eledah / sdxl-lora-character-chamran
SDXL LoRA model for generating images of Chamran
- Public
- 143 runs
-
L40S
- SDXL fine-tune
Prediction
eledah/sdxl-lora-character-chamran:9ee813be18f9e2dc0836789ede7e93f0c53521ddc32067bdef51d2862767a85dIDvv3mcza90nrgj0cj7k5snbts7rStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- fuji film candid portrait of Chamran wearing sunglasses rocking out on the streets of miami at night, 80s album cover, vaporwave, synthwave, retrowave, cinematic, intense, highly detailed, dark ambient, beautiful, dramatic lighting, hyperrealistic
- refine
- no_refiner
- scheduler
- DDIM
- lora_scale
- 0.75
- num_outputs
- 4
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- bad lighting, low-quality, deformed, text, poorly drawn, holding camera, bad art, bad angle, boring, low-resolution, worst quality, bad composition, disfigured
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": " fuji film candid portrait of Chamran wearing sunglasses rocking out on the streets of miami at night, 80s album cover, vaporwave, synthwave, retrowave, cinematic, intense, highly detailed, dark ambient, beautiful, dramatic lighting, hyperrealistic ", "refine": "no_refiner", "scheduler": "DDIM", "lora_scale": 0.75, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "bad lighting, low-quality, deformed, text, poorly drawn, holding camera, bad art, bad angle, boring, low-resolution, worst quality, bad composition, disfigured", "prompt_strength": 0.8, "num_inference_steps": 50 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run eledah/sdxl-lora-character-chamran using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "eledah/sdxl-lora-character-chamran:9ee813be18f9e2dc0836789ede7e93f0c53521ddc32067bdef51d2862767a85d", { input: { width: 1024, height: 1024, prompt: " fuji film candid portrait of Chamran wearing sunglasses rocking out on the streets of miami at night, 80s album cover, vaporwave, synthwave, retrowave, cinematic, intense, highly detailed, dark ambient, beautiful, dramatic lighting, hyperrealistic ", refine: "no_refiner", scheduler: "DDIM", lora_scale: 0.75, num_outputs: 4, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "bad lighting, low-quality, deformed, text, poorly drawn, holding camera, bad art, bad angle, boring, low-resolution, worst quality, bad composition, disfigured", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run eledah/sdxl-lora-character-chamran using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "eledah/sdxl-lora-character-chamran:9ee813be18f9e2dc0836789ede7e93f0c53521ddc32067bdef51d2862767a85d", input={ "width": 1024, "height": 1024, "prompt": " fuji film candid portrait of Chamran wearing sunglasses rocking out on the streets of miami at night, 80s album cover, vaporwave, synthwave, retrowave, cinematic, intense, highly detailed, dark ambient, beautiful, dramatic lighting, hyperrealistic ", "refine": "no_refiner", "scheduler": "DDIM", "lora_scale": 0.75, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "bad lighting, low-quality, deformed, text, poorly drawn, holding camera, bad art, bad angle, boring, low-resolution, worst quality, bad composition, disfigured", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run eledah/sdxl-lora-character-chamran 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": "eledah/sdxl-lora-character-chamran:9ee813be18f9e2dc0836789ede7e93f0c53521ddc32067bdef51d2862767a85d", "input": { "width": 1024, "height": 1024, "prompt": " fuji film candid portrait of Chamran wearing sunglasses rocking out on the streets of miami at night, 80s album cover, vaporwave, synthwave, retrowave, cinematic, intense, highly detailed, dark ambient, beautiful, dramatic lighting, hyperrealistic ", "refine": "no_refiner", "scheduler": "DDIM", "lora_scale": 0.75, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "bad lighting, low-quality, deformed, text, poorly drawn, holding camera, bad art, bad angle, boring, low-resolution, worst quality, bad