omniedgeio / aquaaibase
Model
- Public
- 412 runs
-
A100 (80GB)
Prediction
omniedgeio/aquaaibase:59583f621010a8034d8eac35efbd4aeb4040477398c4a75cb8de5f5772b2aac4IDmhsoi4lbyzfbkqzd5duwz74zxqStatusSucceededSourceAPIHardwareA100 (80GB)Total durationCreatedInput
- width
- 640
- height
- 840
- prompt
- The woman in the photo is wearing a blue dress and standing in a white room. She looks elegant and sophisticated, with her posture and outfit drawing attention. The white room serves as a simple and clean background for her attire.The lighting is bright and natural, realist detail, ue5, detailed character expressions, amazing quality, wallpaper, analog film grain. one person, 8k. In the style of EveningDressDF
- refine
- base_image_refiner
- scheduler
- K_EULER_ANCESTRAL
- apply_watermark
- negative_prompt
- cropped face, cover face, cover visage, mutated hands, bad anatomy, bad hands, three hands, three legs, bad arms,(missing legs), missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate, not human, no head,(low quality, worst quality:1.4), cgi, text, signature, watermark, extra limbs, cleavage
- disable_safety_checker
{ "width": 640, "height": 840, "prompt": "The woman in the photo is wearing a blue dress and standing in a white room. She looks elegant and sophisticated, with her posture and outfit drawing attention. The white room serves as a simple and clean background for her attire.The lighting is bright and natural, realist detail, ue5, detailed character expressions, amazing quality, wallpaper, analog film grain. one person, 8k. In the style of EveningDressDF", "refine": "base_image_refiner", "scheduler": "K_EULER_ANCESTRAL", "apply_watermark": false, "negative_prompt": "cropped face, cover face, cover visage, mutated hands, bad anatomy, bad hands, three hands, three legs, bad arms,(missing legs), missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate, not human, no head,(low quality, worst quality:1.4), cgi, text, signature, watermark, extra limbs, cleavage", "disable_safety_checker": true }
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 omniedgeio/aquaaibase using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "omniedgeio/aquaaibase:59583f621010a8034d8eac35efbd4aeb4040477398c4a75cb8de5f5772b2aac4", { input: { width: 640, height: 840, prompt: "The woman in the photo is wearing a blue dress and standing in a white room. She looks elegant and sophisticated, with her posture and outfit drawing attention. The white room serves as a simple and clean background for her attire.The lighting is bright and natural, realist detail, ue5, detailed character expressions, amazing quality, wallpaper, analog film grain. one person, 8k. In the style of EveningDressDF", refine: "base_image_refiner", scheduler: "K_EULER_ANCESTRAL", apply_watermark: false, negative_prompt: "cropped face, cover face, cover visage, mutated hands, bad anatomy, bad hands, three hands, three legs, bad arms,(missing legs), missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate, not human, no head,(low quality, worst quality:1.4), cgi, text, signature, watermark, extra limbs, cleavage" } } ); // 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 omniedgeio/aquaaibase using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "omniedgeio/aquaaibase:59583f621010a8034d8eac35efbd4aeb4040477398c4a75cb8de5f5772b2aac4", input={ "width": 640, "height": 840, "prompt": "The woman in the photo is wearing a blue dress and standing in a white room. She looks elegant and sophisticated, with her posture and outfit drawing attention. The white room serves as a simple and clean background for her attire.The lighting is bright and natural, realist detail, ue5, detailed character expressions, amazing quality, wallpaper, analog film grain. one person, 8k. In the style of EveningDressDF", "refine": "base_image_refiner", "scheduler": "K_EULER_ANCESTRAL", "apply_watermark": False, "negative_prompt": "cropped face, cover face, cover visage, mutated hands, bad anatomy, bad hands, three hands, three legs, bad arms,(missing legs), missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate, not human, no head,(low quality, worst quality:1.4), cgi, text, signature, watermark, extra limbs, cleavage" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run omniedgeio/aquaaibase 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": "omniedgeio/aquaaibase:59583f621010a8034d8eac35efbd4aeb4040477398c4a75cb8de5f5772b2aac4", "input": { "width": 640, "height": 840, "prompt": "The woman in the photo is wearing a blue dress and standing in a white room. She looks elegant and sophisticated, with her posture and outfit drawing attention. The white room serves as a simple and clean background for her attire.The lighting is bright and natural, realist detail, ue5, detailed character expressions, amazing quality, wallpaper, analog film grain. one person, 8k. In the style of EveningDressDF", "refine": "base_image_refiner", "scheduler": "K_EULER_ANCESTRAL", "apply_watermark": false, "negative_prompt": "cropped face, cover face, cover visage, mutated hands, bad anatomy, bad hands, three hands, three legs, bad arms,(missing legs), missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate, not human, no head,(low quality, worst quality:1.4), cgi, text, signature, watermark, extra limbs, cleavage" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-03-17T09:00:51.430850Z", "created_at": "2024-03-17T08:59:16.432454Z", "data_removed": false, "error": null, "id": "mhsoi4lbyzfbkqzd5duwz74zxq", "input": { "width": 640, "height": 