lucataco / sdxl-lightning-multi-controlnet
SDXL lightning mult-controlnet, img2img & inpainting
Prediction
lucataco/sdxl-lightning-multi-controlnet:d5116b11698b41d34c322cbd7b0bf068015e47831af0527de7a178dc59c5f2eeID7pvmfwtbgfqbzivckkuekdqamaStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- A monkey making latte art
- refine
- no_refiner
- scheduler
- K_EULER
- num_outputs
- 1
- controlnet_1
- none
- controlnet_2
- none
- controlnet_3
- none
- guidance_scale
- 0
- apply_watermark
- negative_prompt
- worst quality, low quality
- prompt_strength
- 0.8
- sizing_strategy
- width_height
- controlnet_1_end
- 1
- controlnet_2_end
- 1
- controlnet_3_end
- 1
- controlnet_1_start
- 0
- controlnet_2_start
- 0
- controlnet_3_start
- 0
- num_inference_steps
- 4
- controlnet_1_conditioning_scale
- 0.75
- controlnet_2_conditioning_scale
- 0.75
- controlnet_3_conditioning_scale
- 0.75
{ "width": 1024, "height": 1024, "prompt": "A monkey making latte art", "refine": "no_refiner", "scheduler": "K_EULER", "num_outputs": 1, "controlnet_1": "none", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 0, "apply_watermark": true, "negative_prompt": "worst quality, low quality", "prompt_strength": 0.8, "sizing_strategy": "width_height", "controlnet_1_end": 1, "controlnet_2_end": 1, "controlnet_3_end": 1, "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 4, "controlnet_1_conditioning_scale": 0.75, "controlnet_2_conditioning_scale": 0.75, "controlnet_3_conditioning_scale": 0.75 }
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 lucataco/sdxl-lightning-multi-controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/sdxl-lightning-multi-controlnet:d5116b11698b41d34c322cbd7b0bf068015e47831af0527de7a178dc59c5f2ee", { input: { width: 1024, height: 1024, prompt: "A monkey making latte art", refine: "no_refiner", scheduler: "K_EULER", num_outputs: 1, controlnet_1: "none", controlnet_2: "none", controlnet_3: "none", guidance_scale: 0, apply_watermark: true, negative_prompt: "worst quality, low quality", prompt_strength: 0.8, sizing_strategy: "width_height", controlnet_1_end: 1, controlnet_2_end: 1, controlnet_3_end: 1, controlnet_1_start: 0, controlnet_2_start: 0, controlnet_3_start: 0, num_inference_steps: 4, controlnet_1_conditioning_scale: 0.75, controlnet_2_conditioning_scale: 0.75, controlnet_3_conditioning_scale: 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 replicate
Import the client:import replicate
Run lucataco/sdxl-lightning-multi-controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/sdxl-lightning-multi-controlnet:d5116b11698b41d34c322cbd7b0bf068015e47831af0527de7a178dc59c5f2ee", input={ "width": 1024, "height": 1024, "prompt": "A monkey making latte art", "refine": "no_refiner", "scheduler": "K_EULER", "num_outputs": 1, "controlnet_1": "none", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 0, "apply_watermark": True, "negative_prompt": "worst quality, low quality", "prompt_strength": 0.8, "sizing_strategy": "width_height", "controlnet_1_end": 1, "controlnet_2_end": 1, "controlnet_3_end": 1, "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 4, "controlnet_1_conditioning_scale": 0.75, "controlnet_2_conditioning_scale": 0.75, "controlnet_3_conditioning_scale": 0.75 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run lucataco/sdxl-lightning-multi-controlnet 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": "lucataco/sdxl-lightning-multi-controlnet:d5116b11698b41d34c322cbd7b0bf068015e47831af0527de7a178dc59c5f2ee", "input": { "width": 1024, "height": 1024, "prompt": "A monkey making latte art", "refine": "no_refiner", "scheduler": "K_EULER", "num_outputs": 1, "controlnet_1": "none", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 0, "apply_watermark": true, "negative_prompt": "worst quality, low quality", "prompt_strength": 0.8, "sizing_strategy": "width_height", "controlnet_1_end": 1, "controlnet_2_end": 