fermatresearch / sdxl-improved-refiner
Great image quality, good old SDXL with a new and improved Tile refiner.
- Public
- 817 runs
-
L40S
Prediction
fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527eIDd5uroutbzbbvo44gmehlqzalayStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- seed
- 16010
- width
- 768
- height
- 768
- prompt
- An astronaut riding a rainbow unicorn, cinematic, dramatic
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- tile_refine
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- prompt_strength
- 0.8
- tile_refine_steps
- 20
- num_inference_steps
- 25
- tile_refine_strength
- 0.5
- tile_refine_conditioning_strength
- 0.5
{ "seed": 16010, "width": 768, "height": 768, "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": true, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "tile_refine_steps": 20, "num_inference_steps": 25, "tile_refine_strength": 0.5, "tile_refine_conditioning_strength": 0.5 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run fermatresearch/sdxl-improved-refiner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e", { input: { seed: 16010, width: 768, height: 768, prompt: "An astronaut riding a rainbow unicorn, cinematic, dramatic", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, tile_refine: true, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "", prompt_strength: 0.8, tile_refine_steps: 20, num_inference_steps: 25, tile_refine_strength: 0.5, tile_refine_conditioning_strength: 0.5 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun fermatresearch/sdxl-improved-refiner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e", input={ "seed": 16010, "width": 768, "height": 768, "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": True, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "tile_refine_steps": 20, "num_inference_steps": 25, "tile_refine_strength": 0.5, "tile_refine_conditioning_strength": 0.5 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run fermatresearch/sdxl-improved-refiner 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": "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e", "input": { "seed": 16010, "width": 768, "height": 768, "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": true, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "tile_refine_steps": 20, "num_inference_steps": 25, "tile_refine_strength": 0.5, "tile_refine_conditioning_strength": 0.5 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-16T16:41:31.780825Z", "created_at": "2024-01-16T16:38:46.808996Z", "data_removed": false, "error": null, "id": "d5uroutbzbbvo44gmehlqzalay", "input": { "seed": 16010, "width": 768, "height": 768, "prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": true, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "tile_refine_steps": 20, "num_inference_steps": 25, "tile_refine_strength": 0.5, "tile_refine_conditioning_strength": 0.5 }, "logs": "Using seed: 16010\nPrompt: An astronaut riding a rainbow unicorn, cinematic, dramatic\ntxt2img mode\n 0%| | 0/20 [00:00<?, ?it/s]\n 5%|▌ | 1/20 [00:00<00:05, 3.59it/s]\n 10%|█ | 2/20 [00:00<00:03, 5.40it/s]\n 15%|█▌ | 3/20 [00:00<00:02, 6.43it/s]\n 20%|██ | 4/20 [00:00<00:02, 7.05it/s]\n 25%|██▌ | 5/20 [00:00<00:02, 7.44it/s]\n 30%|███ | 6/20 [00:00<00:01, 7.69it/s]\n 35%|███▌ | 7/20 [00:01<00:01, 7.86it/s]\n 40%|████ | 8/20 [00:01<00:01, 7.97it/s]\n 45%|████▌ | 9/20 [00:01<00:01, 8.05it/s]\n 50%|█████ | 10/20 [00:01<00:01, 8.11it/s]\n 55%|█████▌ | 11/20 [00:01<00:01, 8.16it/s]\n 60%|██████ | 12/20 [00:01<00:00, 8.20it/s]\n 65%|██████▌ | 13/20 [00:01<00:00, 8.22it/s]\n 70%|███████ | 14/20 [00:01<00:00, 8.24it/s]\n 75%|███████▌ | 15/20 [00:01<00:00, 8.25it/s]\n 80%|████████ | 16/20 [00:02<00:00, 8.25it/s]\n 85%|████████▌ | 17/20 [00:02<00:00, 8.26it/s]\n 90%|█████████ | 18/20 [00:02<00:00, 8.26it/s]\n 95%|█████████▌| 19/20 [00:02<00:00, 8.26it/s]\n100%|██████████| 20/20 [00:02<00:00, 8.27it/s]\n100%|██████████| 20/20 [00:02<00:00, 7.76it/s]\n 0%| | 0/5 [00:00<?, ?it/s]\n 20%|██ | 1/5 [00:00<00:00, 7.31it/s]\n 40%|████ | 2/5 [00:00<00:00, 7.66it/s]\n 60%|██████ | 3/5 [00:00<00:00, 7.78it/s]\n 80%|████████ | 4/5 [00:00<00:00, 7.83it/s]\n100%|██████████| 5/5 [00:00<00:00, 7.87it/s]\n100%|██████████| 5/5 [00:00<00:00, 7.79it/s]\n 0%| | 0/10 [00:00<?, ?it/s]\n 10%|█ | 1/10 [00:00<00:01, 5.82it/s]\n 30%|███ | 3/10 [00:00<00:00, 8.12it/s]\n 40%|████ | 4/10 [00:00<00:00, 7.73it/s]\n 50%|█████ | 5/10 [00:00<00:00, 7.49it/s]\n 60%|██████ | 6/10 [00:00<00:00, 7.35it/s]\n 70%|███████ | 7/10 [00:00<00:00, 7.25it/s]\n 80%|████████ | 8/10 [00:01<00:00, 7.18it/s]\n 90%|█████████ | 9/10 [00:01<00:00, 7.14it/s]\n100%|██████████| 10/10 [00:01<00:00, 7.12it/s]\n100%|██████████| 10/10 [00:01<00:00, 7.27it/s]", "metrics": { "predict_time": 7.556292, "total_time": 164.971829 }, "output": [ "https://replicate.delivery/pbxt/uVlVR57RGYrNIJRQZ1NwDEs8xhoEQfLhxnkJO0bkddJdHjGJA/out-0.png" ], "started_at": "2024-01-16T16:41:24.224533Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/d5uroutbzbbvo44gmehlqzalay", "cancel": "https://api.replicate.com/v1/predictions/d5uroutbzbbvo44gmehlqzalay/cancel" }, "version": "58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e" }Generated inUsing seed: 16010 Prompt: An astronaut riding a rainbow unicorn, cinematic, dramatic txt2img mode 0%| | 0/20 [00:00<?, ?it/s] 5%|▌ | 1/20 [00:00<00:05, 3.59it/s] 10%|█ | 2/20 [00:00<00:03, 5.40it/s] 15%|█▌ | 3/20 [00:00<00:02, 6.43it/s] 20%|██ | 4/20 [00:00<00:02, 7.05it/s] 25%|██▌ | 5/20 [00:00<00:02, 7.44it/s] 30%|███ | 6/20 [00:00<00:01, 7.69it/s] 35%|███▌ | 7/20 [00:01<00:01, 7.86it/s] 40%|████ | 8/20 [00:01<00:01, 7.97it/s] 45%|████▌ | 9/20 [00:01<00:01, 8.05it/s] 50%|█████ | 10/20 [00:01<00:01, 8.11it/s] 55%|█████▌ | 11/20 [00:01<00:01, 8.16it/s] 60%|██████ | 12/20 [00:01<00:00, 8.20it/s] 65%|██████▌ | 13/20 [00:01<00:00, 8.22it/s] 70%|███████ | 14/20 [00:01<00:00, 8.24it/s] 75%|███████▌ | 15/20 [00:01<00:00, 8.25it/s] 80%|████████ | 16/20 [00:02<00:00, 8.25it/s] 85%|████████▌ | 17/20 [00:02<00:00, 8.26it/s] 90%|█████████ | 18/20 [00:02<00:00, 8.26it/s] 95%|█████████▌| 19/20 [00:02<00:00, 8.26it/s] 100%|██████████| 20/20 [00:02<00:00, 8.27it/s] 100%|██████████| 20/20 [00:02<00:00, 7.76it/s] 0%| | 0/5 [00:00<?, ?it/s] 20%|██ | 1/5 [00:00<00:00, 7.31it/s] 40%|████ | 2/5 [00:00<00:00, 7.66it/s] 60%|██████ | 3/5 [00:00<00:00, 7.78it/s] 80%|████████ | 4/5 [00:00<00:00, 7.83it/s] 100%|██████████| 5/5 [00:00<00:00, 7.87it/s] 100%|██████████| 5/5 [00:00<00:00, 7.79it/s] 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:01, 5.82it/s] 30%|███ | 3/10 [00:00<00:00, 8.12it/s] 40%|████ | 4/10 [00:00<00:00, 7.73it/s] 50%|█████ | 5/10 [00:00<00:00, 7.49it/s] 60%|██████ | 6/10 [00:00<00:00, 7.35it/s] 70%|███████ | 7/10 [00:00<00:00, 7.25it/s] 80%|████████ | 8/10 [00:01<00:00, 7.18it/s] 90%|█████████ | 9/10 [00:01<00:00, 7.14it/s] 100%|██████████| 10/10 [00:01<00:00, 7.12it/s] 100%|██████████| 10/10 [00:01<00:00, 7.27it/s]Prediction
fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527eIDy5jiaztbhbn6aomtyu4bqsdioiStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- seed
- 48373
- width
- 1024
- height
- 1024
- prompt
- A studio photo of a rainbow coloured cat
- refine
- expert_ensemble_refiner
- scheduler
- KarrasDPM
- lora_scale
- 0.6
- num_outputs
- 1
- tile_refine
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- prompt_strength
- 0.8
- tile_refine_steps
- 20
- num_inference_steps
- 50
- tile_refine_strength
- 0.5
- tile_refine_conditioning_strength
- 0.5
{ "seed": 48373, "width": 1024, "height": 1024, "prompt": "A studio photo of a rainbow coloured cat", "refine": "expert_ensemble_refiner", "scheduler": "KarrasDPM", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": true, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "prompt_strength": 0.8, "tile_refine_steps": 20, "num_inference_steps": 50, "tile_refine_strength": 0.5, "tile_refine_conditioning_strength": 0.5 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run fermatresearch/sdxl-improved-refiner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e", { input: { seed: 48373, width: 1024, height: 1024, prompt: "A studio photo of a rainbow coloured cat", refine: "expert_ensemble_refiner", scheduler: "KarrasDPM", lora_scale: 0.6, num_outputs: 1, tile_refine: true, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, prompt_strength: 0.8, tile_refine_steps: 20, num_inference_steps: 50, tile_refine_strength: 0.5, tile_refine_conditioning_strength: 0.5 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun fermatresearch/sdxl-improved-refiner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e", input={ "seed": 48373, "width": 1024, "height": 1024, "prompt": "A studio photo of a rainbow coloured cat", "refine": "expert_ensemble_refiner", "scheduler": "KarrasDPM", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": True, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "prompt_strength": 0.8, "tile_refine_steps": 20, "num_inference_steps": 50, "tile_refine_strength": 0.5, "tile_refine_conditioning_strength": 0.5 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run fermatresearch/sdxl-improved-refiner 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": "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e", "input": { "seed": 48373, "width": 1024, "height": 1024, "prompt": "A studio photo of a rainbow coloured cat", "refine": "expert_ensemble_refiner", "scheduler": "KarrasDPM", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": true, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "prompt_strength": 0.8, "tile_refine_steps": 20, "num_inference_steps": 50, "tile_refine_strength": 0.5, "tile_refine_conditioning_strength": 0.5 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-16T16:49:45.736839Z", "created_at": "2024-01-16T16:49:31.281327Z", "data_removed": false, "error": null, "id": "y5jiaztbhbn6aomtyu4bqsdioi", "input": { "seed": 48373, "width": 1024, "height": 1024, "prompt": "A studio photo of a rainbow coloured cat", "refine": "expert_ensemble_refiner", "scheduler": "KarrasDPM", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": true, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "prompt_strength": 0.8, "tile_refine_steps": 20, "num_inference_steps": 50, "tile_refine_strength": 0.5, "tile_refine_conditioning_strength": 0.5 }, "logs": "Using seed: 48373\nPrompt: A studio photo of a rainbow coloured cat\ntxt2img mode\n 0%| | 0/31 [00:00<?, ?it/s]\n 3%|▎ | 1/31 [00:00<00:05, 5.15it/s]\n 6%|▋ | 2/31 [00:00<00:04, 6.79it/s]\n 10%|▉ | 3/31 [00:00<00:04, 5.92it/s]\n 13%|█▎ | 4/31 [00:00<00:04, 5.58it/s]\n 16%|█▌ | 5/31 [00:00<00:04, 5.41it/s]\n 19%|█▉ | 6/31 [00:01<00:04, 5.30it/s]\n 23%|██▎ | 7/31 [00:01<00:04, 5.23it/s]\n 26%|██▌ | 8/31 [00:01<00:04, 5.19it/s]\n 29%|██▉ | 9/31 [00:01<00:04, 5.17it/s]\n 32%|███▏ | 10/31 [00:01<00:04, 5.15it/s]\n 35%|███▌ | 11/31 [00:02<00:03, 5.13it/s]\n 39%|███▊ | 12/31 [00:02<00:03, 5.12it/s]\n 42%|████▏ | 13/31 [00:02<00:03, 5.12it/s]\n 45%|████▌ | 14/31 [00:02<00:03, 5.12it/s]\n 48%|████▊ | 15/31 [00:02<00:03, 5.11it/s]\n 52%|█████▏ | 16/31 [00:03<00:02, 5.11it/s]\n 55%|█████▍ | 17/31 [00:03<00:02, 5.10it/s]\n 58%|█████▊ | 18/31 [00:03<00:02, 5.10it/s]\n 61%|██████▏ | 19/31 [00:03<00:02, 5.10it/s]\n 65%|██████▍ | 20/31 [00:03<00:02, 5.11it/s]\n 68%|██████▊ | 21/31 [00:04<00:01, 5.11it/s]\n 71%|███████ | 22/31 [00:04<00:01, 5.10it/s]\n 74%|███████▍ | 23/31 [00:04<00:01, 5.10it/s]\n 77%|███████▋ | 24/31 [00:04<00:01, 5.10it/s]\n 81%|████████ | 25/31 [00:04<00:01, 5.10it/s]\n 84%|████████▍ | 26/31 [00:05<00:00, 5.10it/s]\n 87%|████████▋ | 27/31 [00:05<00:00, 5.10it/s]\n 90%|█████████ | 28/31 [00:05<00:00, 5.09it/s]\n 94%|█████████▎| 29/31 [00:05<00:00, 5.09it/s]\n 97%|█████████▋| 30/31 [00:05<00:00, 5.09it/s]\n100%|██████████| 31/31 [00:05<00:00, 5.10it/s]\n100%|██████████| 31/31 [00:05<00:00, 5.17it/s]\n 0%| | 0/10 [00:00<?, ?it/s]\n 10%|█ | 1/10 [00:00<00:02, 4.33it/s]\n 20%|██ | 2/10 [00:00<00:01, 4.31it/s]\n 30%|███ | 3/10 [00:00<00:01, 4.30it/s]\n 40%|████ | 4/10 [00:00<00:01, 4.29it/s]\n 50%|█████ | 5/10 [00:01<00:01, 4.28it/s]\n 60%|██████ | 6/10 [00:01<00:00, 4.29it/s]\n 70%|███████ | 7/10 [00:01<00:00, 4.29it/s]\n 80%|████████ | 8/10 [00:01<00:00, 4.29it/s]\n 90%|█████████ | 9/10 [00:02<00:00, 4.29it/s]\n100%|██████████| 10/10 [00:02<00:00, 4.29it/s]\n100%|██████████| 10/10 [00:02<00:00, 4.29it/s]\n 0%| | 0/10 [00:00<?, ?it/s]\n 10%|█ | 1/10 [00:00<00:02, 3.06it/s]\n 20%|██ | 2/10 [00:00<00:01, 4.23it/s]\n 30%|███ | 3/10 [00:00<00:01, 3.61it/s]\n 40%|████ | 4/10 [00:01<00:01, 3.36it/s]\n 50%|█████ | 5/10 [00:01<00:01, 3.25it/s]\n 60%|██████ | 6/10 [00:01<00:01, 3.17it/s]\n 70%|███████ | 7/10 [00:02<00:00, 3.13it/s]\n 80%|████████ | 8/10 [00:02<00:00, 3.10it/s]\n 90%|█████████ | 9/10 [00:02<00:00, 3.09it/s]\n100%|██████████| 10/10 [00:03<00:00, 3.07it/s]\n100%|██████████| 10/10 [00:03<00:00, 3.20it/s]", "metrics": { "predict_time": 14.41882, "total_time": 14.455512 }, "output": [ "https://replicate.delivery/pbxt/vKXf5iicWE1NPShzjR6rRYbdaDH6DMq22fPFSfLIuyrQtMakA/out-0.png" ], "started_at": "2024-01-16T16:49:31.318019Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/y5jiaztbhbn6aomtyu4bqsdioi", "cancel": "https://api.replicate.com/v1/predictions/y5jiaztbhbn6aomtyu4bqsdioi/cancel" }, "version": "58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e" }Generated inUsing seed: 48373 Prompt: A studio photo of a rainbow coloured cat txt2img mode 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:00<00:05, 5.15it/s] 6%|▋ | 2/31 [00:00<00:04, 6.79it/s] 10%|▉ | 3/31 [00:00<00:04, 5.92it/s] 13%|█▎ | 4/31 [00:00<00:04, 5.58it/s] 16%|█▌ | 5/31 [00:00<00:04, 5.41it/s] 19%|█▉ | 6/31 [00:01<00:04, 5.30it/s] 23%|██▎ | 7/31 [00:01<00:04, 5.23it/s] 26%|██▌ | 8/31 [00:01<00:04, 5.19it/s] 29%|██▉ | 9/31 [00:01<00:04, 5.17it/s] 32%|███▏ | 10/31 [00:01<00:04, 5.15it/s] 35%|███▌ | 11/31 [00:02<00:03, 5.13it/s] 39%|███▊ | 12/31 [00:02<00:03, 5.12it/s] 42%|████▏ | 13/31 [00:02<00:03, 5.12it/s] 45%|████▌ | 14/31 [00:02<00:03, 5.12it/s] 48%|████▊ | 15/31 [00:02<00:03, 5.11it/s] 52%|█████▏ | 16/31 [00:03<00:02, 5.11it/s] 55%|█████▍ | 17/31 [00:03<00:02, 5.10it/s] 58%|█████▊ | 18/31 [00:03<00:02, 5.10it/s] 61%|██████▏ | 19/31 [00:03<00:02, 5.10it/s] 65%|██████▍ | 20/31 [00:03<00:02, 5.11it/s] 68%|██████▊ | 21/31 [00:04<00:01, 5.11it/s] 71%|███████ | 22/31 [00:04<00:01, 5.10it/s] 74%|███████▍ | 23/31 [00:04<00:01, 5.10it/s] 77%|███████▋ | 24/31 [00:04<00:01, 5.10it/s] 81%|████████ | 25/31 [00:04<00:01, 5.10it/s] 84%|████████▍ | 26/31 [00:05<00:00, 5.10it/s] 87%|████████▋ | 27/31 [00:05<00:00, 5.10it/s] 90%|█████████ | 28/31 [00:05<00:00, 5.09it/s] 94%|█████████▎| 29/31 [00:05<00:00, 5.09it/s] 97%|█████████▋| 30/31 [00:05<00:00, 5.09it/s] 100%|██████████| 31/31 [00:05<00:00, 5.10it/s] 100%|██████████| 31/31 [00:05<00:00, 5.17it/s] 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:02, 4.33it/s] 20%|██ | 2/10 [00:00<00:01, 4.31it/s] 30%|███ | 3/10 [00:00<00:01, 4.30it/s] 40%|████ | 4/10 [00:00<00:01, 4.29it/s] 50%|█████ | 5/10 [00:01<00:01, 4.28it/s] 60%|██████ | 6/10 [00:01<00:00, 4.29it/s] 70%|███████ | 7/10 [00:01<00:00, 4.29it/s] 80%|████████ | 8/10 [00:01<00:00, 4.29it/s] 90%|█████████ | 9/10 [00:02<00:00, 4.29it/s] 100%|██████████| 10/10 [00:02<00:00, 4.29it/s] 100%|██████████| 10/10 [00:02<00:00, 4.29it/s] 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:02, 3.06it/s] 20%|██ | 2/10 [00:00<00:01, 4.23it/s] 30%|███ | 3/10 [00:00<00:01, 3.61it/s] 40%|████ | 4/10 [00:01<00:01, 3.36it/s] 50%|█████ | 5/10 [00:01<00:01, 3.25it/s] 60%|██████ | 6/10 [00:01<00:01, 3.17it/s] 70%|███████ | 7/10 [00:02<00:00, 3.13it/s] 80%|████████ | 8/10 [00:02<00:00, 3.10it/s] 90%|█████████ | 9/10 [00:02<00:00, 3.09it/s] 100%|██████████| 10/10 [00:03<00:00, 3.07it/s] 100%|██████████| 10/10 [00:03<00:00, 3.20it/s]Prediction
fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527eIDaaz5bc3bjlr2hv2weeqbwqfu2aStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- seed
- 48161
- width
- 1344
- height
- 768
- prompt
- A film still of a robot, sci-fi, cool color grading, 70mm, bokeh, cinematic, anamorphic, beautiful
- refine
- expert_ensemble_refiner
- scheduler
- KarrasDPM
- lora_scale
- 0.6
- num_outputs
- 1
- tile_refine
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- soft, blurry, ugly
- prompt_strength
- 0.8
- tile_refine_steps
- 20
- num_inference_steps
- 50
- tile_refine_strength
- 0.5
- tile_refine_conditioning_strength
- 0.5
{ "seed": 48161, "width": 1344, "height": 768, "prompt": "A film still of a robot, sci-fi, cool color grading, 70mm, bokeh, cinematic, anamorphic, beautiful", "refine": "expert_ensemble_refiner", "scheduler": "KarrasDPM", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": true, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "soft, blurry, ugly", "prompt_strength": 0.8, "tile_refine_steps": 20, "num_inference_steps": 50, "tile_refine_strength": 0.5, "tile_refine_conditioning_strength": 0.5 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run fermatresearch/sdxl-improved-refiner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e", { input: { seed: 48161, width: 1344, height: 768, prompt: "A film still of a robot, sci-fi, cool color grading, 70mm, bokeh, cinematic, anamorphic, beautiful", refine: "expert_ensemble_refiner", scheduler: "KarrasDPM", lora_scale: 0.6, num_outputs: 1, tile_refine: true, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "soft, blurry, ugly", prompt_strength: 0.8, tile_refine_steps: 20, num_inference_steps: 50, tile_refine_strength: 0.5, tile_refine_conditioning_strength: 0.5 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun fermatresearch/sdxl-improved-refiner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e", input={ "seed": 48161, "width": 1344, "height": 768, "prompt": "A film still of a robot, sci-fi, cool color grading, 70mm, bokeh, cinematic, anamorphic, beautiful", "refine": "expert_ensemble_refiner", "scheduler": "KarrasDPM", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": True, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "soft, blurry, ugly", "prompt_strength": 0.8, "tile_refine_steps": 20, "num_inference_steps": 50, "tile_refine_strength": 0.5, "tile_refine_conditioning_strength": 0.5 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run fermatresearch/sdxl-improved-refiner 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": "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e", "input": { "seed": 48161, "width": 1344, "height": 768, "prompt": "A film still of a robot, sci-fi, cool color grading, 70mm, bokeh, cinematic, anamorphic, beautiful", "refine": "expert_ensemble_refiner", "scheduler": "KarrasDPM", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": true, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "soft, blurry, ugly", "prompt_strength": 0.8, "tile_refine_steps": 20, "num_inference_steps": 50, "tile_refine_strength": 0.5, "tile_refine_conditioning_strength": 0.5 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-16T16:50:39.549158Z", "created_at": "2024-01-16T16:50:25.268366Z", "data_removed": false, "error": null, "id": "aaz5bc3bjlr2hv2weeqbwqfu2a", "input": { "seed": 