 512, "prompt": "A detective in a trench coat walking through a rainy, noir-style city street at night, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run martintmv-git/sdxl-cinematic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", { input: { width: 1024, height: 512, prompt: "A detective in a trench coat walking through a rainy, noir-style city street at night, in the style of TOK, crisp, sharp, photorealistic, movie scene", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.8, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", prompt_strength: 0.8, num_inference_steps: 70 } } ); // 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 martintmv-git/sdxl-cinematic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", input={ "width": 1024, "height": 512, "prompt": "A detective in a trench coat walking through a rainy, noir-style city street at night, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run martintmv-git/sdxl-cinematic 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": "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", "input": { "width": 1024, "height": 512, "prompt": "A detective in a trench coat walking through a rainy, noir-style city street at night, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-12-18T22:25:47.106126Z", "created_at": "2023-12-18T22:25:29.049276Z", "data_removed": false, "error": null, "id": "jchtittbnqqmchlzllultw7y7y", "input": { "width": 1024, "height": 512, "prompt": "A detective in a trench coat walking through a rainy, noir-style city street at night, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 }, "logs": "Using seed: 16351\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A detective in a trench coat walking through a rainy, noir-style city street at night, in the style of <s0><s1>, crisp, sharp, photorealistic, movie scene\ntxt2img mode\n 0%| | 0/55 [00:00<?, ?it/s]\n 2%|▏ | 1/55 [00:00<00:07, 7.37it/s]\n 4%|▎ | 2/55 [00:00<00:07, 7.34it/s]\n 5%|▌ | 3/55 [00:00<00:07, 7.33it/s]\n 7%|▋ | 4/55 [00:00<00:06, 7.31it/s]\n 9%|▉ | 5/55 [00:00<00:06, 7.30it/s]\n 11%|█ | 6/55 [00:00<00:06, 7.25it/s]\n 13%|█▎ | 7/55 [00:00<00:06, 7.26it/s]\n 15%|█▍ | 8/55 [00:01<00:06, 7.27it/s]\n 16%|█▋ | 9/55 [00:01<00:06, 7.28it/s]\n 18%|█▊ | 10/55 [00:01<00:06, 7.28it/s]\n 20%|██ | 11/55 [00:01<00:06, 7.29it/s]\n 22%|██▏ | 12/55 [00:01<00:05, 7.28it/s]\n 24%|██▎ | 13/55 [00:01<00:05, 7.28it/s]\n 25%|██▌ | 14/55 [00:01<00:05, 7.27it/s]\n 27%|██▋ | 15/55 [00:02<00:05, 7.27it/s]\n 29%|██▉ | 16/55 [00:02<00:05, 7.28it/s]\n 31%|███ | 17/55 [00:02<00:05, 7.28it/s]\n 33%|███▎ | 18/55 [00:02<00:05, 7.28it/s]\n 35%|███▍ | 19/55 [00:02<00:04, 7.28it/s]\n 36%|███▋ | 20/55 [00:02<00:04, 7.27it/s]\n 38%|███▊ | 21/55 [00:02<00:04, 7.27it/s]\n 40%|████ | 22/55 [00:03<00:04, 7.26it/s]\n 42%|████▏ | 23/55 [00:03<00:04, 7.27it/s]\n 44%|████▎ | 24/55 [00:03<00:04, 7.27it/s]\n 45%|████▌ | 25/55 [00:03<00:04, 7.27it/s]\n 47%|████▋ | 26/55 [00:03<00:03, 7.29it/s]\n 49%|████▉ | 27/55 [00:03<00:03, 7.29it/s]\n 51%|█████ | 28/55 [00:03<00:03, 7.29it/s]\n 53%|█████▎ | 29/55 [00:03<00:03, 7.30it/s]\n 55%|█████▍ | 30/55 [00:04<00:03, 7.29it/s]\n 56%|█████▋ | 31/55 [00:04<00:03, 7.29it/s]\n 58%|█████▊ | 32/55 [00:04<00:03, 7.29it/s]\n 60%|██████ | 33/55 [00:04<00:03, 7.29it/s]\n 62%|██████▏ | 34/55 [00:04<00:02, 7.29it/s]\n 64%|██████▎ | 35/55 [00:04<00:02, 7.28it/s]\n 65%|██████▌ | 36/55 [00:04<00:02, 7.28it/s]\n 67%|██████▋ | 37/55 [00:05<00:02, 7.28it/s]\n 69%|██████▉ | 38/55 [00:05<00:02, 7.28it/s]\n 71%|███████ | 39/55 [00:05<00:02, 7.29it/s]\n 73%|███████▎ | 40/55 [00:05<00:02, 7.30it/s]\n 75%|███████▍ | 41/55 [00:05<00:01, 7.30it/s]\n 76%|███████▋ | 42/55 [00:05<00:01, 7.30it/s]\n 78%|███████▊ | 43/55 [00:05<00:01, 7.30it/s]\n 80%|████████ | 44/55 [00:06<00:01, 7.29it/s]\n 82%|████████▏ | 45/55 [00:06<00:01, 7.30it/s]\n 84%|████████▎ | 46/55 [00:06<00:01, 7.29it/s]\n 85%|████████▌ | 47/55 [00:06<00:01, 7.30it/s]\n 87%|████████▋ | 48/55 [00:06<00:00, 7.30it/s]\n 89%|████████▉ | 49/55 [00:06<00:00, 7.30it/s]\n 91%|█████████ | 50/55 [00:06<00:00, 7.30it/s]\n 93%|█████████▎| 51/55 [00:06<00:00, 7.30it/s]\n 95%|█████████▍| 52/55 [00:07<00:00, 7.30it/s]\n 96%|█████████▋| 53/55 [00:07<00:00, 7.30it/s]\n 98%|█████████▊| 54/55 [00:07<00:00, 7.31it/s]\n100%|██████████| 55/55 [00:07<00:00, 7.31it/s]\n100%|██████████| 55/55 [00:07<00:00, 7.29it/s]\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:00<00:01, 8.82it/s]\n 13%|█▎ | 2/15 [00:00<00:01, 8.72it/s]\n 20%|██ | 3/15 [00:00<00:01, 8.69it/s]\n 27%|██▋ | 4/15 [00:00<00:01, 8.68it/s]\n 33%|███▎ | 5/15 [00:00<00:01, 8.67it/s]\n 40%|████ | 6/15 [00:00<00:01, 8.66it/s]\n 47%|████▋ | 7/15 [00:00<00:00, 8.66it/s]\n 53%|█████▎ | 8/15 [00:00<00:00, 8.65it/s]\n 60%|██████ | 9/15 [00:01<00:00, 8.64it/s]\n 67%|██████▋ | 10/15 [00:01<00:00, 8.64it/s]\n 73%|███████▎ | 11/15 [00:01<00:00, 8.64it/s]\n 80%|████████ | 12/15 [00:01<00:00, 8.65it/s]\n 87%|████████▋ | 13/15 [00:01<00:00, 8.65it/s]\n 93%|█████████▎| 14/15 [00:01<00:00, 8.65it/s]\n100%|██████████| 15/15 [00:01<00:00, 8.65it/s]\n100%|██████████| 15/15 [00:01<00:00, 8.66it/s]", "metrics": { "predict_time": 10.799655, "total_time": 18.05685 }, "output": [ "https://replicate.delivery/pbxt/SnUGeC2ECLSRPaaD7L5EMCnSFY5egPeKLZLSRNt90CiVHPHkA/out-0.png" ], "started_at": "2023-12-18T22:25:36.306471Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/jchtittbnqqmchlzllultw7y7y", "cancel": "https://api.replicate.com/v1/predictions/jchtittbnqqmchlzllultw7y7y/cancel" }, "version": "40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2" }