1, "controlnet_3_end": 1, "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 4, "controlnet_1_conditioning_scale": 0.75, "controlnet_2_conditioning_scale": 0.75, "controlnet_3_conditioning_scale": 0.75 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-02-27T06:45:53.271773Z", "created_at": "2024-02-27T06:45:51.331746Z", "data_removed": false, "error": null, "id": "7pvmfwtbgfqbzivckkuekdqama", "input": { "width": 1024, "height": 1024, "prompt": "A monkey making latte art", "refine": "no_refiner", "scheduler": "K_EULER", "num_outputs": 1, "controlnet_1": "none", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 0, "apply_watermark": true, "negative_prompt": "worst quality, low quality", "prompt_strength": 0.8, "sizing_strategy": "width_height", "controlnet_1_end": 1, "controlnet_2_end": 1, "controlnet_3_end": 1, "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 4, "controlnet_1_conditioning_scale": 0.75, "controlnet_2_conditioning_scale": 0.75, "controlnet_3_conditioning_scale": 0.75 }, "logs": "Using seed: 3660614901\nUsing given dimensions\nresize took: 0.00s\nPrompt: A monkey making latte art\nUsing txt2img pipeline\n 0%| | 0/4 [00:00<?, ?it/s]\n 25%|██▌ | 1/4 [00:00<00:00, 9.16it/s]\n 50%|█████ | 2/4 [00:00<00:00, 9.06it/s]\n 75%|███████▌ | 3/4 [00:00<00:00, 9.02it/s]\n100%|██████████| 4/4 [00:00<00:00, 9.02it/s]\n100%|██████████| 4/4 [00:00<00:00, 9.04it/s]\ninference took: 1.01s\nprediction took: 1.41s", "metrics": { "predict_time": 1.924191, "total_time": 1.940027 }, "output": [ "https://replicate.delivery/pbxt/LyjoffeuFgTjTp9Mj464ensrCWzL3LJw2Zz5fWmwf4sKI3smE/out-0.png" ], "started_at": "2024-02-27T06:45:51.347582Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/7pvmfwtbgfqbzivckkuekdqama", "cancel": "https://api.replicate.com/v1/predictions/7pvmfwtbgfqbzivckkuekdqama/cancel" }, "version": "d5116b11698b41d34c322cbd7b0bf068015e47831af0527de7a178dc59c5f2ee" }
Generated inUsing seed: 3660614901 Using given dimensions resize took: 0.00s Prompt: A monkey making latte art Using txt2img pipeline 0%| | 0/4 [00:00<?, ?it/s] 25%|██▌ | 1/4 [00:00<00:00, 9.16it/s] 50%|█████ | 2/4 [00:00<00:00, 9.06it/s] 75%|███████▌ | 3/4 [00:00<00:00, 9.02it/s] 100%|██████████| 4/4 [00:00<00:00, 9.02it/s] 100%|██████████| 4/4 [00:00<00:00, 9.04it/s] inference took: 1.01s prediction took: 1.41s
Prediction
lucataco/sdxl-lightning-multi-controlnet:d5116b11698b41d34c322cbd7b0bf068015e47831af0527de7a178dc59c5f2eeID56rxbylbcjgp6fkozzwcp75dx4StatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- extreme macro photo of a golden astronaut riding a unicorn statue, in a museum, bokeh, 50mm
- refine
- no_refiner
- scheduler
- K_EULER
- num_outputs
- 1
- controlnet_1
- soft_edge_hed
- controlnet_2
- none
- controlnet_3
- none
- guidance_scale
- 0
- apply_watermark
- negative_prompt
- worst quality, low quality
- prompt_strength
- 0.8
- sizing_strategy
- width_height
- controlnet_1_end
- 1
- controlnet_2_end
- 1
- controlnet_3_end
- 1
- controlnet_1_start
- 0
- controlnet_2_start
- 0
- controlnet_3_start
- 0
- num_inference_steps
- 4
- controlnet_1_conditioning_scale
- 0.75
- controlnet_2_conditioning_scale
- 0.75
- controlnet_3_conditioning_scale
- 0.75
{ "width": 1024, "height": 1024, "prompt": "extreme macro photo of a golden astronaut riding a unicorn statue, in a museum, bokeh, 50mm", "refine": "no_refiner", "scheduler": "K_EULER", "num_outputs": 1, "controlnet_1": "soft_edge_hed", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 0, "apply_watermark": true, "negative_prompt": "worst quality, low quality", "prompt_strength": 0.8, "sizing_strategy": "width_height", "controlnet_1_end": 1, "controlnet_2_end": 1, "controlnet_3_end": 1, "controlnet_1_image": "https://replicate.delivery/pbxt/KTWobEZiPRKJanaeqp2FqDfppvecWkJIZARLqRU3F0U54dtl/astro-on-horse.png", "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 4, "controlnet_1_conditioning_scale": 0.75, "controlnet_2_conditioning_scale": 0.75, "controlnet_3_conditioning_scale": 0.75 }