48161, "width": 1344, "height": 768, "prompt": "A film still of a robot, sci-fi, cool color grading, 70mm, bokeh, cinematic, anamorphic, beautiful", "refine": "expert_ensemble_refiner", "scheduler": "KarrasDPM", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": true, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "soft, blurry, ugly", "prompt_strength": 0.8, "tile_refine_steps": 20, "num_inference_steps": 50, "tile_refine_strength": 0.5, "tile_refine_conditioning_strength": 0.5 }, "logs": "Using seed: 48161\nPrompt: A film still of a robot, sci-fi, cool color grading, 70mm, bokeh, cinematic, anamorphic, beautiful\ntxt2img mode\n 0%| | 0/31 [00:00<?, ?it/s]\n 3%|▎ | 1/31 [00:00<00:05, 5.21it/s]\n 6%|▋ | 2/31 [00:00<00:04, 6.88it/s]\n 10%|▉ | 3/31 [00:00<00:04, 6.01it/s]\n 13%|█▎ | 4/31 [00:00<00:04, 5.68it/s]\n 16%|█▌ | 5/31 [00:00<00:04, 5.51it/s]\n 19%|█▉ | 6/31 [00:01<00:04, 5.40it/s]\n 23%|██▎ | 7/31 [00:01<00:04, 5.34it/s]\n 26%|██▌ | 8/31 [00:01<00:04, 5.30it/s]\n 29%|██▉ | 9/31 [00:01<00:04, 5.28it/s]\n 32%|███▏ | 10/31 [00:01<00:03, 5.26it/s]\n 35%|███▌ | 11/31 [00:02<00:03, 5.24it/s]\n 39%|███▊ | 12/31 [00:02<00:03, 5.23it/s]\n 42%|████▏ | 13/31 [00:02<00:03, 5.23it/s]\n 45%|████▌ | 14/31 [00:02<00:03, 5.22it/s]\n 48%|████▊ | 15/31 [00:02<00:03, 5.22it/s]\n 52%|█████▏ | 16/31 [00:02<00:02, 5.21it/s]\n 55%|█████▍ | 17/31 [00:03<00:02, 5.21it/s]\n 58%|█████▊ | 18/31 [00:03<00:02, 5.20it/s]\n 61%|██████▏ | 19/31 [00:03<00:02, 5.20it/s]\n 65%|██████▍ | 20/31 [00:03<00:02, 5.19it/s]\n 68%|██████▊ | 21/31 [00:03<00:01, 5.19it/s]\n 71%|███████ | 22/31 [00:04<00:01, 5.19it/s]\n 74%|███████▍ | 23/31 [00:04<00:01, 5.19it/s]\n 77%|███████▋ | 24/31 [00:04<00:01, 5.19it/s]\n 81%|████████ | 25/31 [00:04<00:01, 5.19it/s]\n 84%|████████▍ | 26/31 [00:04<00:00, 5.19it/s]\n 87%|████████▋ | 27/31 [00:05<00:00, 5.19it/s]\n 90%|█████████ | 28/31 [00:05<00:00, 5.18it/s]\n 94%|█████████▎| 29/31 [00:05<00:00, 5.18it/s]\n 97%|█████████▋| 30/31 [00:05<00:00, 5.18it/s]\n100%|██████████| 31/31 [00:05<00:00, 5.18it/s]\n100%|██████████| 31/31 [00:05<00:00, 5.27it/s]\n 0%| | 0/10 [00:00<?, ?it/s]\n 10%|█ | 1/10 [00:00<00:02, 4.45it/s]\n 20%|██ | 2/10 [00:00<00:01, 4.42it/s]\n 30%|███ | 3/10 [00:00<00:01, 4.42it/s]\n 40%|████ | 4/10 [00:00<00:01, 4.41it/s]\n 50%|█████ | 5/10 [00:01<00:01, 4.40it/s]\n 60%|██████ | 6/10 [00:01<00:00, 4.40it/s]\n 70%|███████ | 7/10 [00:01<00:00, 4.41it/s]\n 80%|████████ | 8/10 [00:01<00:00, 4.40it/s]\n 90%|█████████ | 9/10 [00:02<00:00, 4.40it/s]\n100%|██████████| 10/10 [00:02<00:00, 4.40it/s]\n100%|██████████| 10/10 [00:02<00:00, 4.40it/s]\n 0%| | 0/10 [00:00<?, ?it/s]\n 10%|█ | 1/10 [00:00<00:02, 3.18it/s]\n 20%|██ | 2/10 [00:00<00:01, 4.42it/s]\n 30%|███ | 3/10 [00:00<00:01, 3.74it/s]\n 40%|████ | 4/10 [00:01<00:01, 3.49it/s]\n 50%|█████ | 5/10 [00:01<00:01, 3.35it/s]\n 60%|██████ | 6/10 [00:01<00:01, 3.28it/s]\n 70%|███████ | 7/10 [00:02<00:00, 3.23it/s]\n 80%|████████ | 8/10 [00:02<00:00, 3.21it/s]\n 90%|█████████ | 9/10 [00:02<00:00, 3.19it/s]\n100%|██████████| 10/10 [00:03<00:00, 3.17it/s]\n100%|██████████| 10/10 [00:03<00:00, 3.31it/s]", "metrics": { "predict_time": 14.242164, "total_time": 14.280792 }, "output": [ "https://replicate.delivery/pbxt/REHNtkAyPC6tEpuobeAo4eGqB2B6t7dJFqcggKxM7eB9uMakA/out-0.png" ], "started_at": "2024-01-16T16:50:25.306994Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/aaz5bc3bjlr2hv2weeqbwqfu2a", "cancel": "https://api.replicate.com/v1/predictions/aaz5bc3bjlr2hv2weeqbwqfu2a/cancel" }, "version": "58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e" }Generated inUsing seed: 48161 Prompt: A film still of a robot, sci-fi, cool color grading, 70mm, bokeh, cinematic, anamorphic, beautiful txt2img mode 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:00<00:05, 5.21it/s] 6%|▋ | 2/31 [00:00<00:04, 6.88it/s] 10%|▉ | 3/31 [00:00<00:04, 6.01it/s] 13%|█▎ | 4/31 [00:00<00:04, 5.68it/s] 16%|█▌ | 5/31 [00:00<00:04, 5.51it/s] 19%|█▉ | 6/31 [00:01<00:04, 5.40it/s] 23%|██▎ | 7/31 [00:01<00:04, 5.34it/s] 26%|██▌ | 8/31 [00:01<00:04, 5.30it/s] 29%|██▉ | 9/31 [00:01<00:04, 5.28it/s] 32%|███▏ | 10/31 [00:01<00:03, 5.26it/s] 35%|███▌ | 11/31 [00:02<00:03, 5.24it/s] 39%|███▊ | 12/31 [00:02<00:03, 5.23it/s] 42%|████▏ | 13/31 [00:02<00:03, 5.23it/s] 45%|████▌ | 14/31 [00:02<00:03, 5.22it/s] 48%|████▊ | 15/31 [00:02<00:03, 5.22it/s] 52%|█████▏ | 16/31 [00:02<00:02, 5.21it/s] 55%|█████▍ | 17/31 [00:03<00:02, 5.21it/s] 58%|█████▊ | 18/31 [00:03<00:02, 5.20it/s] 61%|██████▏ | 19/31 [00:03<00:02, 5.20it/s] 65%|██████▍ | 20/31 [00:03<00:02, 5.19it/s] 68%|██████▊ | 21/31 [00:03<00:01, 5.19it/s] 71%|███████ | 22/31 [00:04<00:01, 5.19it/s] 74%|███████▍ | 23/31 [00:04<00:01, 5.19it/s] 77%|███████▋ | 24/31 [00:04<00:01, 5.19it/s] 81%|████████ | 25/31 [00:04<00:01, 5.19it/s] 84%|████████▍ | 26/31 [00:04<00:00, 5.19it/s] 87%|████████▋ | 27/31 [00:05<00:00, 5.19it/s] 90%|█████████ | 28/31 [00:05<00:00, 5.18it/s] 94%|█████████▎| 29/31 [00:05<00:00, 5.18it/s] 97%|█████████▋| 30/31 [00:05<00:00, 5.18it/s] 100%|██████████| 31/31 [00:05<00:00, 5.18it/s] 100%|██████████| 31/31 [00:05<00:00, 5.27it/s] 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:02, 4.45it/s] 20%|██ | 2/10 [00:00<00:01, 4.42it/s] 30%|███ | 3/10 [00:00<00:01, 4.42it/s] 40%|████ | 4/10 [00:00<00:01, 4.41it/s] 50%|█████ | 5/10 [00:01<00:01, 4.40it/s] 60%|██████ | 6/10 [00:01<00:00, 4.40it/s] 70%|███████ | 7/10 [00:01<00:00, 4.41it/s] 80%|████████ | 8/10 [00:01<00:00, 4.40it/s] 90%|█████████ | 9/10 [00:02<00:00, 4.40it/s] 100%|██████████| 10/10 [00:02<00:00, 4.40it/s] 100%|██████████| 10/10 [00:02<00:00, 4.40it/s] 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:02, 3.18it/s] 20%|██ | 2/10 [00:00<00:01, 4.42it/s] 30%|███ | 3/10 [00:00<00:01, 3.74it/s] 40%|████ | 4/10 [00:01<00:01, 3.49it/s] 50%|█████ | 5/10 [00:01<00:01, 3.35it/s] 60%|██████ | 6/10 [00:01<00:01, 3.28it/s] 70%|███████ | 7/10 [00:02<00:00, 3.23it/s] 80%|████████ | 8/10 [00:02<00:00, 3.21it/s] 90%|█████████ | 9/10 [00:02<00:00, 3.19it/s] 100%|██████████| 10/10 [00:03<00:00, 3.17it/s] 100%|██████████| 10/10 [00:03<00:00, 3.31it/s]Prediction
fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527eIDi4nzk3db4e6xx34ji7oj5xldb4StatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- seed