Generated inUsing seed: 16351 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A detective in a trench coat walking through a rainy, noir-style city street at night, in the style of <s0><s1>, crisp, sharp, photorealistic, movie scene txt2img mode 0%| | 0/55 [00:00<?, ?it/s] 2%|▏ | 1/55 [00:00<00:07, 7.37it/s] 4%|▎ | 2/55 [00:00<00:07, 7.34it/s] 5%|▌ | 3/55 [00:00<00:07, 7.33it/s] 7%|▋ | 4/55 [00:00<00:06, 7.31it/s] 9%|▉ | 5/55 [00:00<00:06, 7.30it/s] 11%|█ | 6/55 [00:00<00:06, 7.25it/s] 13%|█▎ | 7/55 [00:00<00:06, 7.26it/s] 15%|█▍ | 8/55 [00:01<00:06, 7.27it/s] 16%|█▋ | 9/55 [00:01<00:06, 7.28it/s] 18%|█▊ | 10/55 [00:01<00:06, 7.28it/s] 20%|██ | 11/55 [00:01<00:06, 7.29it/s] 22%|██▏ | 12/55 [00:01<00:05, 7.28it/s] 24%|██▎ | 13/55 [00:01<00:05, 7.28it/s] 25%|██▌ | 14/55 [00:01<00:05, 7.27it/s] 27%|██▋ | 15/55 [00:02<00:05, 7.27it/s] 29%|██▉ | 16/55 [00:02<00:05, 7.28it/s] 31%|███ | 17/55 [00:02<00:05, 7.28it/s] 33%|███▎ | 18/55 [00:02<00:05, 7.28it/s] 35%|███▍ | 19/55 [00:02<00:04, 7.28it/s] 36%|███▋ | 20/55 [00:02<00:04, 7.27it/s] 38%|███▊ | 21/55 [00:02<00:04, 7.27it/s] 40%|████ | 22/55 [00:03<00:04, 7.26it/s] 42%|████▏ | 23/55 [00:03<00:04, 7.27it/s] 44%|████▎ | 24/55 [00:03<00:04, 7.27it/s] 45%|████▌ | 25/55 [00:03<00:04, 7.27it/s] 47%|████▋ | 26/55 [00:03<00:03, 7.29it/s] 49%|████▉ | 27/55 [00:03<00:03, 7.29it/s] 51%|█████ | 28/55 [00:03<00:03, 7.29it/s] 53%|█████▎ | 29/55 [00:03<00:03, 7.30it/s] 55%|█████▍ | 30/55 [00:04<00:03, 7.29it/s] 56%|█████▋ | 31/55 [00:04<00:03, 7.29it/s] 58%|█████▊ | 32/55 [00:04<00:03, 7.29it/s] 60%|██████ | 33/55 [00:04<00:03, 7.29it/s] 62%|██████▏ | 34/55 [00:04<00:02, 7.29it/s] 64%|██████▎ | 35/55 [00:04<00:02, 7.28it/s] 65%|██████▌ | 36/55 [00:04<00:02, 7.28it/s] 67%|██████▋ | 37/55 [00:05<00:02, 7.28it/s] 69%|██████▉ | 38/55 [00:05<00:02, 7.28it/s] 71%|███████ | 39/55 [00:05<00:02, 7.29it/s] 73%|███████▎ | 40/55 [00:05<00:02, 7.30it/s] 75%|███████▍ | 41/55 [00:05<00:01, 7.30it/s] 76%|███████▋ | 42/55 [00:05<00:01, 7.30it/s] 78%|███████▊ | 43/55 [00:05<00:01, 7.30it/s] 80%|████████ | 44/55 [00:06<00:01, 7.29it/s] 82%|████████▏ | 45/55 [00:06<00:01, 7.30it/s] 84%|████████▎ | 46/55 [00:06<00:01, 7.29it/s] 85%|████████▌ | 47/55 [00:06<00:01, 7.30it/s] 87%|████████▋ | 48/55 [00:06<00:00, 7.30it/s] 89%|████████▉ | 49/55 [00:06<00:00, 7.30it/s] 91%|█████████ | 50/55 [00:06<00:00, 7.30it/s] 93%|█████████▎| 51/55 [00:06<00:00, 7.30it/s] 95%|█████████▍| 52/55 [00:07<00:00, 7.30it/s] 96%|█████████▋| 53/55 [00:07<00:00, 7.30it/s] 98%|█████████▊| 54/55 [00:07<00:00, 7.31it/s] 100%|██████████| 55/55 [00:07<00:00, 7.31it/s] 100%|██████████| 55/55 [00:07<00:00, 7.29it/s] 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:00<00:01, 8.82it/s] 13%|█▎ | 2/15 [00:00<00:01, 8.72it/s] 20%|██ | 3/15 [00:00<00:01, 8.69it/s] 27%|██▋ | 4/15 [00:00<00:01, 8.68it/s] 33%|███▎ | 5/15 [00:00<00:01, 8.67it/s] 40%|████ | 6/15 [00:00<00:01, 8.66it/s] 47%|████▋ | 7/15 [00:00<00:00, 8.66it/s] 53%|█████▎ | 8/15 [00:00<00:00, 8.65it/s] 60%|██████ | 9/15 [00:01<00:00, 8.64it/s] 67%|██████▋ | 10/15 [00:01<00:00, 8.64it/s] 73%|███████▎ | 11/15 [00:01<00:00, 8.64it/s] 80%|████████ | 12/15 [00:01<00:00, 8.65it/s] 87%|████████▋ | 13/15 [00:01<00:00, 8.65it/s] 93%|█████████▎| 14/15 [00:01<00:00, 8.65it/s] 100%|██████████| 15/15 [00:01<00:00, 8.65it/s] 100%|██████████| 15/15 [00:01<00:00, 8.66it/s]
Prediction
martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2IDt4epbdtb57xueyq54svlewnvnyStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 512
- prompt
- A traditional tea ceremony in a Japanese garden during cherry blossom season, in the style of TOK, crisp, sharp, photorealistic, movie scene
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.8
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- cropped, worst quality, low quality, glitch, deformed, mutated, disfigured
- prompt_strength
- 0.8
- num_inference_steps
- 70