840, "prompt": "The woman in the photo is wearing a blue dress and standing in a white room. She looks elegant and sophisticated, with her posture and outfit drawing attention. The white room serves as a simple and clean background for her attire.The lighting is bright and natural, realist detail, ue5, detailed character expressions, amazing quality, wallpaper, analog film grain. one person, 8k. In the style of EveningDressDF", "refine": "base_image_refiner", "scheduler": "K_EULER_ANCESTRAL", "apply_watermark": false, "negative_prompt": "cropped face, cover face, cover visage, mutated hands, bad anatomy, bad hands, three hands, three legs, bad arms,(missing legs), missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate, not human, no head,(low quality, worst quality:1.4), cgi, text, signature, watermark, extra limbs, cleavage", "disable_safety_checker": true }, "logs": "Using seed: 65503\nEnsuring enough disk space...\nFree disk space: 818957369344\nDownloading weights: https://replicate.delivery/pbxt/UP69cUtnOWL6LB8aoHYp5M5AJyfLFoW1gfREoHNzrglQ6BhSA/trained_model.tar\n2024-03-17T09:00:36Z | INFO | [ Initiating ] dest=/src/weights-cache/62014fdd81e3f2bc minimum_chunk_size=150M url=https://replicate.delivery/pbxt/UP69cUtnOWL6LB8aoHYp5M5AJyfLFoW1gfREoHNzrglQ6BhSA/trained_model.tar\n2024-03-17T09:00:41Z | INFO | [ Complete ] dest=/src/weights-cache/62014fdd81e3f2bc size=\"186 MB\" total_elapsed=4.852s url=https://replicate.delivery/pbxt/UP69cUtnOWL6LB8aoHYp5M5AJyfLFoW1gfREoHNzrglQ6BhSA/trained_model.tar\nb''\nDownloaded weights in 4.9480156898498535 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: The woman in the photo is wearing a blue dress and standing in a white room. She looks elegant and sophisticated, with her posture and outfit drawing attention. The white room serves as a simple and clean background for her attire.The lighting is bright and natural, realist detail, ue5, detailed character expressions, amazing quality, wallpaper, analog film grain. one person, 8k. In the style of EveningDressDF\ntxt2img mode\nToken indices sequence length is longer than the specified maximum sequence length for this model (86 > 77). Running this sequence through the model will result in indexing errors\nThe following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['k. in the style of eveningdressdf']\nToken indices sequence length is longer than the specified maximum sequence length for this model (86 > 77). Running this sequence through the model will result in indexing errors\nThe following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['k. in the style of eveningdressdf']\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:38, 1.26it/s]\n 4%|▍ | 2/50 [00:00<00:18, 2.56it/s]\n 6%|▌ | 3/50 [00:01<00:12, 3.83it/s]\n 8%|▊ | 4/50 [00:01<00:09, 5.00it/s]\n 10%|█ | 5/50 [00:01<00:07, 6.02it/s]\n 12%|█▏ | 6/50 [00:01<00:06, 6.82it/s]\n 14%|█▍ | 7/50 [00:01<00:05, 7.48it/s]\n 16%|█▌ | 8/50 [00:01<00:05, 7.99it/s]\n 18%|█▊ | 9/50 [00:01<00:04, 8.36it/s]\n 20%|██ | 10/50 [00:01<00:04, 8.65it/s]\n 22%|██▏ | 11/50 [00:01<00:04, 8.87it/s]\n 24%|██▍ | 12/50 [00:01<00:04, 9.03it/s]\n 26%|██▌ | 13/50 [00:02<00:04, 9.15it/s]\n 28%|██▊ | 14/50 [00:02<00:03, 9.11it/s]\n 30%|███ | 15/50 [00:02<00:03, 9.16it/s]\n 32%|███▏ | 16/50 [00:02<00:03, 9.19it/s]\n 34%|███▍ | 17/50 [00:02<00:03, 9.22it/s]\n 36%|███▌ | 18/50 [00:02<00:03, 9.26it/s]\n 38%|███▊ | 19/50 [00:02<00:03, 9.28it/s]\n 40%|████ | 20/50 [00:02<00:03, 9.30it/s]\n 42%|████▏ | 21/50 [00:02<00:03, 9.33it/s]\n 44%|████▍ | 22/50 [00:03<00:03, 9.27it/s]\n 46%|████▌ | 23/50 [00:03<00:02, 9.29it/s]\n 48%|████▊ | 24/50 [00:03<00:02, 9.32it/s]\n 50%|█████ | 25/50 [00:03<00:02, 9.31it/s]\n 52%|█████▏ | 26/50 [00:03<00:02, 9.32it/s]\n 54%|█████▍ | 27/50 [00:03<00:02, 9.33it/s]\n 56%|█████▌ | 28/50 [00:03<00:02, 9.31it/s]\n 58%|█████▊ | 29/50 [00:03<00:02, 9.30it/s]\n 60%|██████ | 30/50 [00:03<00:02, 9.25it/s]\n 62%|██████▏ | 31/50 [00:04<00:02, 9.26it/s]\n 64%|██████▍ | 32/50 [00:04<00:01, 9.28it/s]\n 66%|██████▌ | 33/50 [00:04<00:01, 9.28it/s]\n 68%|██████▊ | 34/50 [00:04<00:01, 9.28it/s]\n 70%|███████ | 35/50 [00:04<00:01, 9.29it/s]\n 72%|███████▏ | 36/50 [00:04<00:01, 9.29it/s]\n 74%|███████▍ | 37/50 [00:04<00:01, 9.24it/s]\n 76%|███████▌ | 38/50 [00:04<00:01, 9.23it/s]\n 78%|███████▊ | 39/50 [00:04<00:01, 9.24it/s]\n 80%|████████ | 40/50 [00:04<00:01, 9.26it/s]\n 82%|████████▏ | 41/50 [00:05<00:00, 9.27it/s]\n 84%|████████▍ | 42/50 [00:05<00:00, 9.26it/s]\n 86%|████████▌ | 43/50 [00:05<00:00, 9.26it/s]\n 88%|████████▊ | 44/50 [00:05<00:00, 9.27it/s]\n 90%|█████████ | 45/50 [00:05<00:00, 9.28it/s]\n 92%|█████████▏| 46/50 [00:05<00:00, 9.29it/s]\n 94%|█████████▍| 47/50 [00:05<00:00, 9.29it/s]\n 96%|█████████▌| 48/50 [00:05<00:00, 9.25it/s]\n 98%|█████████▊| 49/50 [00:05<00:00, 9.25it/s]\n100%|██████████| 50/50 [00:06<00:00, 9.25it/s]\n100%|██████████| 50/50 [00:06<00:00, 8.24it/s]\nToken indices sequence length is longer than the specified maximum sequence length for this model (86 > 77). Running this sequence through the model will result in indexing errors\nThe following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['k. in the style of eveningdressdf']\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:00<00:01, 9.75it/s]\n 20%|██ | 3/15 [00:00<00:00, 13.17it/s]\n 33%|███▎ | 5/15 [00:00<00:00, 14.04it/s]\n 47%|████▋ | 7/15 [00:00<00:00, 14.38it/s]\n 60%|██████ | 9/15 [00:00<00:00, 14.59it/s]\n 73%|███████▎ | 11/15 [00:00<00:00, 14.72it/s]\n 87%|████████▋ | 13/15 [00:00<00:00, 14.81it/s]\n100%|██████████| 15/15 [00:01<00:00, 14.85it/s]\n100%|██████████| 15/15 [00:01<00:00, 14.44it/s]", "metrics": { "predict_time": 15.137104, "total_time": 94.998396 }, "output": [ "https://replicate.delivery/pbxt/a4kBibUqVjaoL1TwYLR4res2epkWzmKBG4SwM9wQLehEaMClA/out-0.png" ], "started_at": "2024-03-17T09:00:36.293746Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/mhsoi4lbyzfbkqzd5duwz74zxq", "cancel": "https://api.replicate.com/v1/predictions/mhsoi4lbyzfbkqzd5duwz74zxq/cancel" }, "version": "59583f621010a8034d8eac35efbd4aeb4040477398c4a75cb8de5f5772b2aac4" }