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 lucataco/sdxl-lightning-multi-controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/sdxl-lightning-multi-controlnet:d5116b11698b41d34c322cbd7b0bf068015e47831af0527de7a178dc59c5f2ee", { input: { width: 1024, height: 1024, prompt: "extreme macro photo of a golden astronaut riding a unicorn statue, in a museum, bokeh, 50mm", refine: "no_refiner", scheduler: "K_EULER", num_outputs: 1, controlnet_1: "soft_edge_hed", controlnet_2: "none", controlnet_3: "none", guidance_scale: 0, apply_watermark: true, negative_prompt: "worst quality, low quality", prompt_strength: 0.8, sizing_strategy: "width_height", controlnet_1_end: 1, controlnet_2_end: 1, controlnet_3_end: 1, controlnet_1_image: "https://replicate.delivery/pbxt/KTWobEZiPRKJanaeqp2FqDfppvecWkJIZARLqRU3F0U54dtl/astro-on-horse.png", controlnet_1_start: 0, controlnet_2_start: 0, controlnet_3_start: 0, num_inference_steps: 4, controlnet_1_conditioning_scale: 0.75, controlnet_2_conditioning_scale: 0.75, controlnet_3_conditioning_scale: 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 replicate
Import the client:import replicate
Run lucataco/sdxl-lightning-multi-controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/sdxl-lightning-multi-controlnet:d5116b11698b41d34c322cbd7b0bf068015e47831af0527de7a178dc59c5f2ee", input={ "width": 1024, "height": 1024, "prompt": "extreme macro photo of a golden astronaut riding a unicorn statue, in a museum, bokeh, 50mm", "refine": "no_refiner", "scheduler": "K_EULER", "num_outputs": 1, "controlnet_1": "soft_edge_hed", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 0, "apply_watermark": True, "negative_prompt": "worst quality, low quality", "prompt_strength": 0.8, "sizing_strategy": "width_height", "controlnet_1_end": 1, "controlnet_2_end": 1, "controlnet_3_end": 1, "controlnet_1_image": "https://replicate.delivery/pbxt/KTWobEZiPRKJanaeqp2FqDfppvecWkJIZARLqRU3F0U54dtl/astro-on-horse.png", "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 4, "controlnet_1_conditioning_scale": 0.75, "controlnet_2_conditioning_scale": 0.75, "controlnet_3_conditioning_scale": 0.75 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run lucataco/sdxl-lightning-multi-controlnet 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": "lucataco/sdxl-lightning-multi-controlnet:d5116b11698b41d34c322cbd7b0bf068015e47831af0527de7a178dc59c5f2ee", "input": { "width": 1024, "height": 1024, "prompt": "extreme macro photo of a golden astronaut riding a unicorn statue, in a museum, bokeh, 50mm", "refine": "no_refiner", "scheduler": "K_EULER", "num_outputs": 1, "controlnet_1": "soft_edge_hed", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 0, "apply_watermark": true, "negative_prompt": "worst quality, low quality", "prompt_strength": 0.8, "sizing_strategy": "width_height", "controlnet_1_end": 1, "controlnet_2_end": 1, "controlnet_3_end": 1, "controlnet_1_image": "https://replicate.delivery/pbxt/KTWobEZiPRKJanaeqp2FqDfppvecWkJIZARLqRU3F0U54dtl/astro-on-horse.png", "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 4, "controlnet_1_conditioning_scale": 0.75, "controlnet_2_conditioning_scale": 0.75, "controlnet_3_conditioning_scale": 0.75 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-02-27T06:47:01.532833Z", "created_at": "2024-02-27T06:46:58.234118Z", "data_removed": false, "error": null, "id": "56rxbylbcjgp6fkozzwcp75dx4", "input": { "width": 1024, "height": 1024, "prompt": "extreme macro photo of a golden astronaut riding a unicorn statue, in a museum, bokeh, 50mm", "refine": "no_refiner", "scheduler": "K_EULER", "num_outputs": 1, "controlnet_1": "soft_edge_hed", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 0, "apply_watermark": true, "negative_prompt": "worst quality, low