{ "width": 1024, "height": 512, "prompt": "A traditional tea ceremony in a Japanese garden during cherry blossom season, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run martintmv-git/sdxl-cinematic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", { input: { width: 1024, height: 512, prompt: "A traditional tea ceremony in a Japanese garden during cherry blossom season, in the style of TOK, crisp, sharp, photorealistic, movie scene", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.8, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", prompt_strength: 0.8, num_inference_steps: 70 } } ); // 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 martintmv-git/sdxl-cinematic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", input={ "width": 1024, "height": 512, "prompt": "A traditional tea ceremony in a Japanese garden during cherry blossom season, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run martintmv-git/sdxl-cinematic 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": "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", "input": { "width": 1024, "height": 512, "prompt": "A traditional tea ceremony in a Japanese garden during cherry blossom season, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-12-18T22:28:43.718143Z", "created_at": "2023-12-18T22:28:07.932829Z", "data_removed": false, "error": null, "id": "t4epbdtb57xueyq54svlewnvny", "input": { "width": 1024, "height": 512, "prompt": "A traditional tea ceremony in a Japanese garden during cherry blossom season, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 }, "logs": "Using seed: 30297\nEnsuring enough disk space...\nFree disk space: 1597151207424\nDownloading weights: https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar\n2023-12-18T22:28:31Z | INFO | [ Initiating ] dest=/src/weights-cache/ff016a5a915406b1 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar\n2023-12-18T22:28:32Z | INFO | [ Complete ] dest=/src/weights-cache/ff016a5a915406b1 size=\"186 MB\" total_elapsed=0.746s url=https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar\nb''\nDownloaded weights in 0.8958368301391602 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A traditional tea ceremony in a Japanese garden during cherry blossom season, in the style of <s0><s1>, crisp, sharp, photorealistic, movie scene\ntxt2img mode\n 0%| | 0/55 [00:00<?, ?it/s]\n 2%|▏ | 1/55 [00:00<00:10, 5.14it/s]\n 4%|▎ | 2/55 [00:00<00:08, 6.22it/s]\n 5%|▌ | 3/55 [00:00<00:07, 6.66it/s]\n 7%|▋ | 4/55 [00:00<00:07, 6.88it/s]\n 9%|▉ | 5/55 [00:00<00:07, 7.01it/s]\n 11%|█ | 6/55 [00:00<00:06, 7.09it/s]\n 13%|█▎ | 7/55 [00:01<00:06, 7.14it/s]\n 15%|█▍ | 8/55 [00:01<00:06, 7.16it/s]\n 16%|█▋ | 9/55 [00:01<00:06, 7.18it/s]\n 18%|█▊ | 10/55 [00:01<00:06, 7.20it/s]\n 20%|██ | 11/55 [00:01<00:06, 7.21it/s]\n 22%|██▏ | 12/55 [00:01<00:05, 7.23it/s]\n 24%|██▎ | 13/55 [00:01<00:05, 7.24it/s]\n 25%|██▌ | 14/55 [00:01<00:05, 7.24it/s]\n 27%|██▋ | 15/55 [00:02<00:05, 7.23it/s]\n 29%|██▉ | 16/55 [00:02<00:05, 7.22it/s]\n 31%|███ | 17/55 [00:02<00:05, 7.24it/s]\n 33%|███▎ | 18/55 [00:02<00:05, 7.26it/s]\n 35%|███▍ | 19/55 [00:02<00:04, 7.27it/s]\n 36%|███▋ | 20/55 [00:02<00:04, 7.28it/s]\n 38%|███▊ | 21/55 [00:02<00:04, 7.29it/s]\n 40%|████ | 22/55 [00:03<00:04, 7.29it/s]\n 42%|████▏ | 23/55 [00:03<00:04, 7.29it/s]\n 44%|████▎ | 24/55 [00:03<00:04, 7.27it/s]\n 45%|████▌ | 25/55 [00:03<00:04, 7.27it/s]\n 47%|████▋ | 26/55 [00:03<00:03, 7.28it/s]\n 49%|████▉ | 27/55 [00:03<00:03, 7.29it/s]\n 51%|█████ | 28/55 [00:03<00:03, 7.29it/s]\n 53%|█████▎ | 29/55 [00:04<00:03, 7.29it/s]\n 55%|█████▍ | 30/55 [00:04<00:03, 7.28it/s]\n 56%|█████▋ | 31/55 [00:04<00:03, 7.28it/s]\n 58%|█████▊ | 32/55 [00:04<00:03, 7.28it/s]\n 60%|██████ | 33/55 [00:04<00:03, 7.28it/s]\n 62%|██████▏ | 34/55 [00:04<00:02, 7.28it/s]\n 64%|██████▎ | 35/55 [00:04<00:02, 7.28it/s]\n 65%|██████▌ | 36/55 [00:05<00:02, 7.29it/s]\n 67%|██████▋ | 37/55 [00:05<00:02, 7.29it/s]\n 69%|██████▉ | 38/55 [00:05<00:02, 7.28it/s]\n 71%|███████ | 39/55 [00:05<00:02, 7.27it/s]\n 73%|███████▎ | 40/55 [00:05<00:02, 7.27it/s]\n 75%|███████▍ | 41/55 [00:05<00:01, 7.26it/s]\n 76%|███████▋ | 42/55 [00:05<00:01, 7.26it/s]\n 78%|███████▊ | 43/55 [00:05<00:01, 7.26it/s]\n 80%|████████ | 44/55 [00:06<00:01, 7.27it/s]\n 82%|████████▏ | 45/55 [00:06<00:01, 7.27it/s]\n 84%|████████▎ | 46/55 [00:06<00:01, 7.27it/s]\n 85%|████████▌ | 47/55 [00:06<00:01, 7.27it/s]\n 87%|████████▋ | 48/55 [00:06<00:00, 7.27it/s]\n 89%|████████▉ | 49/55 [00:06<00:00, 7.27it/s]\n 91%|█████████ | 50/55 [00:06<00:00, 7.27it/s]\n 93%|█████████▎| 51/55 [00:07<00:00, 7.26it/s]\n 95%|█████████▍| 52/55 [00:07<00:00, 7.27it/s]\n 96%|█████████▋| 53/55 [00:07<00:00, 7.27it/s]\n 98%|█████████▊| 54/55 [00:07<00:00, 7.28it/s]\n100%|██████████| 55/55 [00:07<00:00, 7.28it/s]\n100%|██████████| 55/55 [00:07<00:00, 7.21it/s]\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:00<00:01, 7.51it/s]\n 13%|█▎ | 2/15 [00:00<00:01, 8.14it/s]\n 20%|██ | 3/15 [00:00<00:01, 8.37it/s]\n 27%|██▋ | 4/15 [00:00<00:01, 8.48it/s]\n 33%|███▎ | 5/15 [00:00<00:01, 8.53it/s]\n 40%|████ | 6/15 [00:00<00:01, 8.56it/s]\n 47%|████▋ | 7/15 [00:00<00:00, 8.60it/s]\n 53%|█████▎ | 8/15 [00:00<00:00, 8.59it/s]\n 60%|██████ | 9/15 [00:01<00:00, 8.59it/s]\n 