Generated inUsing seed: 65503 Ensuring enough disk space... Free disk space: 818957369344 Downloading weights: https://replicate.delivery/pbxt/UP69cUtnOWL6LB8aoHYp5M5AJyfLFoW1gfREoHNzrglQ6BhSA/trained_model.tar 2024-03-17T09:00:36Z | INFO | [ Initiating ] dest=/src/weights-cache/62014fdd81e3f2bc minimum_chunk_size=150M url=https://replicate.delivery/pbxt/UP69cUtnOWL6LB8aoHYp5M5AJyfLFoW1gfREoHNzrglQ6BhSA/trained_model.tar 2024-03-17T09:00:41Z | INFO | [ Complete ] dest=/src/weights-cache/62014fdd81e3f2bc size="186 MB" total_elapsed=4.852s url=https://replicate.delivery/pbxt/UP69cUtnOWL6LB8aoHYp5M5AJyfLFoW1gfREoHNzrglQ6BhSA/trained_model.tar b'' Downloaded weights in 4.9480156898498535 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: The woman in the photo is wearing a blue dress and standing in a white room. She looks elegant and sophisticated, with her posture and outfit drawing attention. The white room serves as a simple and clean background for her attire.The lighting is bright and natural, realist detail, ue5, detailed character expressions, amazing quality, wallpaper, analog film grain. one person, 8k. In the style of EveningDressDF txt2img mode Token indices sequence length is longer than the specified maximum sequence length for this model (86 > 77). Running this sequence through the model will result in indexing errors The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['k. in the style of eveningdressdf'] Token indices sequence length is longer than the specified maximum sequence length for this model (86 > 77). Running this sequence through the model will result in indexing errors The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['k. in the style of eveningdressdf'] 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:38, 1.26it/s] 4%|▍ | 2/50 [00:00<00:18, 2.56it/s] 6%|▌ | 3/50 [00:01<00:12, 3.83it/s] 8%|▊ | 4/50 [00:01<00:09, 5.00it/s] 10%|█ | 5/50 [00:01<00:07, 6.02it/s] 12%|█▏ | 6/50 [00:01<00:06, 6.82it/s] 14%|█▍ | 7/50 [00:01<00:05, 7.48it/s] 16%|█▌ | 8/50 [00:01<00:05, 7.99it/s] 18%|█▊ | 9/50 [00:01<00:04, 8.36it/s] 20%|██ | 10/50 [00:01<00:04, 8.65it/s] 22%|██▏ | 11/50 [00:01<00:04, 8.87it/s] 24%|██▍ | 12/50 [00:01<00:04, 9.03it/s] 26%|██▌ | 13/50 [00:02<00:04, 9.15it/s] 28%|██▊ | 14/50 [00:02<00:03, 9.11it/s] 30%|███ | 15/50 [00:02<00:03, 9.16it/s] 32%|███▏ | 16/50 [00:02<00:03, 9.19it/s] 34%|███▍ | 17/50 [00:02<00:03, 9.22it/s] 36%|███▌ | 18/50 [00:02<00:03, 9.26it/s] 38%|███▊ | 19/50 [00:02<00:03, 9.28it/s] 40%|████ | 20/50 [00:02<00:03, 9.30it/s] 42%|████▏ | 21/50 [00:02<00:03, 9.33it/s] 44%|████▍ | 22/50 [00:03<00:03, 9.27it/s] 46%|████▌ | 23/50 [00:03<00:02, 9.29it/s] 48%|████▊ | 24/50 [00:03<00:02, 9.32it/s] 50%|█████ | 25/50 [00:03<00:02, 9.31it/s] 52%|█████▏ | 26/50 [00:03<00:02, 9.32it/s] 54%|█████▍ | 27/50 [00:03<00:02, 9.33it/s] 56%|█████▌ | 28/50 [00:03<00:02, 9.31it/s] 58%|█████▊ | 29/50 [00:03<00:02, 9.30it/s] 60%|██████ | 30/50 [00:03<00:02, 9.25it/s] 62%|██████▏ | 31/50 [00:04<00:02, 9.26it/s] 64%|██████▍ | 32/50 [00:04<00:01, 9.28it/s] 66%|██████▌ | 33/50 [00:04<00:01, 9.28it/s] 68%|██████▊ | 34/50 [00:04<00:01, 9.28it/s] 70%|███████ | 35/50 [00:04<00:01, 9.29it/s] 72%|███████▏ | 36/50 [00:04<00:01, 9.29it/s] 74%|███████▍ | 37/50 [00:04<00:01, 9.24it/s] 76%|███████▌ | 38/50 [00:04<00:01, 9.23it/s] 78%|███████▊ | 39/50 [00:04<00:01, 9.24it/s] 80%|████████ | 40/50 [00:04<00:01, 9.26it/s] 82%|████████▏ | 41/50 [00:05<00:00, 9.27it/s] 84%|████████▍ | 42/50 [00:05<00:00, 9.26it/s] 86%|████████▌ | 43/50 [00:05<00:00, 9.26it/s] 88%|████████▊ | 44/50 [00:05<00:00, 9.27it/s] 90%|█████████ | 45/50 [00:05<00:00, 9.28it/s] 92%|█████████▏| 46/50 [00:05<00:00, 9.29it/s] 94%|█████████▍| 47/50 [00:05<00:00, 9.29it/s] 96%|█████████▌| 48/50 [00:05<00:00, 9.25it/s] 98%|█████████▊| 49/50 [00:05<00:00, 9.25it/s] 100%|██████████| 50/50 [00:06<00:00, 9.25it/s] 100%|██████████| 50/50 [00:06<00:00, 8.24it/s] Token indices sequence length is longer than the specified maximum sequence length for this model (86 > 77). Running this sequence through the model will result in indexing errors The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['k. in the style of eveningdressdf'] 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:00<00:01, 9.75it/s] 20%|██ | 3/15 [00:00<00:00, 13.17it/s] 33%|███▎ | 5/15 [00:00<00:00, 14.04it/s] 47%|████▋ | 7/15 [00:00<00:00, 14.38it/s] 60%|██████ | 9/15 [00:00<00:00, 14.59it/s] 73%|███████▎ | 11/15 [00:00<00:00, 14.72it/s] 87%|████████▋ | 13/15 [00:00<00:00, 14.81it/s] 100%|██████████| 15/15 [00:01<00:00, 14.85it/s] 100%|██████████| 15/15 [00:01<00:00, 14.44it/s]
Prediction
omniedgeio/aquaaibase:aa55e8fb0395b0b0f0b0c82b160fdf2f9c7933dbb09b2d5b31089d4d53c1cbe8IDtlcel6tbna3mm3r27e2jsywnsmStatusSucceededSourceWebHardwareA100 (40GB)Total durationCreatedInput
- scale
- 2
- width
- 768
- height
- 1024
- prompt
- A woman is wearing a flowy, floral print maxi dress with a pair of strappy sandals and a wide-brimmed hat. She accessorizes with a woven straw bag and a pair of oversized sunglasses.