composition, disfigured", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-09-29T08:01:09.396437Z", "created_at": "2024-09-29T08:00:08.453000Z", "data_removed": false, "error": null, "id": "vv3mcza90nrgj0cj7k5snbts7r", "input": { "width": 1024, "height": 1024, "prompt": " fuji film candid portrait of Chamran wearing sunglasses rocking out on the streets of miami at night, 80s album cover, vaporwave, synthwave, retrowave, cinematic, intense, highly detailed, dark ambient, beautiful, dramatic lighting, hyperrealistic ", "refine": "no_refiner", "scheduler": "DDIM", "lora_scale": 0.75, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "bad lighting, low-quality, deformed, text, poorly drawn, holding camera, bad art, bad angle, boring, low-resolution, worst quality, bad composition, disfigured", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 11126\nEnsuring enough disk space...\nFree disk space: 2049103327232\nDownloading weights: https://replicate.delivery/pbxt/apUqPhefKyjCs0nRswRc6a6NMBjnQhVqi4q2CdjNrCHtTZdTA/trained_model.tar\n2024-09-29T08:00:10Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/1a7c5c72d2147ecf url=https://replicate.delivery/pbxt/apUqPhefKyjCs0nRswRc6a6NMBjnQhVqi4q2CdjNrCHtTZdTA/trained_model.tar\n2024-09-29T08:00:16Z | INFO | [ Complete ] dest=/src/weights-cache/1a7c5c72d2147ecf size=\"186 MB\" total_elapsed=6.119s url=https://replicate.delivery/pbxt/apUqPhefKyjCs0nRswRc6a6NMBjnQhVqi4q2CdjNrCHtTZdTA/trained_model.tar\nb''\nDownloaded weights in 6.240539073944092 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: fuji film candid portrait of Chamran wearing sunglasses rocking out on the streets of miami at night, 80s album cover, vaporwave, synthwave, retrowave, cinematic, intense, highly detailed, dark ambient, beautiful, dramatic lighting, hyperrealistic\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights`\ndeprecate(\n 2%|▏ | 1/50 [00:00<00:45, 1.08it/s]\n 4%|▍ | 2/50 [00:01<00:44, 1.08it/s]\n 6%|▌ | 3/50 [00:02<00:43, 1.08it/s]\n 8%|▊ | 4/50 [00:03<00:42, 1.08it/s]\n 10%|█ | 5/50 [00:04<00:41, 1.08it/s]\n 12%|█▏ | 6/50 [00:05<00:40, 1.08it/s]\n 14%|█▍ | 7/50 [00:06<00:39, 1.08it/s]\n 16%|█▌ | 8/50 [00:07<00:38, 1.08it/s]\n 18%|█▊ | 9/50 [00:08<00:37, 1.08it/s]\n 20%|██ | 10/50 [00:09<00:37, 1.08it/s]\n 22%|██▏ | 11/50 [00:10<00:36, 1.08it/s]\n 24%|██▍ | 12/50 [00:11<00:35, 1.08it/s]\n 26%|██▌ | 13/50 [00:12<00:34, 1.08it/s]\n 28%|██▊ | 14/50 [00:12<00:33, 1.08it/s]\n 30%|███ | 15/50 [00:13<00:32, 1.08it/s]\n 32%|███▏ | 16/50 [00:14<00:31, 1.08it/s]\n 34%|███▍ | 17/50 [00:15<00:30, 1.08it/s]\n 36%|███▌ | 18/50 [00:16<00:29, 1.08it/s]\n 38%|███▊ | 19/50 [00:17<00:28, 1.08it/s]\n 40%|████ | 20/50 [00:18<00:27, 1.08it/s]\n 42%|████▏ | 21/50 [00:19<00:26, 1.08it/s]\n 44%|████▍ | 22/50 [00:20<00:25, 1.08it/s]\n 46%|████▌ | 23/50 [00:21<00:25, 1.08it/s]\n 48%|████▊ | 24/50 [00:22<00:24, 1.08it/s]\n 50%|█████ | 25/50 [00:23<00:23, 1.08it/s]\n 52%|█████▏ | 26/50 [00:24<00:22, 1.08it/s]\n 54%|█████▍ | 27/50 [00:25<00:21, 1.08it/s]\n 56%|█████▌ | 28/50 [00:25<00:20, 1.08it/s]\n 58%|█████▊ | 29/50 [00:26<00:19, 1.08it/s]\n 60%|██████ | 30/50 [00:27<00:18, 1.08it/s]\n 62%|██████▏ | 31/50 [00:28<00:17, 1.08it/s]\n 64%|██████▍ | 32/50 [00:29<00:16, 1.08it/s]\n 66%|██████▌ | 33/50 [00:30<00:15, 1.08it/s]\n 68%|██████▊ | 34/50 [00:31<00:14, 1.07it/s]\n 70%|███████ | 35/50 [00:32<00:13, 1.07it/s]\n 72%|███████▏ | 36/50 [00:33<00:13, 1.08it/s]\n 74%|███████▍ | 37/50 [00:34<00:12, 1.08it/s]\n 76%|███████▌ | 38/50 [00:35<00:11, 1.08it/s]\n 78%|███████▊ | 39/50 [00:36<00:10, 1.08it/s]\n 80%|████████ | 40/50 [00:37<00:09, 1.08it/s]\n 82%|████████▏ | 41/50 [00:38<00:08, 1.07it/s]\n 84%|████████▍ | 42/50 [00:38<00:07, 1.07it/s]\n 86%|████████▌ | 43/50 [00:39<00:06, 1.08it/s]\n 88%|████████▊ | 44/50 [00:40<00:05, 1.07it/s]\n 90%|█████████ | 45/50 [00:41<00:04, 1.07it/s]\n 92%|█████████▏| 46/50 [00:42<00:03, 1.07it/s]\n 94%|█████████▍| 47/50 [00:43<00:02, 1.08it/s]\n 96%|█████████▌| 48/50 [00:44<00:01, 1.07it/s]\n 98%|█████████▊| 49/50 [00:45<00:00, 1.07it/s]\n100%|██████████| 50/50 [00:46<00:00, 1.07it/s]\n100%|██████████| 50/50 [00:46<00:00, 1.08it/s]", "metrics": { "predict_time": 59.275016557, "total_time": 60.943437 }, "output": [ "https://replicate.delivery/pbxt/yqUEH5syf5XWYCEGszXpQ9vfhrYB03gQTxvw69exY4aKaXDnA/out-0.png", "https://replicate.delivery/pbxt/XUyRejuSiFwQPCyNeEXpSff1Sw8Bh8o7Fl3bSsAHieXsodNcC/out-1.png", "https://replicate.delivery/pbxt/0lZSIpsCtEK3AlHk1zuUVcTCSgdTkPePa3DDv5Ip8Hxi21wJA/out-2.png", "https://replicate.delivery/pbxt/d2lZjdLWqMKwBJrWyPXqdpnCYDzI2tFbinsiIYdX6wSR7a4E/out-3.png" ], "started_at": "2024-09-29T08:00:10.121421Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/vv3mcza90nrgj0cj7k5snbts7r", "cancel": "https://api.replicate.com/v1/predictions/vv3mcza90nrgj0cj7k5snbts7r/cancel" }, "version": "9ee813be18f9e2dc0836789ede7e93f0c53521ddc32067bdef51d2862767a85d" }
Generated inUsing seed: 11126 Ensuring enough disk space... Free disk space: 2049103327232 Downloading weights: https://replicate.delivery/pbxt/apUqPhefKyjCs0nRswRc6a6NMBjnQhVqi4q2CdjNrCHtTZdTA/trained_model.tar 2024-09-29T08:00:10Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/1a7c5c72d2147ecf url=https://replicate.delivery/pbxt/apUqPhefKyjCs0nRswRc6a6NMBjnQhVqi4q2CdjNrCHtTZdTA/trained_model.tar 2024-09-29T08:00:16Z | INFO | [ Complete ] dest=/src/weights-cache/1a7c5c72d2147ecf size="186 MB" total_elapsed=6.119s url=https://replicate.delivery/pbxt/apUqPhefKyjCs0nRswRc6a6NMBjnQhVqi4q2CdjNrCHtTZdTA/trained_model.tar b'' Downloaded weights in 6.240539073944092 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: fuji film candid portrait of Chamran wearing sunglasses rocking out on the streets of miami at night, 80s album cover, vaporwave, synthwave, retrowave, cinematic, intense, highly detailed, dark ambient, beautiful, dramatic lighting, hyperrealistic txt2img mode 0%| | 0/50 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights` deprecate( 2%|▏ | 1/50 [00:00<00:45, 1.08it/s] 4%|▍ | 2/50 [00:01<00:44, 1.08it/s] 6%|▌ | 3/50 [00:02<00:43, 1.08it/s] 8%|▊ | 4/50 [00:03<00:42, 1.08it/s] 10%|█ | 5/50 [00:04<00:41, 1.08it/s] 12%|█▏ | 6/50 [00:05<00:40, 1.08it/s] 14%|█▍ | 7/50 [00:06<00:39, 1.08it/s] 16%|█▌ | 8/50 [00:07<00:38, 1.08it/s] 18%|█▊ | 9/50 [00:08<00:37, 1.08it/s] 20%|██ | 10/50 [00:09<00:37, 1.08it/s] 22%|██▏ | 11/50 [00:10<00:36, 1.08it/s] 24%|██▍ | 12/50 [00:11<00:35, 1.08it/s] 26%|██▌ | 13/50 [00:12<00:34, 1.08it/s] 28%|██▊ | 14/50 [00:12<00:33, 1.08it/s] 30%|███ | 15/50 [00:13<00:32, 1.08it/s] 32%|███▏ | 16/50 [00:14<00:31, 1.08it/s] 34%|███▍ | 17/50 [00:15<00:30, 1.08it/s] 36%|███▌ | 18/50 [00:16<00:29, 1.08it/s] 38%|███▊ | 19/50 [00:17<00:28, 1.08it/s] 40%|████ | 20/50 [00:18<00:27, 1.08it/s] 42%|████▏ | 21/50 [00:19<00:26, 1.08it/s] 44%|████▍ | 22/50 [00:20<00:25, 1.08it/s] 46%|████▌ | 23/50 [00:21<00:25, 1.08it/s] 48%|████▊ | 24/50 [00:22<00:24, 1.08it/s] 50%|█████ | 25/50 [00:23<00:23, 1.08it/s] 52%|█████▏ | 26/50 [00:24<00:22, 1.08it/s] 54%|█████▍ | 27/50 [00:25<00:21, 1.08it/s] 56%|█████▌ | 28/50 [00:25<00:20, 1.08it/s] 58%|█████▊ | 29/50 [00:26<00:19, 1.08it/s] 60%|██████ | 30/50 [00:27<00:18, 1.08it/s] 62%|██████▏ | 31/50 [00:28<00:17, 1.08it/s] 64%|██████▍ | 32/50 [00:29<00:16, 1.08it/s] 66%|██████▌ | 33/50 [00:30<00:15, 1.08it/s] 68%|██████▊ | 34/50 [00:31<00:14, 1.07it/s] 70%|███████ | 35/50 [00:32<00:13, 1.07it/s] 72%|███████▏ | 36/50 [00:33<00:13, 1.08it/s] 74%|███████▍ | 37/50 [00:34<00:12, 1.08it/s] 76%|███████▌ | 38/50 [00:35<00:11, 1.08it/s] 78%|███████▊ | 39/50 [00:36<00:10, 1.08it/s] 80%|████████ | 40/50 [00:37<00:09, 1.08it/s] 82%|████████▏ | 41/50 [00:38<00:08, 1.07it/s] 84%|████████▍ | 42/50 [00:38<00:07, 1.07it/s] 86%|████████▌ | 43/50 [00:39<00:06, 1.08it/s] 88%|████████▊ | 44/50 [00:40<00:05, 1.07it/s] 90%|█████████ | 45/50 [00:41<00:04, 1.07it/s] 92%|█████████▏| 46/50 [00:42<00:03, 1.07it/s] 94%|█████████▍| 47/50 [00:43<00:02, 1.08it/s] 96%|█████████▌| 48/50 [00:44<00:01, 1.07it/s] 98%|█████████▊| 49/50 [00:45<00:00, 1.07it/s] 100%|██████████| 50/50 [00:46<00:00, 1.07it/s] 100%|██████████| 50/50 [00:46<00:00, 1.08it/s]
Prediction