- 47500
- image
- width
- 1024
- height
- 1024
- prompt
- A rainbow coloured tiger
- refine
- expert_ensemble_refiner
- scheduler
- KarrasDPM
- lora_scale
- 0.6
- num_outputs
- 1
- tile_refine
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- prompt_strength
- 0.65
- tile_refine_steps
- 20
- num_inference_steps
- 50
- tile_refine_strength
- 0.3
- tile_refine_conditioning_strength
- 0.75
{ "seed": 47500, "image": "https://replicate.delivery/pbxt/KElnqcSH748uOPlKcwlG9lUfxwSVFOnVjMkWeSXYL6qIs2LS/out-0-1.png", "width": 1024, "height": 1024, "prompt": "A rainbow coloured tiger", "refine": "expert_ensemble_refiner", "scheduler": "KarrasDPM", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": true, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.65, "tile_refine_steps": 20, "num_inference_steps": 50, "tile_refine_strength": 0.3, "tile_refine_conditioning_strength": 0.75 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run fermatresearch/sdxl-improved-refiner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e", { input: { seed: 47500, image: "https://replicate.delivery/pbxt/KElnqcSH748uOPlKcwlG9lUfxwSVFOnVjMkWeSXYL6qIs2LS/out-0-1.png", width: 1024, height: 1024, prompt: "A rainbow coloured tiger", refine: "expert_ensemble_refiner", scheduler: "KarrasDPM", lora_scale: 0.6, num_outputs: 1, tile_refine: true, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "", prompt_strength: 0.65, tile_refine_steps: 20, num_inference_steps: 50, tile_refine_strength: 0.3, tile_refine_conditioning_strength: 0.75 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun fermatresearch/sdxl-improved-refiner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e", input={ "seed": 47500, "image": "https://replicate.delivery/pbxt/KElnqcSH748uOPlKcwlG9lUfxwSVFOnVjMkWeSXYL6qIs2LS/out-0-1.png", "width": 1024, "height": 1024, "prompt": "A rainbow coloured tiger", "refine": "expert_ensemble_refiner", "scheduler": "KarrasDPM", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": True, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.65, "tile_refine_steps": 20, "num_inference_steps": 50, "tile_refine_strength": 0.3, "tile_refine_conditioning_strength": 0.75 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run fermatresearch/sdxl-improved-refiner 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": "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e", "input": { "seed": 47500, "image": "https://replicate.delivery/pbxt/KElnqcSH748uOPlKcwlG9lUfxwSVFOnVjMkWeSXYL6qIs2LS/out-0-1.png", "width": 1024, "height": 1024, "prompt": "A rainbow coloured tiger", "refine": "expert_ensemble_refiner", "scheduler": "KarrasDPM", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": true, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.65, "tile_refine_steps": 20, "num_inference_steps": 50, "tile_refine_strength": 0.3, "tile_refine_conditioning_strength": 0.75 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-16T16:55:18.427543Z", "created_at": "2024-01-16T16:55:07.720800Z", "data_removed": false, "error": null, "id": "i4nzk3db4e6xx34ji7oj5xldb4", "input": { "seed": 47500, "image": "https://replicate.delivery/pbxt/KElnqcSH748uOPlKcwlG9lUfxwSVFOnVjMkWeSXYL6qIs2LS/out-0-1.png", "width": 1024, "height": 1024, "prompt": "A rainbow coloured tiger", "refine": "expert_ensemble_refiner", "scheduler": "KarrasDPM", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": true, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.65, "tile_refine_steps": 20, "num_inference_steps": 50, "tile_refine_strength": 0.3, "tile_refine_conditioning_strength": 0.75 }, "logs": "Using seed: 47500\nPrompt: A rainbow coloured tiger\nimg2img mode\n 0%| | 0/13 [00:00<?, ?it/s]\n 8%|▊ | 1/13 [00:00<00:02, 5.11it/s]\n 15%|█▌ | 2/13 [00:00<00:01, 6.76it/s]\n 23%|██▎ | 3/13 [00:00<00:01, 5.90it/s]\n 31%|███ | 4/13 [00:00<00:01, 5.58it/s]\n 38%|███▊ | 5/13 [00:00<00:01, 5.39it/s]\n 46%|████▌ | 6/13 [00:01<00:01, 5.29it/s]\n 54%|█████▍ | 7/13 [00:01<00:01, 5.24it/s]\n 62%|██████▏ | 8/13 [00:01<00:00, 5.20it/s]\n 69%|██████▉ | 9/13 [00:01<00:00, 5.17it/s]\n 77%|███████▋ | 10/13 [00:01<00:00, 5.14it/s]\n 85%|████████▍ | 11/13 [00:02<00:00, 5.13it/s]\n 92%|█████████▏| 12/13 [00:02<00:00, 5.12it/s]\n100%|██████████| 13/13 [00:02<00:00, 5.12it/s]\n100%|██████████| 13/13 [00:02<00:00, 5.28it/s]\n 0%| | 0/10 [00:00<?, ?it/s]\n 10%|█ | 1/10 [00:00<00:02, 4.33it/s]\n 20%|██ | 2/10 [00:00<00:01, 4.32it/s]\n 30%|███ | 3/10 [00:00<00:01, 4.31it/s]\n 40%|████ | 4/10 [00:00<00:01, 4.30it/s]\n 50%|█████ | 5/10 [00:01<00:01, 4.29it/s]\n 60%|██████ | 6/10 [00:01<00:00, 4.29it/s]\n 70%|███████ | 7/10 [00:01<00:00, 4.28it/s]\n 80%|████████ | 8/10 [00:01<00:00, 4.28it/s]\n 90%|█████████ | 9/10 [00:02<00:00, 4.28it/s]\n100%|██████████| 10/10 [00:02<00:00, 4.28it/s]\n100%|██████████| 10/10 [00:02<00:00, 4.29it/s]\n 0%| | 0/6 [00:00<?, ?it/s]\n 17%|█▋ | 1/6 [00:00<00:01, 3.03it/s]\n 33%|███▎ | 2/6 [00:00<00:00, 4.21it/s]\n 50%|█████ | 3/6 [00:00<00:00, 3.58it/s]\n 67%|██████▋ | 4/6 [00:01<00:00, 3.33it/s]\n 83%|████████▎ | 5/6 [00:01<00:00, 3.22it/s]\n100%|██████████| 6/6 [00:01<00:00, 3.15it/s]\n100%|██████████| 6/6 [00:01<00:00, 3.29it/s]", "metrics": { "predict_time": 10.671511, "total_time": 10.706743 }, "output": [ "https://replicate.delivery/pbxt/DRe0cFfXwoiSHUyqtChTj0u7jKH5m7VivdUCp0NJ9wfr3MakA/out-0.png" ], "started_at": "2024-01-16T16:55:07.756032Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/i4nzk3db4e6xx34ji7oj5xldb4", "cancel": "https://api.replicate.com/v1/predictions/i4nzk3db4e6xx34ji7oj5xldb4/cancel" }, "version": "58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e" }Generated inUsing seed: 47500 Prompt: A rainbow coloured tiger img2img mode 0%| | 0/13 [00:00<?, ?it/s] 8%|▊ | 1/13 [00:00<00:02, 5.11it/s] 15%|█▌ | 2/13 [00:00<00:01, 6.76it/s] 23%|██▎ | 3/13 [00:00<00:01, 5.90it/s] 31%|███ | 4/13 [00:00<00:01, 5.58it/s] 38%|███▊ | 5/13 [00:00<00:01, 5.39it/s] 46%|████▌ | 6/13 [00:01<00:01, 5.29it/s] 54%|█████▍ | 7/13 [00:01<00:01, 5.24it/s] 62%|██████▏ | 8/13 [00:01<00:00, 5.20it/s] 69%|██████▉ | 9/13 [00:01<00:00, 5.17it/s] 77%|███████▋ | 10/13 [00:01<00:00, 5.14it/s] 85%|████████▍ | 11/13 [00:02<00:00, 5.13it/s] 92%|█████████▏| 12/13 [00:02<00:00, 5.12it/s] 100%|██████████| 13/13 [00:02<00:00, 5.12it/s] 100%|██████████| 13/13 [00:02<00:00, 5.28it/s] 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:02, 4.33it/s] 20%|██ | 2/10 [00:00<00:01, 4.32it/s] 30%|███ | 3/10 [00:00<00:01, 4.31it/s] 40%|████ | 4/10 [00:00<00:01, 4.30it/s] 50%|█████ | 5/10 [00:01<00:01, 4.29it/s] 60%|██████ | 6/10 [00:01<00:00, 4.29it/s] 70%|███████ | 7/10 [00:01<00:00, 4.28it/s] 80%|████████ | 8/10 [00:01<00:00, 4.28it/s] 90%|█████████ | 9/10 [00:02<00:00, 4.28it/s] 100%|██████████| 10/10 [00:02<00:00, 4.28it/s] 100%|██████████| 10/10 [00:02<00:00, 4.29it/s] 0%| | 0/6 [00:00<?, ?it/s] 17%|█▋ | 1/6 [00:00<00:01, 3.03it/s] 33%|███▎ | 2/6 [00:00<00:00, 4.21it/s] 50%|█████ | 3/6 [00:00<00:00, 3.58it/s] 67%|██████▋ | 4/6 [00:01<00:00, 3.33it/s] 83%|████████▎ | 5/6 [00:01<00:00, 3.22it/s] 100%|██████████| 6/6 [00:01<00:00, 3.15it/s] 100%|██████████| 6/6 [00:01<00:00, 3.29it/s]Prediction
fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527eIDcf3o5hdbsov3pmzicqygj5blveStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- seed
- 58684
- width
- 1248
- height
- 832
- prompt
- A beautiful landscape photo
- refine
- expert_ensemble_refiner
- scheduler
- KarrasDPM
- lora_scale
- 0.6
- num_outputs
- 1
- tile_refine
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- soft, blurry, ugly
- prompt_strength
- 0.65
- tile_refine_steps
- 20
- num_inference_steps
- 50
- tile_refine_strength
- 0.5
- tile_refine_conditioning_strength
- 0.5
{ "seed": 58684, "width": 1248, "height": 832, "prompt": "A beautiful landscape photo", "refine": "expert_ensemble_refiner", "scheduler": "KarrasDPM", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": true, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "soft, blurry, ugly", "prompt_strength": 0.65, "tile_refine_steps": 20, "num_inference_steps": 50, "tile_refine_strength": 0.5, "tile_refine_conditioning_strength": 0.5 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run fermatresearch/sdxl-improved-refiner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e", { input: { seed: 58684, width: 1248, height: 832, prompt: "A beautiful landscape photo", refine: "expert_ensemble_refiner", scheduler: "KarrasDPM", lora_scale: 0.6, num_outputs: 1, tile_refine: true, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "soft, blurry, ugly", prompt_strength: 0.65, tile_refine_steps: 20, num_inference_steps: 50, tile_refine_strength: 0.5, tile_refine_conditioning_strength: 0.5 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun fermatresearch/sdxl-improved-refiner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e", input={ "seed": 58684, "width": 1248, "height": 832, "prompt": "A beautiful landscape photo", "refine": "expert_ensemble_refiner", "scheduler": "KarrasDPM", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": True, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "soft, blurry, ugly", "prompt_strength": 0.65, "tile_refine_steps": 20, "num_inference_steps": 50, "tile_refine_strength": 0.5, "tile_refine_conditioning_strength": 0.5 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run fermatresearch/sdxl-improved-refiner 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": "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e", "input": { "seed": 58684, "width": 1248, "height": 832, "prompt": "A beautiful landscape photo", "refine": "expert_ensemble_refiner", "scheduler": "KarrasDPM", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": true, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "soft, blurry, ugly", "prompt_strength": 0.65, "tile_refine_steps": 20, "num_inference_steps": 50, "tile_refine_strength": 0.5, "tile_refine_conditioning_strength": 0.5 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-16T16:56:40.129907Z", "created_at": "2024-01-16T16:56:20.479206Z", "data_removed": false, "error": null, "id": "cf3o5hdbsov3pmzicqygj5blve", "input": { "seed": 58684, "width": 1248, "height": 832, "prompt": "A beautiful landscape photo", "refine": "expert_ensemble_refiner", "scheduler": "KarrasDPM", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": true, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "soft, blurry, ugly", "prompt_strength": 0.65, "tile_refine_steps": 20, "num_inference_steps": 50, "tile_refine_strength": 0.5, "tile_refine_conditioning_strength": 0.5 }, "logs": "Using seed: 58684\nPrompt: A beautiful landscape photo\ntxt2img mode\n 0%| | 0/31 [00:00<?, ?it/s]\n 3%|▎ | 1/31 [00:00<00:06, 4.84it/s]\n 6%|▋ | 2/31 [00:00<00:04, 6.57it/s]\n 10%|▉ | 3/31 [00:00<00:04, 5.85it/s]\n 13%|█▎ | 4/31 [00:00<00:04, 5.56it/s]\n 16%|█▌ | 5/31 [00:00<00:04, 5.41it/s]\n 19%|█▉ | 6/31 [00:01<00:04, 5.30it/s]\n 23%|██▎ | 7/31 [00:01<00:04, 5.26it/s]\n 26%|██▌ | 8/31 [00:01<00:04, 5.23it/s]\n 29%|██▉ | 9/31 [00:01<00:04, 5.21it/s]\n 32%|███▏ | 10/31 [00:01<00:04, 5.19it/s]\n 35%|███▌ | 11/31 [00:02<00:03, 5.17it/s]\n 39%|███▊ | 12/31 [00:02<00:03, 5.16it/s]\n 42%|████▏ | 13/31 [00:02<00:03, 5.15it/s]\n 45%|████▌ | 14/31 [00:02<00:03, 5.16it/s]\n 48%|████▊ | 15/31 [00:02<00:03, 5.15it/s]\n 52%|█████▏ | 16/31 [00:03<00:02, 5.14it/s]\n 55%|█████▍ | 17/31 [00:03<00:02, 5.14it/s]\n 58%|█████▊ | 18/31 [00:03<00:02, 5.13it/s]\n 61%|██████▏ | 19/31 [00:03<00:02, 5.14it/s]\n 65%|██████▍ | 20/31 [00:03<00:02, 5.14it/s]\n 68%|██████▊ | 21/31 [00:04<00:01, 5.13it/s]\n 71%|███████ | 22/31 [00:04<00:01, 5.12it/s]\n 74%|███████▍ | 23/31 [00:04<00:01, 5.13it/s]\n 77%|███████▋ | 24/31 [00:04<00:01, 5.13it/s]\n 81%|████████ | 25/31 [00:04<00:01, 5.13it/s]\n 84%|████████▍ | 26/31 [00:04<00:00, 5.13it/s]\n 87%|████████▋ | 27/31 [00:05<00:00, 5.13it/s]\n 90%|█████████ | 28/31 [00:05<00:00, 5.12it/s]\n 94%|█████████▎| 29/31 [00:05<00:00, 5.12it/s]\n 97%|█████████▋| 30/31 [00:05<00:00, 5.13it/s]\n100%|██████████| 31/31 [00:05<00:00, 5.12it/s]\n100%|██████████| 31/31 [00:05<00:00, 5.20it/s]\n 0%| | 0/10 [00:00<?, ?it/s]\n 10%|█ | 1/10 [00:00<00:02, 4.11it/s]\n 20%|██ | 2/10 [00:00<00:01, 4.18it/s]\n 30%|███ | 3/10 [00:00<00:01, 4.20it/s]\n 40%|████ | 4/10 [00:00<00:01, 4.20it/s]\n 50%|█████ | 5/10 [00:01<00:01, 4.20it/s]\n 60%|██████ | 6/10 [00:01<00:00, 4.21it/s]\n 70%|███████ | 7/10 [00:01<00:00, 4.21it/s]\n 80%|████████ | 8/10 [00:01<00:00, 4.21it/s]\n 90%|█████████ | 9/10 [00:02<00:00, 4.21it/s]\n100%|██████████| 10/10 [00:02<00:00, 4.21it/s]\n100%|██████████| 10/10 [00:02<00:00, 4.20it/s]\n 0%| | 0/10 [00:00<?, ?it/s]\n 10%|█ | 1/10 [00:00<00:03, 2.93it/s]\n 20%|██ | 2/10 [00:00<00:01, 4.16it/s]\n 30%|███ | 3/10 [00:00<00:01, 3.55it/s]\n 40%|████ | 4/10 [00:01<00:01, 3.32it/s]\n 50%|█████ | 5/10 [00:01<00:01, 3.20it/s]\n 60%|██████ | 6/10 [00:01<00:01, 3.15it/s]\n 70%|███████ | 7/10 [00:02<00:00, 3.10it/s]\n 80%|████████ | 8/10 [00:02<00:00, 3.08it/s]\n 90%|█████████ | 9/10 [00:02<00:00, 3.07it/s]\n100%|██████████| 10/10 [00:03<00:00, 3.04it/s]\n100%|██████████| 10/10 [00:03<00:00, 3.17it/s]", "metrics": { "predict_time": 19.61591, "total_time": 19.650701 }, "output": [ "https://replicate.delivery/pbxt/1G9p3DFLhRZHMxqI4hqeemL92dD0bAQcadeexeBimB0SozoRC/out-0.png" ], "started_at": "2024-01-16T16:56:20.513997Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/cf3o5hdbsov3pmzicqygj5blve", "cancel": "https://api.replicate.com/v1/predictions/cf3o5hdbsov3pmzicqygj5blve/cancel" }, "version": "58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e" }Generated inUsing seed: 58684 Prompt: A beautiful landscape photo txt2img mode 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:00<00:06, 4.84it/s] 6%|▋ | 2/31 [00:00<00:04, 6.57it/s] 10%|▉ | 3/31 [00:00<00:04, 5.85it/s] 13%|█▎ | 4/31 [00:00<00:04, 5.56it/s] 16%|█▌ | 5/31 [00:00<00:04, 5.41it/s] 19%|█▉ | 6/31 [00:01<00:04, 5.30it/s] 23%|██▎ | 7/31 [00:01<00:04, 5.26it/s] 26%|██▌ | 8/31 [00:01<00:04, 5.23it/s] 29%|██▉ | 9/31 [00:01<00:04, 5.21it/s] 32%|███▏ | 10/31 [00:01<00:04, 5.19it/s] 35%|███▌ | 11/31 [00:02<00:03, 5.17it/s] 39%|███▊ | 12/31 [00:02<00:03, 5.16it/s] 42%|████▏ | 13/31 [00:02<00:03, 5.15it/s] 45%|████▌ | 14/31 [00:02<00:03, 5.16it/s] 48%|████▊ | 15/31 [00:02<00:03, 5.15it/s] 52%|█████▏ | 16/31 [00:03<00:02, 5.14it/s] 55%|█████▍ | 17/31 [00:03<00:02, 5.14it/s] 58%|█████▊ | 18/31 [00:03<00:02, 5.13it/s] 61%|██████▏ | 19/31 [00:03<00:02, 5.14it/s] 65%|██████▍ | 20/31 [00:03<00:02, 5.14it/s] 68%|██████▊ | 21/31 [00:04<00:01, 5.13it/s] 71%|███████ | 22/31 [00:04<00:01, 5.12it/s] 74%|███████▍ | 23/31 [00:04<00:01, 5.13it/s] 77%|███████▋ | 24/31 [00:04<00:01, 5.13it/s] 81%|████████ | 25/31 [00:04<00:01, 5.13it/s] 84%|████████▍ | 26/31 [00:04<00:00, 5.13it/s] 87%|████████▋ | 27/31 [00:05<00:00, 5.13it/s] 90%|█████████ | 28/31 [00:05<00:00, 5.12it/s] 94%|█████████▎| 29/31 [00:05<00:00, 5.12it/s] 97%|█████████▋| 30/31 [00:05<00:00, 5.13it/s] 100%|██████████| 31/31 [00:05<00:00, 5.12it/s] 100%|██████████| 31/31 [00:05<00:00, 5.20it/s] 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:02, 4.11it/s] 20%|██ | 2/10 [00:00<00:01, 4.18it/s] 30%|███ | 3/10 [00:00<00:01, 4.20it/s] 40%|████ | 4/10 [00:00<00:01, 4.20it/s] 50%|█████ | 5/10 [00:01<00:01, 4.20it/s] 60%|██████ | 6/10 [00:01<00:00, 4.21it/s] 70%|███████ | 7/10 [00:01<00:00, 4.21it/s] 80%|████████ | 8/10 [00:01<00:00, 4.21it/s] 90%|█████████ | 9/10 [00:02<00:00, 4.21it/s] 100%|██████████| 10/10 [00:02<00:00, 4.21it/s] 100%|██████████| 10/10 [00:02<00:00, 4.20it/s] 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:03, 2.93it/s] 20%|██ | 2/10 [00:00<00:01, 4.16it/s] 30%|███ | 3/10 [00:00<00:01, 3.55it/s] 40%|████ | 4/10 [00:01<00:01, 3.32it/s] 50%|█████ | 5/10 [00:01<00:01, 3.20it/s] 60%|██████ | 6/10 [00:01<00:01, 3.15it/s] 70%|███████ | 7/10 [00:02<00:00, 3.10it/s] 80%|████████ | 8/10 [00:02<00:00, 3.08it/s] 90%|█████████ | 9/10 [00:02<00:00, 3.07it/s] 100%|██████████| 10/10 [00:03<00:00, 3.04it/s] 100%|██████████| 10/10 [00:03<00:00, 3.17it/s]Prediction
fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527eIDntmpr4tbfifulz2nuhwxfyfuyiStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1344
- height
- 768
- prompt
- a handsome Japanese old man staring at a cyberpunk city, neon lights, professional landscape shot by national geographic
- refine
- expert_ensemble_refiner
- scheduler
- KarrasDPM
- lora_scale
- 0.6
- num_outputs
- 1
- tile_refine
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- prompt_strength
- 0.8
- tile_refine_steps
- 20
- num_inference_steps
- 50
- tile_refine_strength
- 0.5
- tile_refine_conditioning_strength
- 0.5
{ "width": 1344, "height": 768, "prompt": "a handsome Japanese old man staring at a cyberpunk city, neon lights, professional landscape shot by national geographic", "refine": "expert_ensemble_refiner", "scheduler": "KarrasDPM", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": true, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "tile_refine_steps": 20, "num_inference_steps": 50, "tile_refine_strength": 0.5, "tile_refine_conditioning_strength": 0.5 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run fermatresearch/sdxl-improved-refiner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e", { input: { width: 1344, height: 768, prompt: "a handsome Japanese old man staring at a cyberpunk city, neon lights, professional landscape shot by national geographic", refine: "expert_ensemble_refiner", scheduler: "KarrasDPM", lora_scale: 0.6, num_outputs: 1, tile_refine: true, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "", prompt_strength: 0.8, tile_refine_steps: 20, num_inference_steps: 50, tile_refine_strength: 0.5, tile_refine_conditioning_strength: 0.5 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun fermatresearch/sdxl-improved-refiner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e", input={ "width": 1344, "height": 768, "prompt": "a handsome Japanese old man staring at a cyberpunk city, neon lights, professional landscape shot by national geographic", "refine": "expert_ensemble_refiner", "scheduler": "KarrasDPM", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": True, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "tile_refine_steps": 20, "num_inference_steps": 50, "tile_refine_strength": 0.5, "tile_refine_conditioning_strength": 0.5 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run fermatresearch/sdxl-improved-refiner 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": "fermatresearch/sdxl-improved-refiner:58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e", "input": { "width": 1344, "height": 768, "prompt": "a handsome Japanese old man staring at a cyberpunk city, neon lights, professional landscape shot by national geographic", "refine": "expert_ensemble_refiner", "scheduler": "KarrasDPM", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": true, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "tile_refine_steps": 20, "num_inference_steps": 50, "tile_refine_strength": 0.5, "tile_refine_conditioning_strength": 0.5 