- refine
- base_image_refiner
- scheduler
- K_EULER_ANCESTRAL
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- cropped face, cover face, cover visage, mutated hands, bad anatomy, bad hands, three hands, three legs, bad arms,(missing legs), missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate, not human, no head,(low quality, worst quality:1.4), cgi, text, signature, watermark, extra limbs, cleavage
- prompt_strength
- 0.8
- is_face_enhancer
- num_inference_steps
- 50
- replicate_weights_Lora_url
- https://replicate.delivery/pbxt/erRAThfHeKS5jJXmZEKeWFye5nRf9eUQZypyjNafeZHd1EFLlA/trained_model.tar
{ "scale": 2, "width": 768, "height": 1024, "prompt": "A woman is wearing a flowy, floral print maxi dress with a pair of strappy sandals and a wide-brimmed hat. She accessorizes with a woven straw bag and a pair of oversized sunglasses.", "refine": "base_image_refiner", "scheduler": "K_EULER_ANCESTRAL", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "cropped face, cover face, cover visage, mutated hands, bad anatomy, bad hands, three hands, three legs, bad arms,(missing legs), missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate, not human, no head,(low quality, worst quality:1.4), cgi, text, signature, watermark, extra limbs, cleavage", "prompt_strength": 0.8, "is_face_enhancer": true, "num_inference_steps": 50, "replicate_weights_Lora_url": "https://replicate.delivery/pbxt/erRAThfHeKS5jJXmZEKeWFye5nRf9eUQZypyjNafeZHd1EFLlA/trained_model.tar" }
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 omniedgeio/aquaaibase using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "omniedgeio/aquaaibase:aa55e8fb0395b0b0f0b0c82b160fdf2f9c7933dbb09b2d5b31089d4d53c1cbe8", { input: { scale: 2, width: 768, height: 1024, prompt: "A woman is wearing a flowy, floral print maxi dress with a pair of strappy sandals and a wide-brimmed hat. She accessorizes with a woven straw bag and a pair of oversized sunglasses.", refine: "base_image_refiner", scheduler: "K_EULER_ANCESTRAL", lora_scale: 0.6, num_outputs: 1, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.8, negative_prompt: "cropped face, cover face, cover visage, mutated hands, bad anatomy, bad hands, three hands, three legs, bad arms,(missing legs), missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate, not human, no head,(low quality, worst quality:1.4), cgi, text, signature, watermark, extra limbs, cleavage", prompt_strength: 0.8, is_face_enhancer: true, num_inference_steps: 50, replicate_weights_Lora_url: "https://replicate.delivery/pbxt/erRAThfHeKS5jJXmZEKeWFye5nRf9eUQZypyjNafeZHd1EFLlA/trained_model.tar" } } ); // 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 omniedgeio/aquaaibase using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "omniedgeio/aquaaibase:aa55e8fb0395b0b0f0b0c82b160fdf2f9c7933dbb09b2d5b31089d4d53c1cbe8", input={ "scale": 2, "width": 768, "height": 1024, "prompt": "A woman is wearing a flowy, floral print maxi dress with a pair of strappy sandals and a wide-brimmed hat. She accessorizes with a woven straw bag and a pair of oversized sunglasses.", "refine": "base_image_refiner", "scheduler": "K_EULER_ANCESTRAL", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.8, "negative_prompt": "cropped face, cover face, cover visage, mutated hands, bad anatomy, bad hands, three hands, three legs, bad arms,(missing legs), missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate, not human, no head,(low quality, worst quality:1.4), cgi, text, signature, watermark, extra limbs, cleavage", "prompt_strength": 0.8, "is_face_enhancer": True, "num_inference_steps": 50, "replicate_weights_Lora_url": "https://replicate.delivery/pbxt/erRAThfHeKS5jJXmZEKeWFye5nRf9eUQZypyjNafeZHd1EFLlA/trained_model.tar" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run omniedgeio/aquaaibase 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": "omniedgeio/aquaaibase:aa55e8fb0395b0b0f0b0c82b160fdf2f9c7933dbb09b2d5b31089d4d53c1cbe8", "input": { "scale": 2, "width": 768, "height": 1024, "prompt": "A woman is wearing a flowy, floral print maxi dress with a pair of strappy sandals and a wide-brimmed hat. She accessorizes with a woven straw bag and a pair of oversized sunglasses.", "refine": "base_image_refiner", "scheduler": "K_EULER_ANCESTRAL", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "cropped face, cover face, cover visage, mutated hands, bad anatomy, bad hands, three hands, three legs, bad arms,(missing legs), missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate, not human, no head,(low quality, worst quality:1.4), cgi, text, signature, watermark, extra limbs, cleavage", "prompt_strength": 0.8, "is_face_enhancer": true, "num_inference_steps": 50, "replicate_weights_Lora_url": "https://replicate.delivery/pbxt/erRAThfHeKS5jJXmZEKeWFye5nRf9eUQZypyjNafeZHd1EFLlA/trained_model.tar" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-03-31T02:32:04.918823Z", "created_at": "2024-03-31T02:30:25.307522Z", "data_removed": false, "error": null, "id": "tlcel6tbna3mm3r27e2jsywnsm", "input": { "scale": 2, "width": 768, "height": 1024, "prompt": "A woman is wearing a flowy, floral print maxi dress with a pair of strappy sandals and a wide-brimmed hat. She accessorizes with a woven straw bag and a pair of oversized sunglasses.", "refine": "base_image_refiner", "scheduler": "K_EULER_ANCESTRAL", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "cropped face, cover face, cover visage, mutated hands, bad anatomy, bad hands, three hands, three legs, bad arms,(missing legs), missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate, not human, no head,(low quality, worst quality:1.4), cgi, text, signature, watermark, extra limbs, cleavage", "prompt_strength": 0.8, "is_face_enhancer": true, "num_inference_steps": 50, "replicate_weights_Lora_url": "https://replicate.delivery/pbxt/erRAThfHeKS5jJXmZEKeWFye5nRf9eUQZypyjNafeZHd1EFLlA/trained_model.tar" }, "logs": "Using seed: 36622\nEnsuring enough disk space...