quality", "prompt_strength": 0.8, "sizing_strategy": "width_height", "controlnet_1_end": 1, "controlnet_2_end": 1, "controlnet_3_end": 1, "controlnet_1_image": "https://replicate.delivery/pbxt/KTWobEZiPRKJanaeqp2FqDfppvecWkJIZARLqRU3F0U54dtl/astro-on-horse.png", "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 4, "controlnet_1_conditioning_scale": 0.75, "controlnet_2_conditioning_scale": 0.75, "controlnet_3_conditioning_scale": 0.75 }, "logs": "Using seed: 3924493178\nUsing given dimensions\nresize took: 0.03s\nPrompt: extreme macro photo of a golden astronaut riding a unicorn statue, in a museum, bokeh, 50mm\nProcessing image with soft_edge_hed\ncontrolnet preprocess took: 0.58s\nUsing txt2img + controlnet pipeline\nLoading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s]\nLoading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 15134.09it/s]\nYou have 1 ControlNets and you have passed 1 prompts. The conditionings will be fixed across the prompts.\n 0%| | 0/4 [00:00<?, ?it/s]\n 25%|██▌ | 1/4 [00:00<00:00, 6.19it/s]\n 50%|█████ | 2/4 [00:00<00:00, 6.16it/s]\n 75%|███████▌ | 3/4 [00:00<00:00, 6.14it/s]\n100%|██████████| 4/4 [00:00<00:00, 6.14it/s]\n100%|██████████| 4/4 [00:00<00:00, 6.14it/s]\ninference took: 1.25s\nprediction took: 2.34s", "metrics": { "predict_time": 3.286964, "total_time": 3.298715 }, "output": [ "https://replicate.delivery/pbxt/uWqiRRbTlezCGyfu5ziSaIpsiuzmLGqukIJQeWGztkRJ7m1kA/control-0.png", "https://replicate.delivery/pbxt/X0rtJUsEeXyOekN1yAEqeJLvSQegmKQoeroNC9Hzef6myuZNJA/out-0.png" ], "started_at": "2024-02-27T06:46:58.245869Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/56rxbylbcjgp6fkozzwcp75dx4", "cancel": "https://api.replicate.com/v1/predictions/56rxbylbcjgp6fkozzwcp75dx4/cancel" }, "version": "d5116b11698b41d34c322cbd7b0bf068015e47831af0527de7a178dc59c5f2ee" }
Generated inUsing seed: 3924493178 Using given dimensions resize took: 0.03s Prompt: extreme macro photo of a golden astronaut riding a unicorn statue, in a museum, bokeh, 50mm Processing image with soft_edge_hed controlnet preprocess took: 0.58s Using txt2img + controlnet pipeline Loading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s] Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 15134.09it/s] You have 1 ControlNets and you have passed 1 prompts. The conditionings will be fixed across the prompts. 0%| | 0/4 [00:00<?, ?it/s] 25%|██▌ | 1/4 [00:00<00:00, 6.19it/s] 50%|█████ | 2/4 [00:00<00:00, 6.16it/s] 75%|███████▌ | 3/4 [00:00<00:00, 6.14it/s] 100%|██████████| 4/4 [00:00<00:00, 6.14it/s] 100%|██████████| 4/4 [00:00<00:00, 6.14it/s] inference took: 1.25s prediction took: 2.34s
Prediction
lucataco/sdxl-lightning-multi-controlnet:d5116b11698b41d34c322cbd7b0bf068015e47831af0527de7a178dc59c5f2eeIDeinq5ntbkgrvquihdvi6vyzdoeStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- The 90s, a beautiful woman with a radiant smile and long hair, dressed in summer attire
- refine
- no_refiner
- scheduler
- K_EULER
- num_outputs
- 1
- controlnet_1
- none
- controlnet_2
- none
- controlnet_3
- none
- guidance_scale
- 0
- apply_watermark
- negative_prompt
- worst quality, low quality
- prompt_strength
- 0.8
- sizing_strategy
- width_height
- controlnet_1_end
- 1
- controlnet_2_end
- 1
- controlnet_3_end
- 1
- controlnet_1_start
- 0
- controlnet_2_start
- 0
- controlnet_3_start
- 0
- num_inference_steps
- 4
- controlnet_1_conditioning_scale
- 0.75
- controlnet_2_conditioning_scale
- 0.75
- controlnet_3_conditioning_scale
- 0.75
{ "width": 1024, "height": 1024, "prompt": "The 90s, a beautiful woman with a radiant smile and long hair, dressed in summer attire", "refine": "no_refiner", "scheduler": "K_EULER", "num_outputs": 1, "controlnet_1": "none", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 0, "apply_watermark": true, "negative_prompt": "worst quality, low quality", "prompt_strength": 0.8, "sizing_strategy": "width_height", "controlnet_1_end": 1, "controlnet_2_end": 1, "controlnet_3_end": 1, "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 4, "controlnet_1_conditioning_scale": 0.75, "controlnet_2_conditioning_scale": 0.75, "controlnet_3_conditioning_scale": 0.75 }