eledah/sdxl-lora-character-chamran:9ee813be18f9e2dc0836789ede7e93f0c53521ddc32067bdef51d2862767a85dID8nrv90yr39rgm0cj7k78bwwc6cStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- by Rembrandt van Rijn, chamran, confident stance, Direct light, Film grain
- refine
- no_refiner
- scheduler
- DDIM
- lora_scale
- 0.75
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- bad lighting, low-quality, deformed, text, poorly drawn, holding camera, bad art, bad angle, boring, low-resolution, worst quality, bad composition, disfigured
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "by Rembrandt van Rijn, chamran, confident stance, Direct light, Film grain", "refine": "no_refiner", "scheduler": "DDIM", "lora_scale": 0.75, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "bad lighting, low-quality, deformed, text, poorly drawn, holding camera, bad art, bad angle, boring, low-resolution, worst quality, bad composition, disfigured", "prompt_strength": 0.8, "num_inference_steps": 50 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run eledah/sdxl-lora-character-chamran using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "eledah/sdxl-lora-character-chamran:9ee813be18f9e2dc0836789ede7e93f0c53521ddc32067bdef51d2862767a85d", { input: { width: 1024, height: 1024, prompt: "by Rembrandt van Rijn, chamran, confident stance, Direct light, Film grain", refine: "no_refiner", scheduler: "DDIM", lora_scale: 0.75, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "bad lighting, low-quality, deformed, text, poorly drawn, holding camera, bad art, bad angle, boring, low-resolution, worst quality, bad composition, disfigured", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run eledah/sdxl-lora-character-chamran using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "eledah/sdxl-lora-character-chamran:9ee813be18f9e2dc0836789ede7e93f0c53521ddc32067bdef51d2862767a85d", input={ "width": 1024, "height": 1024, "prompt": "by Rembrandt van Rijn, chamran, confident stance, Direct light, Film grain", "refine": "no_refiner", "scheduler": "DDIM", "lora_scale": 0.75, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "bad lighting, low-quality, deformed, text, poorly drawn, holding camera, bad art, bad angle, boring, low-resolution, worst quality, bad composition, disfigured", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run eledah/sdxl-lora-character-chamran 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": "eledah/sdxl-lora-character-chamran:9ee813be18f9e2dc0836789ede7e93f0c53521ddc32067bdef51d2862767a85d", "input": { "width": 1024, "height": 1024, "prompt": "by Rembrandt van Rijn, chamran, confident stance, Direct light, Film grain", "refine": "no_refiner", "scheduler": "DDIM", "lora_scale": 0.75, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "bad lighting, low-quality, deformed, text, poorly drawn, holding camera, bad art, bad angle, boring, low-resolution, worst quality, bad composition, disfigured", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-09-29T08:04:14.776004Z", "created_at": "2024-09-29T08:04:01.690000Z", "data_removed": false, "error": null, "id": "8nrv90yr39rgm0cj7k78bwwc6c", "input": { "width": 1024, "height": 1024, "prompt": "by Rembrandt van Rijn, chamran, confident stance, Direct light, Film grain", "refine": "no_refiner", "scheduler": "DDIM", "lora_scale": 0.75, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "bad lighting, low-quality, deformed, text, poorly drawn, holding camera, bad art, bad angle, boring, low-resolution, worst quality, bad composition, disfigured", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 19622\nskipping loading .. weights already loaded\nPrompt: by Rembrandt van Rijn, <s0><s1>, confident stance, Direct light, Film grain\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:11, 4.30it/s]\n 4%|▍ | 2/50 [00:00<00:11, 4.28it/s]\n 6%|▌ | 3/50 [00:00<00:11, 4.26it/s]\n 8%|▊ | 4/50 [00:00<00:10, 4.26it/s]\n 10%|█ | 5/50 [00:01<00:10, 4.25it/s]\n 12%|█▏ | 6/50 [00:01<00:10, 4.24it/s]\n 14%|█▍ | 7/50 [00:01<00:10, 4.24it/s]\n 16%|█▌ | 8/50 [00:01<00:09, 