\nFree disk space: 2994108903424\nDownloading weights: https://replicate.delivery/pbxt/erRAThfHeKS5jJXmZEKeWFye5nRf9eUQZypyjNafeZHd1EFLlA/trained_model.tar\n2024-03-31T02:31:44Z | INFO | [ Initiating ] dest=/src/weights-cache/8b13f37f7f2a7e7a minimum_chunk_size=150M url=https://replicate.delivery/pbxt/erRAThfHeKS5jJXmZEKeWFye5nRf9eUQZypyjNafeZHd1EFLlA/trained_model.tar\n2024-03-31T02:31:48Z | INFO | [ Complete ] dest=/src/weights-cache/8b13f37f7f2a7e7a size=\"186 MB\" total_elapsed=3.769s url=https://replicate.delivery/pbxt/erRAThfHeKS5jJXmZEKeWFye5nRf9eUQZypyjNafeZHd1EFLlA/trained_model.tar\nb''\nDownloaded weights in 3.8806345462799072 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A woman is wearing a flowy, floral print maxi dress with a pair of strappy sandals and a wide-brimmed hat. She accessorizes with a woven straw bag and a pair of oversized sunglasses.\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:38, 1.26it/s]\n 4%|▍ | 2/50 [00:00<00:19, 2.48it/s]\n 6%|▌ | 3/50 [00:01<00:13, 3.60it/s]\n 8%|▊ | 4/50 [00:01<00:10, 4.58it/s]\n 10%|█ | 5/50 [00:01<00:08, 5.38it/s]\n 12%|█▏ | 6/50 [00:01<00:07, 6.02it/s]\n 14%|█▍ | 7/50 [00:01<00:06, 6.51it/s]\n 16%|█▌ | 8/50 [00:01<00:06, 6.87it/s]\n 18%|█▊ | 9/50 [00:01<00:05, 7.14it/s]\n 20%|██ | 10/50 [00:01<00:05, 7.34it/s]\n 22%|██▏ | 11/50 [00:02<00:05, 7.48it/s]\n 24%|██▍ | 12/50 [00:02<00:05, 7.58it/s]\n 26%|██▌ | 13/50 [00:02<00:04, 7.65it/s]\n 28%|██▊ | 14/50 [00:02<00:04, 7.71it/s]\n 30%|███ | 15/50 [00:02<00:04, 7.74it/s]\n 32%|███▏ | 16/50 [00:02<00:04, 7.77it/s]\n 34%|███▍ | 17/50 [00:02<00:04, 7.78it/s]\n 36%|███▌ | 18/50 [00:02<00:04, 7.80it/s]\n 38%|███▊ | 19/50 [00:03<00:03, 7.80it/s]\n 40%|████ | 20/50 [00:03<00:03, 7.81it/s]\n 42%|████▏ | 21/50 [00:03<00:03, 7.81it/s]\n 44%|████▍ | 22/50 [00:03<00:03, 7.81it/s]\n 46%|████▌ | 23/50 [00:03<00:03, 7.82it/s]\n 48%|████▊ | 24/50 [00:03<00:03, 7.82it/s]\n 50%|█████ | 25/50 [00:03<00:03, 7.82it/s]\n 52%|█████▏ | 26/50 [00:03<00:03, 7.82it/s]\n 54%|█████▍ | 27/50 [00:04<00:02, 7.82it/s]\n 56%|█████▌ | 28/50 [00:04<00:02, 7.83it/s]\n 58%|█████▊ | 29/50 [00:04<00:02, 7.83it/s]\n 60%|██████ | 30/50 [00:04<00:02, 7.82it/s]\n 62%|██████▏ | 31/50 [00:04<00:02, 7.82it/s]\n 64%|██████▍ | 32/50 [00:04<00:02, 7.82it/s]\n 66%|██████▌ | 33/50 [00:04<00:02, 7.82it/s]\n 68%|██████▊ | 34/50 [00:05<00:02, 7.82it/s]\n 70%|███████ | 35/50 [00:05<00:01, 7.82it/s]\n 72%|███████▏ | 36/50 [00:05<00:01, 7.82it/s]\n 74%|███████▍ | 37/50 [00:05<00:01, 7.81it/s]\n 76%|███████▌ | 38/50 [00:05<00:01, 7.81it/s]\n 78%|███████▊ | 39/50 [00:05<00:01, 7.80it/s]\n 80%|████████ | 40/50 [00:05<00:01, 7.80it/s]\n 82%|████████▏ | 41/50 [00:05<00:01, 7.80it/s]\n 84%|████████▍ | 42/50 [00:06<00:01, 7.80it/s]\n 86%|████████▌ | 43/50 [00:06<00:00, 7.80it/s]\n 88%|████████▊ | 44/50 [00:06<00:00, 7.80it/s]\n 90%|█████████ | 45/50 [00:06<00:00, 7.80it/s]\n 92%|█████████▏| 46/50 [00:06<00:00, 7.80it/s]\n 94%|█████████▍| 47/50 [00:06<00:00, 7.80it/s]\n 96%|█████████▌| 48/50 [00:06<00:00, 7.81it/s]\n 98%|█████████▊| 49/50 [00:06<00:00, 7.81it/s]\n100%|██████████| 50/50 [00:07<00:00, 7.81it/s]\n100%|██████████| 50/50 [00:07<00:00, 7.08it/s]\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:00<00:01, 9.35it/s]\n 20%|██ | 3/15 [00:00<00:01, 10.27it/s]\n 33%|███▎ | 5/15 [00:00<00:00, 10.44it/s]\n 47%|████▋ | 7/15 [00:00<00:00, 10.50it/s]\n 60%|██████ | 9/15 [00:00<00:00, 10.54it/s]\n 73%|███████▎ | 11/15 [00:01<00:00, 10.57it/s]\n 87%|████████▋ | 13/15 [00:01<00:00, 10.58it/s]\n100%|██████████| 15/15 [00:01<00:00, 10.60it/s]\n100%|██████████| 15/15 [00:01<00:00, 10.52it/s]\n/root/.pyenv/versions/3.9.19/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.\nwarnings.warn(\n/root/.pyenv/versions/3.9.19/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=None`.\nwarnings.warn(msg)\nDownloading: \"https://github.com/xinntao/facexlib/releases/download/v0.1.0/detection_Resnet50_Final.pth\" to /src/gfpgan/weights/detection_Resnet50_Final.pth\n 0%| | 0.00/104M [00:00<?, ?B/s]\n 45%|████▌ | 47.3M/104M [00:00<00:00, 496MB/s]\n 91%|█████████ | 94.9M/104M [00:00<00:00, 498MB/s]\n100%|██████████| 104M/104M [00:00<00:00, 498MB/s]\nDownloading: \"https://github.com/xinntao/facexlib/releases/download/v0.2.2/parsing_parsenet.pth\" to /src/gfpgan/weights/parsing_parsenet.pth\n 0%| | 0.00/81.4M [00:00<?, ?B/s]\n 56%|█████▌ | 45.7M/81.4M [00:00<00:00, 479MB/s]\n100%|██████████| 81.4M/81.4M [00:00<00:00, 483MB/s]\nTile 1/6\nTile 2/6\nTile 3/6\nTile 4/6\nTile 5/6\nTile 6/6\nis_face_enhancer is done", "metrics": { "predict_time": 20.649379, "total_time": 99.611301 }, "output": [ "https://replicate.delivery/pbxt/BpwmIYtVuMb5PZW08ORPgFizuXpHCZmfxheBJbx1zu2j0nlSA/DF-0.png" ], "started_at": "2024-03-31T02:31:44.269444Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/tlcel6tbna3mm3r27e2jsywnsm", "cancel": "https://api.replicate.com/v1/predictions/tlcel6tbna3mm3r27e2jsywnsm/cancel" }, "version": "aa55e8fb0395b0b0f0b0c82b160fdf2f9c7933dbb09b2d5b31089d4d53c1cbe8" }