67%|██████▋ | 10/15 [00:01<00:00, 8.60it/s]\n 73%|███████▎ | 11/15 [00:01<00:00, 8.60it/s]\n 80%|████████ | 12/15 [00:01<00:00, 8.61it/s]\n 87%|████████▋ | 13/15 [00:01<00:00, 8.63it/s]\n 93%|█████████▎| 14/15 [00:01<00:00, 8.63it/s]\n100%|██████████| 15/15 [00:01<00:00, 8.62it/s]\n100%|██████████| 15/15 [00:01<00:00, 8.54it/s]", "metrics": { "predict_time": 12.470708, "total_time": 35.785314 }, "output": [ "https://replicate.delivery/pbxt/i1SLkVs9fF2yI6WDQVVgZAIMmjYD7BCN7nBI2GVr29ZNzzBJA/out-0.png" ], "started_at": "2023-12-18T22:28:31.247435Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/t4epbdtb57xueyq54svlewnvny", "cancel": "https://api.replicate.com/v1/predictions/t4epbdtb57xueyq54svlewnvny/cancel" }, "version": "40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2" }
Generated inUsing seed: 30297 Ensuring enough disk space... Free disk space: 1597151207424 Downloading weights: https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar 2023-12-18T22:28:31Z | INFO | [ Initiating ] dest=/src/weights-cache/ff016a5a915406b1 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar 2023-12-18T22:28:32Z | INFO | [ Complete ] dest=/src/weights-cache/ff016a5a915406b1 size="186 MB" total_elapsed=0.746s url=https://replicate.delivery/pbxt/HfFr4HaeymgDTEUFvcGuiUsLXUYRmRQdQYe9RZnduvh2hNHkA/trained_model.tar b'' Downloaded weights in 0.8958368301391602 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A traditional tea ceremony in a Japanese garden during cherry blossom season, in the style of <s0><s1>, crisp, sharp, photorealistic, movie scene txt2img mode 0%| | 0/55 [00:00<?, ?it/s] 2%|▏ | 1/55 [00:00<00:10, 5.14it/s] 4%|▎ | 2/55 [00:00<00:08, 6.22it/s] 5%|▌ | 3/55 [00:00<00:07, 6.66it/s] 7%|▋ | 4/55 [00:00<00:07, 6.88it/s] 9%|▉ | 5/55 [00:00<00:07, 7.01it/s] 11%|█ | 6/55 [00:00<00:06, 7.09it/s] 13%|█▎ | 7/55 [00:01<00:06, 7.14it/s] 15%|█▍ | 8/55 [00:01<00:06, 7.16it/s] 16%|█▋ | 9/55 [00:01<00:06, 7.18it/s] 18%|█▊ | 10/55 [00:01<00:06, 7.20it/s] 20%|██ | 11/55 [00:01<00:06, 7.21it/s] 22%|██▏ | 12/55 [00:01<00:05, 7.23it/s] 24%|██▎ | 13/55 [00:01<00:05, 7.24it/s] 25%|██▌ | 14/55 [00:01<00:05, 7.24it/s] 27%|██▋ | 15/55 [00:02<00:05, 7.23it/s] 29%|██▉ | 16/55 [00:02<00:05, 7.22it/s] 31%|███ | 17/55 [00:02<00:05, 7.24it/s] 33%|███▎ | 18/55 [00:02<00:05, 7.26it/s] 35%|███▍ | 19/55 [00:02<00:04, 7.27it/s] 36%|███▋ | 20/55 [00:02<00:04, 7.28it/s] 38%|███▊ | 21/55 [00:02<00:04, 7.29it/s] 40%|████ | 22/55 [00:03<00:04, 7.29it/s] 42%|████▏ | 23/55 [00:03<00:04, 7.29it/s] 44%|████▎ | 24/55 [00:03<00:04, 7.27it/s] 45%|████▌ | 25/55 [00:03<00:04, 7.27it/s] 47%|████▋ | 26/55 [00:03<00:03, 7.28it/s] 49%|████▉ | 27/55 [00:03<00:03, 7.29it/s] 51%|█████ | 28/55 [00:03<00:03, 7.29it/s] 53%|█████▎ | 29/55 [00:04<00:03, 7.29it/s] 55%|█████▍ | 30/55 [00:04<00:03, 7.28it/s] 56%|█████▋ | 31/55 [00:04<00:03, 7.28it/s] 58%|█████▊ | 32/55 [00:04<00:03, 7.28it/s] 60%|██████ | 33/55 [00:04<00:03, 7.28it/s] 62%|██████▏ | 34/55 [00:04<00:02, 7.28it/s] 64%|██████▎ | 35/55 [00:04<00:02, 7.28it/s] 65%|██████▌ | 36/55 [00:05<00:02, 7.29it/s] 67%|██████▋ | 37/55 [00:05<00:02, 7.29it/s] 69%|██████▉ | 38/55 [00:05<00:02, 7.28it/s] 71%|███████ | 39/55 [00:05<00:02, 7.27it/s] 73%|███████▎ | 40/55 [00:05<00:02, 7.27it/s] 75%|███████▍ | 41/55 [00:05<00:01, 7.26it/s] 76%|███████▋ | 42/55 [00:05<00:01, 7.26it/s] 78%|███████▊ | 43/55 [00:05<00:01, 7.26it/s] 80%|████████ | 44/55 [00:06<00:01, 7.27it/s] 82%|████████▏ | 45/55 [00:06<00:01, 7.27it/s] 84%|████████▎ | 46/55 [00:06<00:01, 7.27it/s] 85%|████████▌ | 47/55 [00:06<00:01, 7.27it/s] 87%|████████▋ | 48/55 [00:06<00:00, 7.27it/s] 89%|████████▉ | 49/55 [00:06<00:00, 7.27it/s] 91%|█████████ | 50/55 [00:06<00:00, 7.27it/s] 93%|█████████▎| 51/55 [00:07<00:00, 7.26it/s] 95%|█████████▍| 52/55 [00:07<00:00, 7.27it/s] 96%|█████████▋| 53/55 [00:07<00:00, 7.27it/s] 98%|█████████▊| 54/55 [00:07<00:00, 7.28it/s] 100%|██████████| 55/55 [00:07<00:00, 7.28it/s] 100%|██████████| 55/55 [00:07<00:00, 7.21it/s] 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:00<00:01, 7.51it/s] 13%|█▎ | 2/15 [00:00<00:01, 8.14it/s] 20%|██ | 3/15 [00:00<00:01, 8.37it/s] 27%|██▋ | 4/15 [00:00<00:01, 8.48it/s] 33%|███▎ | 5/15 [00:00<00:01, 8.53it/s] 40%|████ | 6/15 [00:00<00:01, 8.56it/s] 47%|████▋ | 7/15 [00:00<00:00, 8.60it/s] 53%|█████▎ | 8/15 [00:00<00:00, 8.59it/s] 60%|██████ | 9/15 [00:01<00:00, 8.59it/s] 67%|██████▋ | 10/15 [00:01<00:00, 8.60it/s] 73%|███████▎ | 11/15 [00:01<00:00, 8.60it/s] 80%|████████ | 12/15 [00:01<00:00, 8.61it/s] 87%|████████▋ | 13/15 [00:01<00:00, 8.63it/s] 93%|█████████▎| 14/15 [00:01<00:00, 8.63it/s] 100%|██████████| 15/15 [00:01<00:00, 8.62it/s] 100%|██████████| 15/15 [00:01<00:00, 8.54it/s]
Prediction
martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2IDdwmzpjtbnrghr2seaw5jha7ygyStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 512
- prompt