4.24it/s]\n 18%|█▊ | 9/50 [00:02<00:09, 4.24it/s]\n 20%|██ | 10/50 [00:02<00:09, 4.24it/s]\n 22%|██▏ | 11/50 [00:02<00:09, 4.24it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.23it/s]\n 26%|██▌ | 13/50 [00:03<00:08, 4.23it/s]\n 28%|██▊ | 14/50 [00:03<00:08, 4.23it/s]\n 30%|███ | 15/50 [00:03<00:08, 4.23it/s]\n 32%|███▏ | 16/50 [00:03<00:08, 4.23it/s]\n 34%|███▍ | 17/50 [00:04<00:07, 4.23it/s]\n 36%|███▌ | 18/50 [00:04<00:07, 4.23it/s]\n 38%|███▊ | 19/50 [00:04<00:07, 4.23it/s]\n 40%|████ | 20/50 [00:04<00:07, 4.23it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.23it/s]\n 44%|████▍ | 22/50 [00:05<00:06, 4.23it/s]\n 46%|████▌ | 23/50 [00:05<00:06, 4.23it/s]\n 48%|████▊ | 24/50 [00:05<00:06, 4.23it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.23it/s]\n 52%|█████▏ | 26/50 [00:06<00:05, 4.22it/s]\n 54%|█████▍ | 27/50 [00:06<00:05, 4.22it/s]\n 56%|█████▌ | 28/50 [00:06<00:05, 4.22it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.22it/s]\n 60%|██████ | 30/50 [00:07<00:04, 4.22it/s]\n 62%|██████▏ | 31/50 [00:07<00:04, 4.22it/s]\n 64%|██████▍ | 32/50 [00:07<00:04, 4.22it/s]\n 66%|██████▌ | 33/50 [00:07<00:04, 4.22it/s]\n 68%|██████▊ | 34/50 [00:08<00:03, 4.22it/s]\n 70%|███████ | 35/50 [00:08<00:03, 4.21it/s]\n 72%|███████▏ | 36/50 [00:08<00:03, 4.21it/s]\n 74%|███████▍ | 37/50 [00:08<00:03, 4.22it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.21it/s]\n 78%|███████▊ | 39/50 [00:09<00:02, 4.21it/s]\n 80%|████████ | 40/50 [00:09<00:02, 4.21it/s]\n 82%|████████▏ | 41/50 [00:09<00:02, 4.21it/s]\n 84%|████████▍ | 42/50 [00:09<00:01, 4.21it/s]\n 86%|████████▌ | 43/50 [00:10<00:01, 4.21it/s]\n 88%|████████▊ | 44/50 [00:10<00:01, 4.21it/s]\n 90%|█████████ | 45/50 [00:10<00:01, 4.21it/s]\n 92%|█████████▏| 46/50 [00:10<00:00, 4.22it/s]\n 94%|█████████▍| 47/50 [00:11<00:00, 4.22it/s]\n 96%|█████████▌| 48/50 [00:11<00:00, 4.22it/s]\n 98%|█████████▊| 49/50 [00:11<00:00, 4.22it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.21it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.23it/s]", "metrics": { "predict_time": 13.048943412, "total_time": 13.086004 }, "output": [ "https://replicate.delivery/pbxt/uEsefuavJ4nm9kfl5Gw6Oy7thmHaOQiKHFsGaOSeylA4fdNcC/out-0.png" ], "started_at": "2024-09-29T08:04:01.727061Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/8nrv90yr39rgm0cj7k78bwwc6c", "cancel": "https://api.replicate.com/v1/predictions/8nrv90yr39rgm0cj7k78bwwc6c/cancel" }, "version": "9ee813be18f9e2dc0836789ede7e93f0c53521ddc32067bdef51d2862767a85d" }
Generated inUsing seed: 19622 skipping loading .. weights already loaded Prompt: by Rembrandt van Rijn, <s0><s1>, confident stance, Direct light, Film grain txt2img mode 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:11, 4.30it/s] 4%|▍ | 2/50 [00:00<00:11, 4.28it/s] 6%|▌ | 3/50 [00:00<00:11, 4.26it/s] 8%|▊ | 4/50 [00:00<00:10, 4.26it/s] 10%|█ | 5/50 [00:01<00:10, 4.25it/s] 12%|█▏ | 6/50 [00:01<00:10, 4.24it/s] 14%|█▍ | 7/50 [00:01<00:10, 4.24it/s] 16%|█▌ | 8/50 [00:01<00:09, 4.24it/s] 18%|█▊ | 9/50 [00:02<00:09, 4.24it/s] 20%|██ | 10/50 [00:02<00:09, 4.24it/s] 22%|██▏ | 11/50 [00:02<00:09, 4.24it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.23it/s] 26%|██▌ | 13/50 [00:03<00:08, 4.23it/s] 28%|██▊ | 14/50 [00:03<00:08, 4.23it/s] 30%|███ | 15/50 [00:03<00:08, 4.23it/s] 32%|███▏ | 16/50 [00:03<00:08, 4.23it/s] 34%|███▍ | 17/50 [00:04<00:07, 4.23it/s] 36%|███▌ | 18/50 [00:04<00:07, 4.23it/s] 38%|███▊ | 19/50 [00:04<00:07, 4.23it/s] 40%|████ | 20/50 [00:04<00:07, 4.23it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.23it/s] 44%|████▍ | 22/50 [00:05<00:06, 4.23it/s] 46%|████▌ | 23/50 [00:05<00:06, 4.23it/s] 48%|████▊ | 24/50 [00:05<00:06, 4.23it/s] 50%|█████ | 25/50 [00:05<00:05, 4.23it/s] 52%|█████▏ | 26/50 [00:06<00:05, 4.22it/s] 54%|█████▍ | 27/50 [00:06<00:05, 4.22it/s] 56%|█████▌ | 28/50 [00:06<00:05, 4.22it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.22it/s] 60%|██████ | 30/50 [00:07<00:04, 4.22it/s] 62%|██████▏ | 31/50 [00:07<00:04, 4.22it/s] 64%|██████▍ | 32/50 [00:07<00:04, 4.22it/s] 