Generated inUsing seed: 36622 Ensuring enough disk space... Free disk space: 2994108903424 Downloading weights: https://replicate.delivery/pbxt/erRAThfHeKS5jJXmZEKeWFye5nRf9eUQZypyjNafeZHd1EFLlA/trained_model.tar 2024-03-31T02:31:44Z | INFO | [ Initiating ] dest=/src/weights-cache/8b13f37f7f2a7e7a minimum_chunk_size=150M url=https://replicate.delivery/pbxt/erRAThfHeKS5jJXmZEKeWFye5nRf9eUQZypyjNafeZHd1EFLlA/trained_model.tar 2024-03-31T02:31:48Z | INFO | [ Complete ] dest=/src/weights-cache/8b13f37f7f2a7e7a size="186 MB" total_elapsed=3.769s url=https://replicate.delivery/pbxt/erRAThfHeKS5jJXmZEKeWFye5nRf9eUQZypyjNafeZHd1EFLlA/trained_model.tar b'' Downloaded weights in 3.8806345462799072 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A woman is wearing a flowy, floral print maxi dress with a pair of strappy sandals and a wide-brimmed hat. She accessorizes with a woven straw bag and a pair of oversized sunglasses. txt2img mode 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:38, 1.26it/s] 4%|▍ | 2/50 [00:00<00:19, 2.48it/s] 6%|▌ | 3/50 [00:01<00:13, 3.60it/s] 8%|▊ | 4/50 [00:01<00:10, 4.58it/s] 10%|█ | 5/50 [00:01<00:08, 5.38it/s] 12%|█▏ | 6/50 [00:01<00:07, 6.02it/s] 14%|█▍ | 7/50 [00:01<00:06, 6.51it/s] 16%|█▌ | 8/50 [00:01<00:06, 6.87it/s] 18%|█▊ | 9/50 [00:01<00:05, 7.14it/s] 20%|██ | 10/50 [00:01<00:05, 7.34it/s] 22%|██▏ | 11/50 [00:02<00:05, 7.48it/s] 24%|██▍ | 12/50 [00:02<00:05, 7.58it/s] 26%|██▌ | 13/50 [00:02<00:04, 7.65it/s] 28%|██▊ | 14/50 [00:02<00:04, 7.71it/s] 30%|███ | 15/50 [00:02<00:04, 7.74it/s] 32%|███▏ | 16/50 [00:02<00:04, 7.77it/s] 34%|███▍ | 17/50 [00:02<00:04, 7.78it/s] 36%|███▌ | 18/50 [00:02<00:04, 7.80it/s] 38%|███▊ | 19/50 [00:03<00:03, 7.80it/s] 40%|████ | 20/50 [00:03<00:03, 7.81it/s] 42%|████▏ | 21/50 [00:03<00:03, 7.81it/s] 44%|████▍ | 22/50 [00:03<00:03, 7.81it/s] 46%|████▌ | 23/50 [00:03<00:03, 7.82it/s] 48%|████▊ | 24/50 [00:03<00:03, 7.82it/s] 50%|█████ | 25/50 [00:03<00:03, 7.82it/s] 52%|█████▏ | 26/50 [00:03<00:03, 7.82it/s] 54%|█████▍ | 27/50 [00:04<00:02, 7.82it/s] 56%|█████▌ | 28/50 [00:04<00:02, 7.83it/s] 58%|█████▊ | 29/50 [00:04<00:02, 7.83it/s] 60%|██████ | 30/50 [00:04<00:02, 7.82it/s] 62%|██████▏ | 31/50 [00:04<00:02, 7.82it/s] 64%|██████▍ | 32/50 [00:04<00:02, 7.82it/s] 66%|██████▌ | 33/50 [00:04<00:02, 7.82it/s] 68%|██████▊ | 34/50 [00:05<00:02, 7.82it/s] 70%|███████ | 35/50 [00:05<00:01, 7.82it/s] 72%|███████▏ | 36/50 [00:05<00:01, 7.82it/s] 74%|███████▍ | 37/50 [00:05<00:01, 7.81it/s] 76%|███████▌ | 38/50 [00:05<00:01, 7.81it/s] 78%|███████▊ | 39/50 [00:05<00:01, 7.80it/s] 80%|████████ | 40/50 [00:05<00:01, 7.80it/s] 82%|████████▏ | 41/50 [00:05<00:01, 7.80it/s] 84%|████████▍ | 42/50 [00:06<00:01, 7.80it/s] 86%|████████▌ | 43/50 [00:06<00:00, 7.80it/s] 88%|████████▊ | 44/50 [00:06<00:00, 7.80it/s] 90%|█████████ | 45/50 [00:06<00:00, 7.80it/s] 92%|█████████▏| 46/50 [00:06<00:00, 7.80it/s] 94%|█████████▍| 47/50 [00:06<00:00, 7.80it/s] 96%|█████████▌| 48/50 [00:06<00:00, 7.81it/s] 98%|█████████▊| 49/50 [00:06<00:00, 7.81it/s] 100%|██████████| 50/50 [00:07<00:00, 7.81it/s] 100%|██████████| 50/50 [00:07<00:00, 7.08it/s] 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:00<00:01, 9.35it/s] 20%|██ | 3/15 [00:00<00:01, 10.27it/s] 33%|███▎ | 5/15 [00:00<00:00, 10.44it/s] 47%|████▋ | 7/15 [00:00<00:00, 10.50it/s] 60%|██████ | 9/15 [00:00<00:00, 10.54it/s] 73%|███████▎ | 11/15 [00:01<00:00, 10.57it/s] 87%|████████▋ | 13/15 [00:01<00:00, 10.58it/s] 100%|██████████| 15/15 [00:01<00:00, 10.60it/s] 100%|██████████| 15/15 [00:01<00:00, 10.52it/s] /root/.pyenv/versions/3.9.19/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. warnings.warn( /root/.pyenv/versions/3.9.19/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=None`. warnings.warn(msg) Downloading: "https://github.com/xinntao/facexlib/releases/download/v0.1.0/detection_Resnet50_Final.pth" to /src/gfpgan/weights/detection_Resnet50_Final.pth 0%| | 0.00/104M [00:00<?, ?B/s] 45%|████▌ | 47.3M/104M [00:00<00:00, 496MB/s] 91%|█████████ | 94.9M/104M [00:00<00:00, 498MB/s] 100%|██████████| 104M/104M [00:00<00:00, 498MB/s] Downloading: "https://github.com/xinntao/facexlib/releases/download/v0.2.2/parsing_parsenet.pth" to /src/gfpgan/weights/parsing_parsenet.pth 0%| | 0.00/81.4M [00:00<?, ?B/s] 56%|█████▌ | 45.7M/81.4M [00:00<00:00, 479MB/s] 100%|██████████| 81.4M/81.4M [00:00<00:00, 483MB/s] Tile 1/6 Tile 2/6 Tile 3/6 Tile 4/6 Tile 5/6 Tile 6/6 is_face_enhancer is done
Prediction
omniedgeio/aquaaibase:aa55e8fb0395b0b0f0b0c82b160fdf2f9c7933dbb09b2d5b31089d4d53c1cbe8ID3g0k99j3p9rgg0cemwyt5ef2rgStatusSucceededSourceWebHardwareA100 (40GB)Total durationCreatedInput
- scale
- 2
- width
- 1024
- height
- 1024
- prompt
- UHD 4k vogue, a woman wearing a colorful organic hat
- refine
- base_image_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- Teeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutant
- prompt_strength
- 0.8
- is_face_enhancer
- num_inference_steps
- 50
{ "scale": 2, "width": 1024, "height": 1024, "prompt": "UHD 4k vogue, a woman wearing a colorful organic hat", "refine": "base_image_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "Teeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutant", "prompt_strength": 0.8, "is_face_enhancer": true, "num_inference_steps": 50 }