- A rugged mountaineer's face up close, weathered and resolute, with a panoramic mountain view subtly blurred in the backdrop, in the style of TOK, crisp, sharp, photorealistic, movie scene
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.8
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- cropped, worst quality, low quality, glitch, deformed, mutated, disfigured
- prompt_strength
- 0.8
- num_inference_steps
- 70
{ "width": 1024, "height": 512, "prompt": "A rugged mountaineer's face up close, weathered and resolute, with a panoramic mountain view subtly blurred in the backdrop, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run martintmv-git/sdxl-cinematic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", { input: { width: 1024, height: 512, prompt: "A rugged mountaineer's face up close, weathered and resolute, with a panoramic mountain view subtly blurred in the backdrop, in the style of TOK, crisp, sharp, photorealistic, movie scene", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.8, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", prompt_strength: 0.8, num_inference_steps: 70 } } ); // 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 martintmv-git/sdxl-cinematic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", input={ "width": 1024, "height": 512, "prompt": "A rugged mountaineer's face up close, weathered and resolute, with a panoramic mountain view subtly blurred in the backdrop, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run martintmv-git/sdxl-cinematic 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": "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", "input": { "width": 1024, "height": 512, "prompt": "A rugged mountaineer\'s face up close, weathered and resolute, with a panoramic mountain view subtly blurred in the backdrop, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-12-18T22:45:33.314018Z", "created_at": "2023-12-18T22:45:13.694100Z", "data_removed": false, "error": null, "id": "dwmzpjtbnrghr2seaw5jha7ygy", "input": { "width": 1024, "height": 512, "prompt": "A rugged mountaineer's face up close, weathered and resolute, with a panoramic mountain view subtly blurred in the backdrop, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 }, "logs": "Using seed: 47133\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A rugged mountaineer's face up close, weathered and resolute, with a panoramic mountain view subtly blurred in the backdrop, in the style of <s0><s1>, crisp, sharp, photorealistic, movie scene\ntxt2img mode\n 0%| | 0/55 [00:00<?, ?it/s]\n 2%|▏ | 1/55 [00:00<00:10, 5.23it/s]\n 4%|▎ | 2/55 [00:00<00:08, 6.21it/s]\n 5%|▌ | 3/55 [00:00<00:07, 6.60it/s]\n 7%|▋ | 4/55 [00:00<00:07, 6.79it/s]\n 9%|▉ | 5/55 [00:00<00:07, 6.92it/s]\n 11%|█ | 6/55 [00:00<00:07, 6.99it/s]\n 13%|█▎ | 7/55 [00:01<00:06, 7.04it/s]\n 15%|█▍ | 8/55 [00:01<00:06, 7.07it/s]\n 16%|█▋ | 9/55 [00:01<00:06, 7.09it/s]\n 18%|█▊ | 10/55 [00:01<00:06, 7.11it/s]\n 20%|██ | 11/55 [00:01<00:06, 7.12it/s]\n 22%|██▏ | 12/55 [00:01<00:06, 7.13it/s]\n 24%|██▎ | 13/55 [00:01<00:05, 7.13it/s]\n 25%|██▌ | 14/55 [00:02<00:05, 7.14it/s]\n 27%|██▋ | 15/55 [00:02<00:05, 7.14it/s]\n 29%|██▉ | 16/55 [00:02<00:05, 7.13it/s]\n 31%|███ | 17/55 [00:02<00:05, 7.14it/s]\n 33%|███▎ | 18/55 [00:02<00:05, 7.15it/s]\n 35%|███▍ | 19/55 [00:02<00:05, 7.14it/s]\n 36%|███▋ | 20/55 [00:02<00:04, 7.14it/s]\n 38%|███▊ | 21/55 [00:02<00:04, 7.14it/s]\n 40%|████ | 22/55 [00:03<00:04, 7.13it/s]\n 42%|████▏ | 23/55 [00:03<00:04, 7.14it/s]\n 44%|████▎ | 24/55 [00:03<00:04, 7.14it/s]\n 45%|████▌ | 25/55 [00:03<00:04, 7.14it/s]\n 47%|████▋ | 26/55 [00:03<00:04, 7.13it/s]\n 49%|████▉ | 27/55 [00:03<00:03, 7.13it/s]\n 51%|█████ | 28/55 [00:03<00:03, 7.12it/s]\n 53%|█████▎ | 29/55 [00:04<00:03, 7.11it/s]\n 55%|█████▍ | 30/55 [00:04<00:03, 7.11it/s]\n 56%|█████▋ | 31/55 [00:04<00:03, 7.11it/s]\n 58%|█████▊ | 32/55 [00:04<00:03, 7.12it/s]\n 60%|██████ | 33/55 [00:04<00:03, 7.11it/s]\n 62%|██████▏ | 34/55 [00:04<00:02, 7.11it/s]\n 64%|██████▎ | 35/55 [00:04<00:02, 7.10it/s]\n 65%|██████▌ | 36/55 [00:05<00:02, 7.10it/s]\n 67%|██████▋ | 37/55 [00:05<00:02, 7.11it/s]\n 69%|██████▉ | 38/55 [00:05<00:02, 7.11it/s]\n 71%|███████ | 39/55 [00:05<00:02, 7.11it/s]\n 73%|███████▎ | 40/55 [00:05<00:02, 7.12it/s]\n 75%|███████▍ | 41/55 [00:05<00:01, 7.11it/s]\n 76%|███████▋ | 42/55 [00:05<00:01, 7.12it/s]\n 78%|███████▊ | 43/55 [00:06<00:01, 7.11it/s]\n 80%|████████ | 44/55 [00:06<00:01, 7.12it/s]\n 82%|████████▏ | 45/55 [00:06<00:01, 7.12it/s]\n 84%|████████▎ | 46/55 [00:06<00:01, 7.12it/s]\n 85%|████████▌ | 47/55 [00:06<00:01, 7.11it/s]\n 87%|████████▋ | 48/55 [00:06<00:00, 7.11it/s]\n 89%|████████▉ | 49/55 [00:06<00:00, 7.10it/s]\n 91%|█████████ | 50/55 [00:07<00:00, 7.10it/s]\n 93%|█████████▎| 51/55 [00:07<00:00, 7.11it/s]\n 95%|█████████▍| 52/55 [00:07<00:00, 7.11it/s]\n 96%|█████████▋| 53/55 [00:07<00:00, 7.11it/s]\n 98%|█████████▊| 54/55 [00:07<00:00, 7.11it/s]\n100%|██████████| 