66%|██████▌ | 33/50 [00:07<00:04, 4.22it/s] 68%|██████▊ | 34/50 [00:08<00:03, 4.22it/s] 70%|███████ | 35/50 [00:08<00:03, 4.21it/s] 72%|███████▏ | 36/50 [00:08<00:03, 4.21it/s] 74%|███████▍ | 37/50 [00:08<00:03, 4.22it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.21it/s] 78%|███████▊ | 39/50 [00:09<00:02, 4.21it/s] 80%|████████ | 40/50 [00:09<00:02, 4.21it/s] 82%|████████▏ | 41/50 [00:09<00:02, 4.21it/s] 84%|████████▍ | 42/50 [00:09<00:01, 4.21it/s] 86%|████████▌ | 43/50 [00:10<00:01, 4.21it/s] 88%|████████▊ | 44/50 [00:10<00:01, 4.21it/s] 90%|█████████ | 45/50 [00:10<00:01, 4.21it/s] 92%|█████████▏| 46/50 [00:10<00:00, 4.22it/s] 94%|█████████▍| 47/50 [00:11<00:00, 4.22it/s] 96%|█████████▌| 48/50 [00:11<00:00, 4.22it/s] 98%|█████████▊| 49/50 [00:11<00:00, 4.22it/s] 100%|██████████| 50/50 [00:11<00:00, 4.21it/s] 100%|██████████| 50/50 [00:11<00:00, 4.23it/s]
Prediction
eledah/sdxl-lora-character-chamran:9ee813be18f9e2dc0836789ede7e93f0c53521ddc32067bdef51d2862767a85dIDsq8fbrb39drgp0cj7k7rpbkjg4StatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- fashion art designed by Davide Sorrenti, ripped chamran, 😎, Earbuds, Wide view, Fashion photography, raw style, documentary
- refine
- no_refiner
- scheduler
- DDIM
- lora_scale
- 0.75
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- bad lighting, low-quality, deformed, text, poorly drawn, holding camera, bad art, bad angle, boring, low-resolution, worst quality, bad composition, disfigured
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "fashion art designed by Davide Sorrenti, ripped chamran, 😎, Earbuds, Wide view, Fashion photography, raw style, documentary", "refine": "no_refiner", "scheduler": "DDIM", "lora_scale": 0.75, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "bad lighting, low-quality, deformed, text, poorly drawn, holding camera, bad art, bad angle, boring, low-resolution, worst quality, bad composition, disfigured", "prompt_strength": 0.8, "num_inference_steps": 50 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run eledah/sdxl-lora-character-chamran using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "eledah/sdxl-lora-character-chamran:9ee813be18f9e2dc0836789ede7e93f0c53521ddc32067bdef51d2862767a85d", { input: { width: 1024, height: 1024, prompt: "fashion art designed by Davide Sorrenti, ripped chamran, 😎, Earbuds, Wide view, Fashion photography, raw style, documentary", refine: "no_refiner", scheduler: "DDIM", lora_scale: 0.75, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "bad lighting, low-quality, deformed, text, poorly drawn, holding camera, bad art, bad angle, boring, low-resolution, worst quality, bad composition, disfigured", prompt_strength: 0.8, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run eledah/sdxl-lora-character-chamran using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "eledah/sdxl-lora-character-chamran:9ee813be18f9e2dc0836789ede7e93f0c53521ddc32067bdef51d2862767a85d", input={ "width": 1024, "height": 1024, "prompt": "fashion art designed by Davide Sorrenti, ripped chamran, 😎, Earbuds, Wide view, Fashion photography, raw style, documentary", "refine": "no_refiner", "scheduler": "DDIM", "lora_scale": 0.75, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "bad lighting, low-quality, deformed, text, poorly drawn, holding camera, bad art, bad angle, boring, low-resolution, worst quality, bad composition, disfigured", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run eledah/sdxl-lora-character-chamran 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": "eledah/sdxl-lora-character-chamran:9ee813be18f9e2dc0836789ede7e93f0c53521ddc32067bdef51d2862767a85d", "input": { "width": 1024, "height": 1024, "prompt": "fashion art designed by Davide Sorrenti, ripped chamran, 😎, Earbuds, Wide view, Fashion photography, raw style, documentary", "refine": "no_refiner", "scheduler": "DDIM", "lora_scale": 0.75, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "bad lighting, low-quality, deformed, text, poorly drawn, holding camera, bad art, bad