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 omniedgeio/aquaaibase using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "omniedgeio/aquaaibase:aa55e8fb0395b0b0f0b0c82b160fdf2f9c7933dbb09b2d5b31089d4d53c1cbe8", { input: { scale: 2, width: 1024, height: 1024, prompt: "UHD 4k vogue, a woman wearing a colorful organic hat", refine: "base_image_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "Teeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutant", prompt_strength: 0.8, is_face_enhancer: true, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run omniedgeio/aquaaibase using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "omniedgeio/aquaaibase:aa55e8fb0395b0b0f0b0c82b160fdf2f9c7933dbb09b2d5b31089d4d53c1cbe8", input={ "scale": 2, "width": 1024, "height": 1024, "prompt": "UHD 4k vogue, a woman wearing a colorful organic hat", "refine": "base_image_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "Teeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutant", "prompt_strength": 0.8, "is_face_enhancer": True, "num_inference_steps": 50 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run omniedgeio/aquaaibase 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": "omniedgeio/aquaaibase:aa55e8fb0395b0b0f0b0c82b160fdf2f9c7933dbb09b2d5b31089d4d53c1cbe8", "input": { "scale": 2, "width": 1024, "height": 1024, "prompt": "UHD 4k vogue, a woman wearing a colorful organic hat", "refine": "base_image_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "Teeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutant", "prompt_strength": 0.8, "is_face_enhancer": true, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-04-04T03:55:59.299259Z", "created_at": "2024-04-04T03:53:13.906000Z", "data_removed": false, "error": null, "id": "3g0k99j3p9rgg0cemwyt5ef2rg", "input": { "scale": 2, "width": 1024, "height": 1024, "prompt": "UHD 4k vogue, a woman wearing a colorful organic hat", "refine": "base_image_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "Teeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutant", "prompt_strength": 0.8, "is_face_enhancer": true, "num_inference_steps": 50 }, "logs": "Using seed: 43752\nPrompt: UHD 4k vogue, a woman wearing a colorful organic hat\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:39, 1.25it/s]\n 4%|▍ | 2/50 [00:00<00:19, 2.52it/s]\n 6%|▌ | 3/50 [00:01<00:12, 3.74it/s]\n 8%|▊ | 4/50 [00:01<00:09, 4.83it/s]\n 10%|█ | 5/50 [00:01<00:07, 5.77it/s]\n 12%|█▏ | 6/50 [00:01<00:06, 6.53it/s]\n 14%|█▍ | 7/50 [00:01<00:06, 7.12it/s]\n 16%|█▌ | 8/50 [00:01<00:05, 7.57it/s]\n 18%|█▊ | 9/50 [00:01<00:05, 7.91it/s]\n 20%|██ | 10/50 [00:01<00:04, 8.16it/s]\n 22%|██▏ | 11/50 [00:01<00:04, 8.33it/s]\n 24%|██▍ | 12/50 [00:02<00:04, 8.46it/s]\n 26%|██▌ | 13/50 [00:02<00:04, 8.56it/s]\n 28%|██▊ | 14/50 [00:02<00:04, 8.62it/s]\n 30%|███ | 15/50 [00:02<00:04, 8.66it/s]\n 32%|███▏ | 16/50 [00:02<00:03, 8.69it/s]\n 34%|███▍ | 17/50 [00:02<00:03, 8.72it/s]\n 36%|███▌ | 18/50 [00:02<00:03, 8.73it/s]\n 38%|███▊ | 19/50 [00:02<00:03, 8.74it/s]\n 40%|████ | 20/50 [00:02<00:03, 8.75it/s]\n 42%|████▏ | 21/50 [00:03<00:03, 8.75it/s]\n 44%|████▍ | 22/50 [00:03<00:03, 8.75it/s]\n 46%|████▌ | 23/50 [00:03<00:03, 8.75it/s]\n 48%|████▊ | 24/50 [00:03<00:02, 8.75it/s]\n 50%|█████ | 25/50 [00:03<00:02, 8.76it/s]\n 52%|█████▏ | 26/50 [00:03<00:02, 8.76it/s]\n 54%|█████▍ | 27/50 [00:03<00:02, 8.76it/s]\n 56%|█████▌ | 28/50 [00:03<00:02, 8.76it/s]\n 58%|█████▊ | 29/50 [00:03<00:02, 8.75it/s]\n 60%|██████ | 30/50 [00:04<00:02, 8.75it/s]\n 62%|██████▏ | 31/50 [00:04<00:02, 8.75it/s]\n 64%|██████▍ | 32/50 [00:04<00:02, 8.75it/s]\n 66%|██████▌ | 33/50 [00:04<00:01, 8.75it/s]\n 68%|██████▊ | 34/50 [00:04<00:01, 8.76it/s]\n 70%|███████ | 35/50 [00:04<00:01, 8.77it/s]\n 72%|███████▏ | 36/50 [00:04<00:01, 8.77it/s]\n 74%|███████▍ | 37/50 [00:04<00:01, 8.77it/s]\n 76%|███████▌ | 38/50 [00:05<00:01, 8.77it/s]\n 78%|███████▊ | 39/50 [00:05<00:01, 8.77it/s]\n 80%|████████ | 40/50 [00:05<00:01, 8.76it/s]\n 82%|████████▏ | 41/50 [00:05<00:01, 8.76it/s]\n 84%|████████▍ | 42/50 [00:05<00:00, 8.76it/s]\n 86%|████████▌ | 43/50 [00:05<00:00, 8.76it/s]\n 88%|████████▊ | 44/50 [00:05<00:00, 8.77it/s]\n 90%|█████████ | 45/50 [00:05<00:00, 8.76it/s]\n 92%|█████████▏| 46/50 [00:05<00:00, 8.76it/s]\n 94%|█████████▍| 47/50 [00:06<00:00, 8.77it/s]\n 96%|█████████▌| 48/50 [00:06<00:00, 8.77it/s]\n 98%|█████████▊| 49/50 [00:06<00:00, 8.76it/s]\n100%|██████████| 50/50 [00:06<00:00, 8.76it/s]\n100%|██████████| 50/50 [00:06<00:00, 7.82it/s]\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:00<00:01, 7.33it/s]\n 13%|█▎ | 2/15 [00:00<00:01, 7.63it/s]\n 20%|██ | 3/15 [00:00<00:01, 7.73it/s]\n 27%|██▋ | 4/15 [00:00<00:01, 7.78it/s]\n 33%|███▎ | 5/15 [00:00<00:01, 7.81it/s]\n 40%|████ | 6/15 [00:00<00:01, 7.82it/s]\n 47%|████▋ | 7/15 [00:00<00:01, 7.83it/s]\n 53%|█████▎ | 8/15 [00:01<00:00, 7.83it/s]\n 60%|██████ | 9/15 [00:01<00:00, 7.84it/s]\n 67%|██████▋ | 10/15 [00:01<00:00, 7.85it/s]\n 73%|███████▎ | 11/15 [00:01<00:00, 7.86it/s]\n 80%|████████ | 12/15 [00:01<00:00, 7.86it/s]\n 87%|████████▋ | 13/15 [00:01<00:00, 7.85it/s]\n 93%|█████████▎| 14/15 [00:01<00:00, 7.85it/s]\n100%|██████████| 15/15 [00:01<00:00, 7.85it/s]\n100%|██████████| 15/15 [00:01<00:00, 7.82it/s]\n/root/.pyenv/versions/3.9.19/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.