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-16T16:59:01.743201Z", "created_at": "2024-01-16T16:58:47.080086Z", "data_removed": false, "error": null, "id": "ntmpr4tbfifulz2nuhwxfyfuyi", "input": { "width": 1344, "height": 768, "prompt": "a handsome Japanese old man staring at a cyberpunk city, neon lights, professional landscape shot by national geographic", "refine": "expert_ensemble_refiner", "scheduler": "KarrasDPM", "lora_scale": 0.6, "num_outputs": 1, "tile_refine": true, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "tile_refine_steps": 20, "num_inference_steps": 50, "tile_refine_strength": 0.5, "tile_refine_conditioning_strength": 0.5 }, "logs": "Using seed: 44539\nPrompt: a handsome Japanese old man staring at a cyberpunk city, neon lights, professional landscape shot by national geographic\ntxt2img mode\n 0%| | 0/31 [00:00<?, ?it/s]\n 3%|▎ | 1/31 [00:00<00:06, 5.00it/s]\n 6%|▋ | 2/31 [00:00<00:04, 6.72it/s]\n 10%|▉ | 3/31 [00:00<00:04, 5.92it/s]\n 13%|█▎ | 4/31 [00:00<00:04, 5.61it/s]\n 16%|█▌ | 5/31 [00:00<00:04, 5.44it/s]\n 19%|█▉ | 6/31 [00:01<00:04, 5.32it/s]\n 23%|██▎ | 7/31 [00:01<00:04, 5.28it/s]\n 26%|██▌ | 8/31 [00:01<00:04, 5.26it/s]\n 29%|██▉ | 9/31 [00:01<00:04, 5.24it/s]\n 32%|███▏ | 10/31 [00:01<00:04, 5.23it/s]\n 35%|███▌ | 11/31 [00:02<00:03, 5.22it/s]\n 39%|███▊ | 12/31 [00:02<00:03, 5.21it/s]\n 42%|████▏ | 13/31 [00:02<00:03, 5.20it/s]\n 45%|████▌ | 14/31 [00:02<00:03, 5.20it/s]\n 48%|████▊ | 15/31 [00:02<00:03, 5.19it/s]\n 52%|█████▏ | 16/31 [00:03<00:02, 5.19it/s]\n 55%|█████▍ | 17/31 [00:03<00:02, 5.19it/s]\n 58%|█████▊ | 18/31 [00:03<00:02, 5.18it/s]\n 61%|██████▏ | 19/31 [00:03<00:02, 5.19it/s]\n 65%|██████▍ | 20/31 [00:03<00:02, 5.19it/s]\n 68%|██████▊ | 21/31 [00:03<00:01, 5.18it/s]\n 71%|███████ | 22/31 [00:04<00:01, 5.18it/s]\n 74%|███████▍ | 23/31 [00:04<00:01, 5.18it/s]\n 77%|███████▋ | 24/31 [00:04<00:01, 5.18it/s]\n 81%|████████ | 25/31 [00:04<00:01, 5.17it/s]\n 84%|████████▍ | 26/31 [00:04<00:00, 5.18it/s]\n 87%|████████▋ | 27/31 [00:05<00:00, 5.18it/s]\n 90%|█████████ | 28/31 [00:05<00:00, 5.18it/s]\n 94%|█████████▎| 29/31 [00:05<00:00, 5.18it/s]\n 97%|█████████▋| 30/31 [00:05<00:00, 5.18it/s]\n100%|██████████| 31/31 [00:05<00:00, 5.18it/s]\n100%|██████████| 31/31 [00:05<00:00, 5.25it/s]\n 0%| | 0/10 [00:00<?, ?it/s]\n 10%|█ | 1/10 [00:00<00:02, 4.29it/s]\n 20%|██ | 2/10 [00:00<00:01, 4.35it/s]\n 30%|███ | 3/10 [00:00<00:01, 4.38it/s]\n 40%|████ | 4/10 [00:00<00:01, 4.38it/s]\n 50%|█████ | 5/10 [00:01<00:01, 4.38it/s]\n 60%|██████ | 6/10 [00:01<00:00, 4.39it/s]\n 70%|███████ | 7/10 [00:01<00:00, 4.39it/s]\n 80%|████████ | 8/10 [00:01<00:00, 4.39it/s]\n 90%|█████████ | 9/10 [00:02<00:00, 4.39it/s]\n100%|██████████| 10/10 [00:02<00:00, 4.39it/s]\n100%|██████████| 10/10 [00:02<00:00, 4.38it/s]\n 0%| | 0/10 [00:00<?, ?it/s]\n 10%|█ | 1/10 [00:00<00:02, 3.03it/s]\n 20%|██ | 2/10 [00:00<00:01, 4.28it/s]\n 30%|███ | 3/10 [00:00<00:01, 3.69it/s]\n 40%|████ | 4/10 [00:01<00:01, 3.44it/s]\n 50%|█████ | 5/10 [00:01<00:01, 3.34it/s]\n 60%|██████ | 6/10 [00:01<00:01, 3.27it/s]\n 70%|███████ | 7/10 [00:02<00:00, 3.22it/s]\n 80%|████████ | 8/10 [00:02<00:00, 3.20it/s]\n 90%|█████████ | 9/10 [00:02<00:00, 3.20it/s]\n100%|██████████| 10/10 [00:03<00:00, 3.17it/s]\n100%|██████████| 10/10 [00:03<00:00, 3.29it/s]", "metrics": { "predict_time": 14.625395, "total_time": 14.663115 }, "output": [ "https://replicate.delivery/pbxt/4xnb2XqDmgJVGd7QuD298fN6eVnp7s8YbFfbIHf5TzhR9Z0IB/out-0.png" ], "started_at": "2024-01-16T16:58:47.117806Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/ntmpr4tbfifulz2nuhwxfyfuyi", "cancel": "https://api.replicate.com/v1/predictions/ntmpr4tbfifulz2nuhwxfyfuyi/cancel" }, "version": "58534db966a6866fa7e699482ebf8b508a8c39e197bb8ed7ce2d9b1e1cc6527e" }Generated inUsing seed: 44539 Prompt: a handsome Japanese old man staring at a cyberpunk city, neon lights, professional landscape shot by national geographic txt2img mode 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:00<00:06, 5.00it/s] 6%|▋ | 2/31 [00:00<00:04, 6.72it/s] 10%|▉ | 3/31 [00:00<00:04, 5.92it/s] 13%|█▎ | 4/31 [00:00<00:04, 5.61it/s] 16%|█▌ | 5/31 [00:00<00:04, 5.44it/s] 19%|█▉ | 6/31 [00:01<00:04, 5.32it/s] 23%|██▎ | 7/31 [00:01<00:04, 5.28it/s] 26%|██▌ | 8/31 [00:01<00:04, 5.26it/s] 29%|██▉ | 9/31 [00:01<00:04, 5.24it/s] 32%|███▏ | 10/31 [00:01<00:04, 5.23it/s] 35%|███▌ | 11/31 [00:02<00:03, 5.22it/s] 39%|███▊ | 12/31 [00:02<00:03, 5.21it/s] 42%|████▏ | 13/31 [00:02<00:03, 5.20it/s] 45%|████▌ | 14/31 [00:02<00:03, 5.20it/s] 48%|████▊ | 15/31 [00:02<00:03, 5.19it/s] 52%|█████▏ | 16/31 [00:03<00:02, 5.19it/s] 55%|█████▍ | 17/31 [00:03<00:02, 5.19it/s] 58%|█████▊ | 18/31 [00:03<00:02, 5.18it/s] 61%|██████▏ | 19/31 [00:03<00:02, 5.19it/s] 65%|██████▍ | 20/31 [00:03<00:02, 5.19it/s] 68%|██████▊ | 21/31 [00:03<00:01, 5.18it/s] 71%|███████ | 22/31 [00:04<00:01, 5.18it/s] 74%|███████▍ | 23/31 [00:04<00:01, 5.18it/s] 77%|███████▋ | 24/31 [00:04<00:01, 5.18it/s] 81%|████████ | 25/31 [00:04<00:01, 5.17it/s] 84%|████████▍ | 26/31 [00:04<00:00, 5.18it/s] 87%|████████▋ | 27/31 [00:05<00:00, 5.18it/s] 90%|█████████ | 28/31 [00:05<00:00, 5.18it/s] 94%|█████████▎| 29/31 [00:05<00:00, 5.18it/s] 97%|█████████▋| 30/31 [00:05<00:00, 5.18it/s] 100%|██████████| 31/31 [00:05<00:00, 5.18it/s] 100%|██████████| 31/31 [00:05<00:00, 5.25it/s] 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:02, 4.29it/s] 20%|██ | 2/10 [00:00<00:01, 4.35it/s] 30%|███ | 3/10 [00:00<00:01, 4.38it/s] 40%|████ | 4/10 [00:00<00:01, 4.38it/s] 50%|█████ | 5/10 [00:01<00:01, 4.38it/s] 60%|██████ | 6/10 [00:01<00:00, 4.39it/s] 70%|███████ | 7/10 [00:01<00:00, 4.39it/s] 80%|████████ | 8/10 [00:01<00:00, 4.39it/s] 90%|█████████ | 9/10 [00:02<00:00, 4.39it/s] 100%|██████████| 10/10 [00:02<00:00, 4.39it/s] 100%|██████████| 10/10 [00:02<00:00, 4.38it/s] 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:02, 3.03it/s] 20%|██ | 2/10 [00:00<00:01, 4.28it/s] 30%|███ | 3/10 [00:00<00:01, 3.69it/s] 40%|████ | 4/10 [00:01<00:01, 3.44it/s] 50%|█████ | 5/10 [00:01<00:01, 3.34it/s] 60%|██████ | 6/10 [00:01<00:01, 3.27it/s] 70%|███████ | 7/10 [00:02<00:00, 3.22it/s] 80%|████████ | 8/10 [00:02<00:00, 3.20it/s] 90%|█████████ | 9/10 [00:02<00:00, 3.20it/s] 100%|██████████| 10/10 [00:03<00:00, 3.17it/s] 100%|██████████| 10/10 [00:03<00:00, 3.29it/s]
Want to make some of these yourself?
Run this model