angle, boring, low-resolution, worst quality, bad composition, disfigured", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-09-29T08:05:46.273651Z", "created_at": "2024-09-29T08:04:37.323000Z", "data_removed": false, "error": null, "id": "sq8fbrb39drgp0cj7k7rpbkjg4", "input": { "width": 1024, "height": 1024, "prompt": "fashion art designed by Davide Sorrenti, ripped chamran, 😎, Earbuds, Wide view, Fashion photography, raw style, documentary", "refine": "no_refiner", "scheduler": "DDIM", "lora_scale": 0.75, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "bad lighting, low-quality, deformed, text, poorly drawn, holding camera, bad art, bad angle, boring, low-resolution, worst quality, bad composition, disfigured", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 2679\nEnsuring enough disk space...\nFree disk space: 1428688801792\nDownloading weights: https://replicate.delivery/pbxt/apUqPhefKyjCs0nRswRc6a6NMBjnQhVqi4q2CdjNrCHtTZdTA/trained_model.tar\n2024-09-29T08:05:26Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/1a7c5c72d2147ecf url=https://replicate.delivery/pbxt/apUqPhefKyjCs0nRswRc6a6NMBjnQhVqi4q2CdjNrCHtTZdTA/trained_model.tar\n2024-09-29T08:05:31Z | INFO | [ Complete ] dest=/src/weights-cache/1a7c5c72d2147ecf size=\"186 MB\" total_elapsed=5.050s url=https://replicate.delivery/pbxt/apUqPhefKyjCs0nRswRc6a6NMBjnQhVqi4q2CdjNrCHtTZdTA/trained_model.tar\nb''\nDownloaded weights in 5.183465003967285 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: fashion art designed by Davide Sorrenti, ripped <s0><s1>, 😎, Earbuds, Wide view, Fashion photography, raw style, documentary\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/torch/nn/modules/conv.py:459: UserWarning: Applied workaround for CuDNN issue, install nvrtc.so (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:80.)\nreturn F.conv2d(input, weight, bias, self.stride,\n/usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights`\ndeprecate(\n 2%|▏ | 1/50 [00:00<00:20, 2.37it/s]\n 4%|▍ | 2/50 [00:00<00:14, 3.21it/s]\n 6%|▌ | 3/50 [00:00<00:13, 3.61it/s]\n 8%|▊ | 4/50 [00:01<00:11, 3.84it/s]\n 10%|█ | 5/50 [00:01<00:11, 3.97it/s]\n 12%|█▏ | 6/50 [00:01<00:10, 4.06it/s]\n 14%|█▍ | 7/50 [00:01<00:10, 4.11it/s]\n 16%|█▌ | 8/50 [00:02<00:10, 4.15it/s]\n 18%|█▊ | 9/50 [00:02<00:09, 4.18it/s]\n 20%|██ | 10/50 [00:02<00:09, 4.20it/s]\n 22%|██▏ | 11/50 [00:02<00:09, 4.21it/s]\n 24%|██▍ | 12/50 [00:03<00:09, 4.21it/s]\n 26%|██▌ | 13/50 [00:03<00:08, 4.22it/s]\n 28%|██▊ | 14/50 [00:03<00:08, 4.22it/s]\n 30%|███ | 15/50 [00:03<00:08, 4.22it/s]\n 32%|███▏ | 16/50 [00:03<00:08, 4.22it/s]\n 34%|███▍ | 17/50 [00:04<00:07, 4.22it/s]\n 36%|███▌ | 18/50 [00:04<00:07, 4.22it/s]\n 38%|███▊ | 19/50 [00:04<00:07, 4.22it/s]\n 40%|████ | 20/50 [00:04<00:07, 4.22it/s]\n 42%|████▏ | 21/50 [00:05<00:06, 4.21it/s]\n 44%|████▍ | 22/50 [00:05<00:06, 4.21it/s]\n 46%|████▌ | 23/50 [00:05<00:06, 4.22it/s]\n 48%|████▊ | 24/50 [00:05<00:06, 4.22it/s]\n 50%|█████ | 25/50 [00:06<00:05, 4.22it/s]\n 52%|█████▏ | 26/50 [00:06<00:05, 4.22it/s]\n 54%|█████▍ | 27/50 [00:06<00:05, 4.21it/s]\n 56%|█████▌ | 28/50 [00:06<00:05, 4.21it/s]\n 58%|█████▊ | 29/50 [00:07<00:04, 4.22it/s]\n 60%|██████ | 30/50 [00:07<00:04, 4.22it/s]\n 62%|██████▏ | 31/50 [00:07<00:04, 4.22it/s]\n 64%|██████▍ | 32/50 [00:07<00:04, 4.22it/s]\n 66%|██████▌ | 33/50 [00:07<00:04, 4.23it/s]\n 68%|██████▊ | 34/50 [00:08<00:03, 4.23it/s]\n 70%|███████ | 35/50 [00:08<00:03, 4.24it/s]\n 72%|███████▏ | 36/50 [00:08<00:03, 4.24it/s]\n 74%|███████▍ | 37/50 [00:08<00:03, 4.24it/s]\n 76%|███████▌ | 38/50 [00:09<00:02, 4.24it/s]\n 78%|███████▊ | 39/50 [00:09<00:02, 4.24it/s]\n 80%|████████ | 40/50 [00:09<00:02, 4.24it/s]\n 82%|████████▏ | 41/50 [00:09<00:02, 4.25it/s]\n 84%|████████▍ | 42/50 [00:10<00:01, 4.25it/s]\n 86%|████████▌ | 43/50 [00:10<00:01, 4.25it/s]\n 88%|████████▊ | 44/50 [00:10<00:01, 4.25it/s]\n 90%|█████████ | 45/50 [00:10<00:01, 4.24it/s]\n 92%|█████████▏| 46/50 [00:11<00:00, 4.25it/s]\n 94%|█████████▍| 47/50 [00:11<00:00, 4.25it/s]\n 96%|█████████▌| 48/50 [00:11<00:00, 4.25it/s]\n 