\nwarnings.warn(\n/root/.pyenv/versions/3.9.19/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=None`.\nwarnings.warn(msg)\nDownloading: \"https://github.com/xinntao/facexlib/releases/download/v0.1.0/detection_Resnet50_Final.pth\" to /src/gfpgan/weights/detection_Resnet50_Final.pth\n 0%| | 0.00/104M [00:00<?, ?B/s]\n 33%|███▎ | 34.9M/104M [00:00<00:00, 366MB/s]\n 68%|██████▊ | 70.5M/104M [00:00<00:00, 370MB/s]\n100%|██████████| 104M/104M [00:00<00:00, 373MB/s]\nDownloading: \"https://github.com/xinntao/facexlib/releases/download/v0.2.2/parsing_parsenet.pth\" to /src/gfpgan/weights/parsing_parsenet.pth\n 0%| | 0.00/81.4M [00:00<?, ?B/s]\n 31%|███ | 25.2M/81.4M [00:00<00:00, 264MB/s]\n 66%|██████▌ | 53.7M/81.4M [00:00<00:00, 284MB/s]\n100%|██████████| 81.4M/81.4M [00:00<00:00, 302MB/s]\nTile 1/9\nTile 2/9\nTile 3/9\nTile 4/9\nTile 5/9\nTile 6/9\nTile 7/9\nTile 8/9\nTile 9/9\nis_face_enhancer is done", "metrics": { "predict_time": 24.480502, "total_time": 165.393259 }, "output": [ "https://replicate.delivery/pbxt/nprKtJETfh2dXSIigVFhfuV8DI9cIYqt25kaGJhgawhOb9mSA/DF-0.png" ], "started_at": "2024-04-04T03:55:34.818757Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/3g0k99j3p9rgg0cemwyt5ef2rg", "cancel": "https://api.replicate.com/v1/predictions/3g0k99j3p9rgg0cemwyt5ef2rg/cancel" }, "version": "aa55e8fb0395b0b0f0b0c82b160fdf2f9c7933dbb09b2d5b31089d4d53c1cbe8" }
Generated inUsing seed: 43752 Prompt: UHD 4k vogue, a woman wearing a colorful organic hat txt2img mode 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:39, 1.25it/s] 4%|▍ | 2/50 [00:00<00:19, 2.52it/s] 6%|▌ | 3/50 [00:01<00:12, 3.74it/s] 8%|▊ | 4/50 [00:01<00:09, 4.83it/s] 10%|█ | 5/50 [00:01<00:07, 5.77it/s] 12%|█▏ | 6/50 [00:01<00:06, 6.53it/s] 14%|█▍ | 7/50 [00:01<00:06, 7.12it/s] 16%|█▌ | 8/50 [00:01<00:05, 7.57it/s] 18%|█▊ | 9/50 [00:01<00:05, 7.91it/s] 20%|██ | 10/50 [00:01<00:04, 8.16it/s] 22%|██▏ | 11/50 [00:01<00:04, 8.33it/s] 24%|██▍ | 12/50 [00:02<00:04, 8.46it/s] 26%|██▌ | 13/50 [00:02<00:04, 8.56it/s] 28%|██▊ | 14/50 [00:02<00:04, 8.62it/s] 30%|███ | 15/50 [00:02<00:04, 8.66it/s] 32%|███▏ | 16/50 [00:02<00:03, 8.69it/s] 34%|███▍ | 17/50 [00:02<00:03, 8.72it/s] 36%|███▌ | 18/50 [00:02<00:03, 8.73it/s] 38%|███▊ | 19/50 [00:02<00:03, 8.74it/s] 40%|████ | 20/50 [00:02<00:03, 8.75it/s] 42%|████▏ | 21/50 [00:03<00:03, 8.75it/s] 44%|████▍ | 22/50 [00:03<00:03, 8.75it/s] 46%|████▌ | 23/50 [00:03<00:03, 8.75it/s] 48%|████▊ | 24/50 [00:03<00:02, 8.75it/s] 50%|█████ | 25/50 [00:03<00:02, 8.76it/s] 52%|█████▏ | 26/50 [00:03<00:02, 8.76it/s] 54%|█████▍ | 27/50 [00:03<00:02, 8.76it/s] 56%|█████▌ | 28/50 [00:03<00:02, 8.76it/s] 58%|█████▊ | 29/50 [00:03<00:02, 8.75it/s] 60%|██████ | 30/50 [00:04<00:02, 8.75it/s] 62%|██████▏ | 31/50 [00:04<00:02, 8.75it/s] 64%|██████▍ | 32/50 [00:04<00:02, 8.75it/s] 66%|██████▌ | 33/50 [00:04<00:01, 8.75it/s] 68%|██████▊ | 34/50 [00:04<00:01, 8.76it/s] 70%|███████ | 35/50 [00:04<00:01, 8.77it/s] 72%|███████▏ | 36/50 [00:04<00:01, 8.77it/s] 74%|███████▍ | 37/50 [00:04<00:01, 8.77it/s] 76%|███████▌ | 38/50 [00:05<00:01, 8.77it/s] 78%|███████▊ | 39/50 [00:05<00:01, 8.77it/s] 80%|████████ | 40/50 [00:05<00:01, 8.76it/s] 82%|████████▏ | 41/50 [00:05<00:01, 8.76it/s] 84%|████████▍ | 42/50 [00:05<00:00, 8.76it/s] 86%|████████▌ | 43/50 [00:05<00:00, 8.76it/s] 88%|████████▊ | 44/50 [00:05<00:00, 8.77it/s] 90%|█████████ | 45/50 [00:05<00:00, 8.76it/s] 92%|█████████▏| 46/50 [00:05<00:00, 8.76it/s] 94%|█████████▍| 47/50 [00:06<00:00, 8.77it/s] 96%|█████████▌| 48/50 [00:06<00:00, 8.77it/s] 98%|█████████▊| 49/50 [00:06<00:00, 8.76it/s] 100%|██████████| 50/50 [00:06<00:00, 8.76it/s] 100%|██████████| 50/50 [00:06<00:00, 7.82it/s] 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:00<00:01, 7.33it/s] 13%|█▎ | 2/15 [00:00<00:01, 7.63it/s] 20%|██ | 3/15 [00:00<00:01, 7.73it/s] 27%|██▋ | 4/15 [00:00<00:01, 7.78it/s] 33%|███▎ | 5/15 [00:00<00:01, 7.81it/s] 40%|████ | 6/15 [00:00<00:01, 7.82it/s] 47%|████▋ | 7/15 [00:00<00:01, 7.83it/s] 53%|█████▎ | 8/15 [00:01<00:00, 7.83it/s] 60%|██████ | 9/15 [00:01<00:00, 7.84it/s] 67%|██████▋ | 10/15 [00:01<00:00, 7.85it/s] 73%|███████▎ | 11/15 [00:01<00:00, 7.86it/s] 80%|████████ | 12/15 [00:01<00:00, 7.86it/s] 87%|████████▋ | 13/15 [00:01<00:00, 7.85it/s] 93%|█████████▎| 14/15 [00:01<00:00, 7.85it/s] 100%|██████████| 15/15 [00:01<00:00, 7.85it/s] 100%|██████████| 15/15 [00:01<00:00, 7.82it/s] /root/.pyenv/versions/3.9.19/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. warnings.warn( /root/.pyenv/versions/3.9.19/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=None`. warnings.warn(msg) Downloading: "https://github.com/xinntao/facexlib/releases/download/v0.1.0/detection_Resnet50_Final.pth" to /src/gfpgan/weights/detection_Resnet50_Final.pth 0%| | 0.00/104M [00:00<?, ?B/s] 33%|███▎ | 34.9M/104M [00:00<00:00, 366MB/s] 68%|██████▊ | 70.5M/104M [00:00<00:00, 370MB/s] 100%|██████████| 104M/104M [00:00<00:00, 373MB/s] Downloading: "https://github.com/xinntao/facexlib/releases/download/v0.2.2/parsing_parsenet.pth" to /src/gfpgan/weights/parsing_parsenet.pth 0%| | 0.00/81.4M [00:00<?, ?B/s] 31%|███ | 25.2M/81.4M [00:00<00:00, 264MB/s] 66%|██████▌ | 53.7M/81.4M [00:00<00:00, 284MB/s] 100%|██████████| 81.4M/81.4M [00:00<00:00, 302MB/s] Tile 1/9 Tile 2/9 Tile 3/9 Tile 4/9 Tile 5/9 Tile 6/9 Tile 7/9 Tile 8/9 Tile 9/9 is_face_enhancer is done
Want to make some of these yourself?
Run this model