55/55 [00:07<00:00, 7.11it/s]\n100%|██████████| 55/55 [00:07<00:00, 7.08it/s]\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:00<00:01, 7.27it/s]\n 13%|█▎ | 2/15 [00:00<00:01, 7.91it/s]\n 20%|██ | 3/15 [00:00<00:01, 8.15it/s]\n 27%|██▋ | 4/15 [00:00<00:01, 8.26it/s]\n 33%|███▎ | 5/15 [00:00<00:01, 8.32it/s]\n 40%|████ | 6/15 [00:00<00:01, 8.36it/s]\n 47%|████▋ | 7/15 [00:00<00:00, 8.39it/s]\n 53%|█████▎ | 8/15 [00:00<00:00, 8.41it/s]\n 60%|██████ | 9/15 [00:01<00:00, 8.42it/s]\n 67%|██████▋ | 10/15 [00:01<00:00, 8.42it/s]\n 73%|███████▎ | 11/15 [00:01<00:00, 8.42it/s]\n 80%|████████ | 12/15 [00:01<00:00, 8.41it/s]\n 87%|████████▋ | 13/15 [00:01<00:00, 8.41it/s]\n 93%|█████████▎| 14/15 [00:01<00:00, 8.41it/s]\n100%|██████████| 15/15 [00:01<00:00, 8.41it/s]\n100%|██████████| 15/15 [00:01<00:00, 8.34it/s]", "metrics": { "predict_time": 11.766203, "total_time": 19.619918 }, "output": [ "https://replicate.delivery/pbxt/E6Se6PBrc0UGUyZmNJF9QNasWqOllIQPjVY998yJUIQG7zBJA/out-0.png" ], "started_at": "2023-12-18T22:45:21.547815Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/dwmzpjtbnrghr2seaw5jha7ygy", "cancel": "https://api.replicate.com/v1/predictions/dwmzpjtbnrghr2seaw5jha7ygy/cancel" }, "version": "40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2" }
Generated inUsing seed: 47133 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A rugged mountaineer's face up close, weathered and resolute, with a panoramic mountain view subtly blurred in the backdrop, in the style of <s0><s1>, crisp, sharp, photorealistic, movie scene txt2img mode 0%| | 0/55 [00:00<?, ?it/s] 2%|▏ | 1/55 [00:00<00:10, 5.23it/s] 4%|▎ | 2/55 [00:00<00:08, 6.21it/s] 5%|▌ | 3/55 [00:00<00:07, 6.60it/s] 7%|▋ | 4/55 [00:00<00:07, 6.79it/s] 9%|▉ | 5/55 [00:00<00:07, 6.92it/s] 11%|█ | 6/55 [00:00<00:07, 6.99it/s] 13%|█▎ | 7/55 [00:01<00:06, 7.04it/s] 15%|█▍ | 8/55 [00:01<00:06, 7.07it/s] 16%|█▋ | 9/55 [00:01<00:06, 7.09it/s] 18%|█▊ | 10/55 [00:01<00:06, 7.11it/s] 20%|██ | 11/55 [00:01<00:06, 7.12it/s] 22%|██▏ | 12/55 [00:01<00:06, 7.13it/s] 24%|██▎ | 13/55 [00:01<00:05, 7.13it/s] 25%|██▌ | 14/55 [00:02<00:05, 7.14it/s] 27%|██▋ | 15/55 [00:02<00:05, 7.14it/s] 29%|██▉ | 16/55 [00:02<00:05, 7.13it/s] 31%|███ | 17/55 [00:02<00:05, 7.14it/s] 33%|███▎ | 18/55 [00:02<00:05, 7.15it/s] 35%|███▍ | 19/55 [00:02<00:05, 7.14it/s] 36%|███▋ | 20/55 [00:02<00:04, 7.14it/s] 38%|███▊ | 21/55 [00:02<00:04, 7.14it/s] 40%|████ | 22/55 [00:03<00:04, 7.13it/s] 42%|████▏ | 23/55 [00:03<00:04, 7.14it/s] 44%|████▎ | 24/55 [00:03<00:04, 7.14it/s] 45%|████▌ | 25/55 [00:03<00:04, 7.14it/s] 47%|████▋ | 26/55 [00:03<00:04, 7.13it/s] 49%|████▉ | 27/55 [00:03<00:03, 7.13it/s] 51%|█████ | 28/55 [00:03<00:03, 7.12it/s] 53%|█████▎ | 29/55 [00:04<00:03, 7.11it/s] 55%|█████▍ | 30/55 [00:04<00:03, 7.11it/s] 56%|█████▋ | 31/55 [00:04<00:03, 7.11it/s] 58%|█████▊ | 32/55 [00:04<00:03, 7.12it/s] 60%|██████ | 33/55 [00:04<00:03, 7.11it/s] 62%|██████▏ | 34/55 [00:04<00:02, 7.11it/s] 64%|██████▎ | 35/55 [00:04<00:02, 7.10it/s] 65%|██████▌ | 36/55 [00:05<00:02, 7.10it/s] 67%|██████▋ | 37/55 [00:05<00:02, 7.11it/s] 69%|██████▉ | 38/55 [00:05<00:02, 7.11it/s] 71%|███████ | 39/55 [00:05<00:02, 7.11it/s] 73%|███████▎ | 40/55 [00:05<00:02, 7.12it/s] 75%|███████▍ | 41/55 [00:05<00:01, 7.11it/s] 76%|███████▋ | 42/55 [00:05<00:01, 7.12it/s] 78%|███████▊ | 43/55 [00:06<00:01, 7.11it/s] 80%|████████ | 44/55 [00:06<00:01, 7.12it/s] 82%|████████▏ | 45/55 [00:06<00:01, 7.12it/s] 84%|████████▎ | 46/55 [00:06<00:01, 7.12it/s] 85%|████████▌ | 47/55 [00:06<00:01, 7.11it/s] 87%|████████▋ | 48/55 [00:06<00:00, 7.11it/s] 89%|████████▉ | 49/55 [00:06<00:00, 7.10it/s] 91%|█████████ | 50/55 [00:07<00:00, 7.10it/s] 93%|█████████▎| 51/55 [00:07<00:00, 7.11it/s] 95%|█████████▍| 52/55 [00:07<00:00, 7.11it/s] 96%|█████████▋| 53/55 [00:07<00:00, 7.11it/s] 98%|█████████▊| 54/55 [00:07<00:00, 7.11it/s] 100%|██████████| 55/55 [00:07<00:00, 7.11it/s] 100%|██████████| 55/55 [00:07<00:00, 7.08it/s] 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:00<00:01, 7.27it/s] 13%|█▎ | 2/15 [00:00<00:01, 7.91it/s] 20%|██ | 3/15 [00:00<00:01, 8.15it/s] 27%|██▋ | 4/15 [00:00<00:01, 8.26it/s] 33%|███▎ | 5/15 [00:00<00:01, 8.32it/s] 40%|████ | 6/15 [00:00<00:01, 8.36it/s] 47%|████▋ | 7/15 [00:00<00:00, 8.39it/s] 53%|█████▎ | 8/15 [00:00<00:00, 8.41it/s] 60%|██████ | 9/15 [00:01<00:00, 8.42it/s] 67%|██████▋ | 10/15 [00:01<00:00, 8.42it/s] 73%|███████▎ | 11/15 [00:01<00:00, 8.42it/s] 80%|████████ | 12/15 [00:01<00:00, 8.41it/s] 87%|████████▋ | 13/15 [00:01<00:00, 8.41it/s] 93%|█████████▎| 14/15 [00:01<00:00, 8.41it/s] 100%|██████████| 15/15 [00:01<00:00, 8.41it/s] 100%|██████████| 15/15 [00:01<00:00, 8.34it/s]
Prediction
martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2IDxfgzr5dbbvfmcddgcdc45o46iiStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 512
- prompt