98%|█████████▊| 49/50 [00:11<00:00, 4.24it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.25it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.17it/s]", "metrics": { "predict_time": 19.574498894, "total_time": 68.950651 }, "output": [ "https://replicate.delivery/pbxt/YFpYnFbDhqKaBVUYIKY3L3EgKTSfAByfUqSiYAZFMqqaxrhTA/out-0.png" ], "started_at": "2024-09-29T08:05:26.699153Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/sq8fbrb39drgp0cj7k7rpbkjg4", "cancel": "https://api.replicate.com/v1/predictions/sq8fbrb39drgp0cj7k7rpbkjg4/cancel" }, "version": "9ee813be18f9e2dc0836789ede7e93f0c53521ddc32067bdef51d2862767a85d" }
Generated inUsing seed: 2679 Ensuring enough disk space... Free disk space: 1428688801792 Downloading weights: https://replicate.delivery/pbxt/apUqPhefKyjCs0nRswRc6a6NMBjnQhVqi4q2CdjNrCHtTZdTA/trained_model.tar 2024-09-29T08:05:26Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/1a7c5c72d2147ecf url=https://replicate.delivery/pbxt/apUqPhefKyjCs0nRswRc6a6NMBjnQhVqi4q2CdjNrCHtTZdTA/trained_model.tar 2024-09-29T08:05:31Z | INFO | [ Complete ] dest=/src/weights-cache/1a7c5c72d2147ecf size="186 MB" total_elapsed=5.050s url=https://replicate.delivery/pbxt/apUqPhefKyjCs0nRswRc6a6NMBjnQhVqi4q2CdjNrCHtTZdTA/trained_model.tar b'' Downloaded weights in 5.183465003967285 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: fashion art designed by Davide Sorrenti, ripped <s0><s1>, 😎, Earbuds, Wide view, Fashion photography, raw style, documentary txt2img mode 0%| | 0/50 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/torch/nn/modules/conv.py:459: UserWarning: Applied workaround for CuDNN issue, install nvrtc.so (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:80.) return F.conv2d(input, weight, bias, self.stride, /usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights` deprecate( 2%|▏ | 1/50 [00:00<00:20, 2.37it/s] 4%|▍ | 2/50 [00:00<00:14, 3.21it/s] 6%|▌ | 3/50 [00:00<00:13, 3.61it/s] 8%|▊ | 4/50 [00:01<00:11, 3.84it/s] 10%|█ | 5/50 [00:01<00:11, 3.97it/s] 12%|█▏ | 6/50 [00:01<00:10, 4.06it/s] 14%|█▍ | 7/50 [00:01<00:10, 4.11it/s] 16%|█▌ | 8/50 [00:02<00:10, 4.15it/s] 18%|█▊ | 9/50 [00:02<00:09, 4.18it/s] 20%|██ | 10/50 [00:02<00:09, 4.20it/s] 22%|██▏ | 11/50 [00:02<00:09, 4.21it/s] 24%|██▍ | 12/50 [00:03<00:09, 4.21it/s] 26%|██▌ | 13/50 [00:03<00:08, 4.22it/s] 28%|██▊ | 14/50 [00:03<00:08, 4.22it/s] 30%|███ | 15/50 [00:03<00:08, 4.22it/s] 32%|███▏ | 16/50 [00:03<00:08, 4.22it/s] 34%|███▍ | 17/50 [00:04<00:07, 4.22it/s] 36%|███▌ | 18/50 [00:04<00:07, 4.22it/s] 38%|███▊ | 19/50 [00:04<00:07, 4.22it/s] 40%|████ | 20/50 [00:04<00:07, 4.22it/s] 42%|████▏ | 21/50 [00:05<00:06, 4.21it/s] 44%|████▍ | 22/50 [00:05<00:06, 4.21it/s] 46%|████▌ | 23/50 [00:05<00:06, 4.22it/s] 48%|████▊ | 24/50 [00:05<00:06, 4.22it/s] 50%|█████ | 25/50 [00:06<00:05, 4.22it/s] 52%|█████▏ | 26/50 [00:06<00:05, 4.22it/s] 54%|█████▍ | 27/50 [00:06<00:05, 4.21it/s] 56%|█████▌ | 28/50 [00:06<00:05, 4.21it/s] 58%|█████▊ | 29/50 [00:07<00:04, 4.22it/s] 60%|██████ | 30/50 [00:07<00:04, 4.22it/s] 62%|██████▏ | 31/50 [00:07<00:04, 4.22it/s] 64%|██████▍ | 32/50 [00:07<00:04, 4.22it/s] 66%|██████▌ | 33/50 [00:07<00:04, 4.23it/s] 68%|██████▊ | 34/50 [00:08<00:03, 4.23it/s] 70%|███████ | 35/50 [00:08<00:03, 4.24it/s] 72%|███████▏ | 36/50 [00:08<00:03, 4.24it/s] 74%|███████▍ | 37/50 [00:08<00:03, 4.24it/s] 76%|███████▌ | 38/50 [00:09<00:02, 4.24it/s] 78%|███████▊ | 39/50 [00:09<00:02, 4.24it/s] 80%|████████ | 40/50 [00:09<00:02, 4.24it/s] 82%|████████▏ | 41/50 [00:09<00:02, 4.25it/s] 84%|████████▍ | 42/50 [00:10<00:01, 4.25it/s] 86%|████████▌ | 43/50 [00:10<00:01, 4.25it/s] 88%|████████▊ | 44/50 [00:10<00:01, 4.25it/s] 90%|█████████ | 45/50 [00:10<00:01, 4.24it/s] 92%|█████████▏| 46/50 [00:11<00:00, 4.25it/s] 94%|█████████▍| 47/50 [00:11<00:00, 4.25it/s] 96%|█████████▌| 48/50 [00:11<00:00, 4.25it/s] 98%|█████████▊| 49/50 [00:11<00:00, 4.24it/s] 100%|██████████| 50/50 [00:11<00:00, 4.25it/s] 100%|██████████| 50/50 [00:11<00:00, 4.17it/s]
Want to make some of these yourself?
Run this model