- A close-up of a smiling woman's face, capturing her bright eyes and joyful expression, with a softly blurred background, in the style of TOK, crisp, sharp, photorealistic, movie scene
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.8
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- cropped, worst quality, low quality, glitch, deformed, mutated, disfigured
- prompt_strength
- 0.8
- num_inference_steps
- 70
{ "width": 1024, "height": 512, "prompt": "A close-up of a smiling woman's face, capturing her bright eyes and joyful expression, with a softly blurred background, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run martintmv-git/sdxl-cinematic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", { input: { width: 1024, height: 512, prompt: "A close-up of a smiling woman's face, capturing her bright eyes and joyful expression, with a softly blurred background, in the style of TOK, crisp, sharp, photorealistic, movie scene", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.8, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", prompt_strength: 0.8, num_inference_steps: 70 } } ); // 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 martintmv-git/sdxl-cinematic using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", input={ "width": 1024, "height": 512, "prompt": "A close-up of a smiling woman's face, capturing her bright eyes and joyful expression, with a softly blurred background, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run martintmv-git/sdxl-cinematic 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": "martintmv-git/sdxl-cinematic:40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2", "input": { "width": 1024, "height": 512, "prompt": "A close-up of a smiling woman\'s face, capturing her bright eyes and joyful expression, with a softly blurred background, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-12-18T22:52:44.256969Z", "created_at": "2023-12-18T22:52:03.183911Z", "data_removed": false, "error": null, "id": "xfgzr5dbbvfmcddgcdc45o46ii", "input": { "width": 1024, "height": 512, "prompt": "A close-up of a smiling woman's face, capturing her bright eyes and joyful expression, with a softly blurred background, in the style of TOK, crisp, sharp, photorealistic, movie scene", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "cropped, worst quality, low quality, glitch, deformed, mutated, disfigured", "prompt_strength": 0.8, "num_inference_steps": 70 }, "logs": "Using seed: 11191\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A close-up of a smiling woman's face, capturing her bright eyes and joyful expression, with a softly blurred background, in the style of <s0><s1>, crisp, sharp, photorealistic, movie scene\ntxt2img mode\n 0%| | 0/55 [00:00<?, ?it/s]\n 2%|▏ | 1/55 [00:00<00:07, 7.36it/s]\n 4%|▎ | 2/55 [00:00<00:07, 7.33it/s]\n 5%|▌ | 3/55 [00:00<00:07, 7.31it/s]\n 7%|▋ | 4/55 [00:00<00:06, 7.30it/s]\n 9%|▉ | 5/55 [00:00<00:06, 7.30it/s]\n 11%|█ | 6/55 [00:00<00:06, 7.29it/s]\n 13%|█▎ | 7/55 [00:00<00:06, 7.29it/s]\n 15%|█▍ | 8/55 [00:01<00:06, 7.30it/s]\n 16%|█▋ | 9/55 [00:01<00:06, 7.31it/s]\n 18%|█▊ | 10/55 [00:01<00:06, 7.32it/s]\n 20%|██ | 11/55 [00:01<00:06, 7.33it/s]\n 22%|██▏ | 12/55 [00:01<00:05, 7.33it/s]\n 24%|██▎ | 13/55 [00:01<00:05, 7.33it/s]\n 25%|██▌ | 14/55 [00:01<00:05, 7.33it/s]\n 27%|██▋ | 15/55 [00:02<00:05, 7.33it/s]\n 29%|██▉ | 16/55 [00:02<00:05, 7.33it/s]\n 31%|███ | 17/55 [00:02<00:05, 7.33it/s]\n 33%|███▎ | 18/55 [00:02<00:05, 7.33it/s]\n 35%|███▍ | 19/55 [00:02<00:04, 7.33it/s]\n 36%|███▋ | 20/55 [00:02<00:04, 7.33it/s]\n 38%|███▊ | 21/55 [00:02<00:04, 7.33it/s]\n 40%|████ | 22/55 [00:03<00:04, 7.33it/s]\n 42%|████▏ | 23/55 [00:03<00:04, 7.32it/s]\n 44%|████▎ | 24/55 [00:03<00:04, 7.32it/s]\n 45%|████▌ | 25/55 [00:03<00:04, 7.33it/s]\n 47%|████▋ | 26/55 [00:03<00:03, 7.33it/s]\n 49%|████▉ | 27/55 [00:03<00:03, 7.33it/s]\n 51%|█████ | 28/55 [00:03<00:03, 7.33it/s]\n 53%|█████▎ | 29/55 [00:03<00:03, 7.33it/s]\n 55%|█████▍ | 30/55 [00:04<00:03, 7.33it/s]\n 56%|█████▋ | 31/55 [00:04<00:03, 7.33it/s]\n 58%|█████▊ | 32/55 [00:04<00:03, 7.33it/s]\n 60%|██████ | 33/55 [00:04<00:03, 7.32it/s]\n 62%|██████▏ | 34/55 [00:04<00:02, 7.32it/s]\n 64%|██████▎ | 35/55 [00:04<00:02, 7.32it/s]\n 65%|██████▌ | 36/55 [00:04<00:02, 7.33it/s]\n 67%|██████▋ | 37/55 [00:05<00:02, 7.33it/s]\n 69%|██████▉ | 38/55 [00:05<00:02, 7.33it/s]\n 71%|███████ | 39/55 [00:05<00:02, 7.33it/s]\n 73%|███████▎ | 40/55 [00:05<00:02, 7.32it/s]\n 75%|███████▍ | 41/55 [00:05<00:01, 7.32it/s]\n 76%|███████▋ | 42/55 [00:05<00:01, 7.33it/s]\n 78%|███████▊ | 43/55 [00:05<00:01, 7.32it/s]\n 80%|████████ | 44/55 [00:06<00:01, 7.32it/s]\n 82%|████████▏ | 45/55 [00:06<00:01, 7.32it/s]\n 84%|████████▎ | 46/55 [00:06<00:01, 7.32it/s]\n 85%|████████▌ | 47/55 [00:06<00:01, 7.32it/s]\n 87%|████████▋ | 48/55 [00:06<00:00, 7.32it/s]\n 89%|████████▉ | 49/55 [00:06<00:00, 7.32it/s]\n 91%|█████████ | 50/55 [00:06<00:00, 7.33it/s]\n 93%|█████████▎| 51/55 [00:06<00:00, 7.32it/s]\n 95%|█████████▍| 52/55 [00:07<00:00, 7.32it/s]\n 96%|█████████▋| 53/55 [00:07<00:00, 7.32it/s]\n 98%|█████████▊| 54/55 [00:07<00:00, 7.32it/s]\n100%|██████████| 55/55 [00:07<00:00, 7.32it/s]\n100%|██████████| 55/55 [00:07<00:00, 7.32it/s]\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:00<00:01, 8.81it/s]\n 13%|█▎ | 2/15 [00:00<00:01, 8.71it/s]\n 20%|██ | 3/15 [00:00<00:01, 8.69it/s]\n 27%|██▋ | 4/15 [00:00<00:01, 8.68it/s]\n 33%|███▎ | 5/15 [00:00<00:01, 8.67it/s]\n 40%|████ | 6/15 [00:00<00:01, 8.67it/s]\n 47%|████▋ | 7/15 [00:00<00:00, 8.67it/s]\n 53%|█████▎ | 8/15 [00:00<00:00, 8.64it/s]\n 60%|██████ | 9/15 [00:01<00:00, 8.63it/s]\n 67%|██████▋ | 10/15 [00:01<00:00, 8.64it/s]\n 73%|███████▎ | 11/15 [00:01<00:00, 8.63it/s]\n 80%|████████ | 12/15 [00:01<00:00, 8.64it/s]\n 87%|████████▋ | 13/15 [00:01<00:00, 8.65it/s]\n 93%|█████████▎| 14/15 [00:01<00:00, 8.66it/s]\n100%|██████████| 15/15 [00:01<00:00, 8.65it/s]\n100%|██████████| 15/15 [00:01<00:00, 8.66it/s]", "metrics": { "predict_time": 10.80574, "total_time": 41.073058 }, "output": [ "https://replicate.delivery/pbxt/GLKBN6rUBurADpdfdxaurITXw34tibMtWhWfUTmEJQf25PHkA/out-0.png" ], "started_at": "2023-12-18T22:52:33.451229Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/xfgzr5dbbvfmcddgcdc45o46ii", "cancel": "https://api.replicate.com/v1/predictions/xfgzr5dbbvfmcddgcdc45o46ii/cancel" }, "version": "40224311d882f9cd120ea648c0bd11836b606b70b4dc215a7c6661235eefbaf2" }
Generated inUsing seed: 11191 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A close-up of a smiling woman's face, capturing her bright eyes and joyful expression, with a softly blurred background, in the style of <s0><s1>, crisp, sharp, photorealistic, movie scene txt2img mode 0%| | 0/55 [00:00<?, ?it/s] 2%|▏ | 1/55 [00:00<00:07, 7.36it/s] 4%|▎ | 2/55 [00:00<00:07, 7.33it/s] 5%|▌ | 3/55 [00:00<00:07, 7.31it/s] 7%|▋ | 4/55 [00:00<00:06, 7.30it/s] 9%|▉ | 5/55 [00:00<00:06, 7.30it/s] 11%|█ | 6/55 [00:00<00:06, 7.29it/s] 13%|█▎ | 7/55 [00:00<00:06, 7.29it/s] 15%|█▍ | 8/55 [00:01<00:06, 7.30it/s] 16%|█▋ | 9/55 [00:01<00:06, 7.31it/s] 18%|█▊ | 10/55 [00:01<00:06, 7.32it/s] 20%|██ | 11/55 [00:01<00:06, 7.33it/s] 22%|██▏ | 12/55 [00:01<00:05, 7.33it/s] 24%|██▎ | 13/55 [00:01<00:05, 7.33it/s] 25%|██▌ | 14/55 [00:01<00:05, 7.33it/s] 27%|██▋ | 15/55 [00:02<00:05, 7.33it/s] 29%|██▉ | 16/55 [00:02<00:05, 7.33it/s] 31%|███ | 17/55 [00:02<00:05, 7.33it/s] 33%|███▎ | 18/55 [00:02<00:05, 7.33it/s] 35%|███▍ | 19/55 [00:02<00:04, 7.33it/s] 36%|███▋ | 20/55 [00:02<00:04, 7.33it/s] 38%|███▊ | 21/55 [00:02<00:04, 7.33it/s] 40%|████ | 22/55 [00:03<00:04, 7.33it/s] 42%|████▏ | 23/55 [00:03<00:04, 7.32it/s] 44%|████▎ | 24/55 [00:03<00:04, 7.32it/s] 45%|████▌ | 25/55 [00:03<00:04, 7.33it/s] 47%|████▋ | 26/55 [00:03<00:03, 7.33it/s] 49%|████▉ | 27/55 [00:03<00:03, 7.33it/s] 51%|█████ | 28/55 [00:03<00:03, 7.33it/s] 53%|█████▎ | 29/55 [00:03<00:03, 7.33it/s] 55%|█████▍ | 30/55 [00:04<00:03, 7.33it/s] 56%|█████▋ | 31/55 [00:04<00:03, 7.33it/s] 58%|█████▊ | 32/55 [00:04<00:03, 7.33it/s] 60%|██████ | 33/55 [00:04<00:03, 7.32it/s] 62%|██████▏ | 34/55 [00:04<00:02, 7.32it/s] 64%|██████▎ | 35/55 [00:04<00:02, 7.32it/s] 65%|██████▌ | 36/55 [00:04<00:02, 7.33it/s] 67%|██████▋ | 37/55 [00:05<00:02, 7.33it/s] 69%|██████▉ | 38/55 [00:05<00:02, 7.33it/s] 71%|███████ | 39/55 [00:05<00:02, 7.33it/s] 73%|███████▎ | 40/55 [00:05<00:02, 7.32it/s] 75%|███████▍ | 41/55 [00:05<00:01, 7.32it/s] 76%|███████▋ | 42/55 [00:05<00:01, 7.33it/s] 78%|███████▊ | 43/55 [00:05<00:01, 7.32it/s] 80%|████████ | 44/55 [00:06<00:01, 7.32it/s] 82%|████████▏ | 45/55 [00:06<00:01, 7.32it/s] 84%|████████▎ | 46/55 [00:06<00:01, 7.32it/s] 85%|████████▌ | 47/55 [00:06<00:01, 7.32it/s] 87%|████████▋ | 48/55 [00:06<00:00, 7.32it/s] 89%|████████▉ | 49/55 [00:06<00:00, 7.32it/s] 91%|█████████ | 50/55 [00:06<00:00, 7.33it/s] 93%|█████████▎| 51/55 [00:06<00:00, 7.32it/s] 95%|█████████▍| 52/55 [00:07<00:00, 7.32it/s] 96%|█████████▋| 53/55 [00:07<00:00, 7.32it/s] 98%|█████████▊| 54/55 [00:07<00:00, 7.32it/s] 100%|██████████| 55/55 [00:07<00:00, 7.32it/s] 100%|██████████| 55/55 [00:07<00:00, 7.32it/s] 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:00<00:01, 8.81it/s] 13%|█▎ | 2/15 [00:00<00:01, 8.71it/s] 20%|██ | 3/15 [00:00<00:01, 8.69it/s] 27%|██▋ | 4/15 [00:00<00:01, 8.68it/s] 33%|███▎ | 5/15 [00:00<00:01, 8.67it/s] 40%|████ | 6/15 [00:00<00:01, 8.67it/s] 47%|████▋ | 7/15 [00:00<00:00, 8.67it/s] 53%|█████▎ | 8/15 [00:00<00:00, 8.64it/s] 60%|██████ | 9/15 [00:01<00:00, 8.63it/s] 67%|██████▋ | 10/15 [00:01<00:00, 8.64it/s] 73%|███████▎ | 11/15 [00:01<00:00, 8.63it/s] 80%|████████ | 12/15 [00:01<00:00, 8.64it/s] 87%|████████▋ | 13/15 [00:01<00:00, 8.65it/s] 93%|█████████▎| 14/15 [00:01<00:00, 8.66it/s] 100%|██████████| 15/15 [00:01<00:00, 8.65it/s] 100%|██████████| 15/15 [00:01<00:00, 8.66it/s]
Want to make some of these yourself?
Run this model