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 lucataco/sdxl-lightning-multi-controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/sdxl-lightning-multi-controlnet:d5116b11698b41d34c322cbd7b0bf068015e47831af0527de7a178dc59c5f2ee", { input: { width: 1024, height: 1024, prompt: "The 90s, a beautiful woman with a radiant smile and long hair, dressed in summer attire", refine: "no_refiner", scheduler: "K_EULER", num_outputs: 1, controlnet_1: "none", controlnet_2: "none", controlnet_3: "none", guidance_scale: 0, apply_watermark: true, negative_prompt: "worst quality, low quality", prompt_strength: 0.8, sizing_strategy: "width_height", controlnet_1_end: 1, controlnet_2_end: 1, controlnet_3_end: 1, controlnet_1_start: 0, controlnet_2_start: 0, controlnet_3_start: 0, num_inference_steps: 4, controlnet_1_conditioning_scale: 0.75, controlnet_2_conditioning_scale: 0.75, controlnet_3_conditioning_scale: 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 replicate
Import the client:import replicate
Run lucataco/sdxl-lightning-multi-controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/sdxl-lightning-multi-controlnet:d5116b11698b41d34c322cbd7b0bf068015e47831af0527de7a178dc59c5f2ee", input={ "width": 1024, "height": 1024, "prompt": "The 90s, a beautiful woman with a radiant smile and long hair, dressed in summer attire", "refine": "no_refiner", "scheduler": "K_EULER", "num_outputs": 1, "controlnet_1": "none", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 0, "apply_watermark": True, "negative_prompt": "worst quality, low quality", "prompt_strength": 0.8, "sizing_strategy": "width_height", "controlnet_1_end": 1, "controlnet_2_end": 1, "controlnet_3_end": 1, "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 4, "controlnet_1_conditioning_scale": 0.75, "controlnet_2_conditioning_scale": 0.75, "controlnet_3_conditioning_scale": 0.75 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run lucataco/sdxl-lightning-multi-controlnet 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": "lucataco/sdxl-lightning-multi-controlnet:d5116b11698b41d34c322cbd7b0bf068015e47831af0527de7a178dc59c5f2ee", "input": { "width": 1024, "height": 1024, "prompt": "The 90s, a beautiful woman with a radiant smile and long hair, dressed in summer attire", "refine": "no_refiner", "scheduler": "K_EULER", "num_outputs": 1, "controlnet_1": "none", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 0, "apply_watermark": true, "negative_prompt": "worst quality, low quality", "prompt_strength": 0.8, "sizing_strategy": "width_height", "controlnet_1_end": 1, "controlnet_2_end": 1, "controlnet_3_end": 1, "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 4, "controlnet_1_conditioning_scale": 0.75, "controlnet_2_conditioning_scale": 0.75, "controlnet_3_conditioning_scale": 0.75 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-02-27T06:49:11.130282Z", "created_at": "2024-02-27T06:49:09.152760Z", "data_removed": false, "error": null, "id": "einq5ntbkgrvquihdvi6vyzdoe", "input": { "width": 1024, "height": 1024, "prompt": "The 90s, a beautiful woman with a radiant smile and long hair, dressed in summer attire", "refine": "no_refiner", "scheduler": "K_EULER", "num_outputs": 1, "controlnet_1": "none", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 0, "apply_watermark": true, "negative_prompt": "worst quality, low quality", "prompt_strength": 0.8, "sizing_strategy": "width_height", "controlnet_1_end": 1, "controlnet_2_end": 1, "controlnet_3_end": 1, "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 4, "controlnet_1_conditioning_scale": 0.75, "controlnet_2_conditioning_scale": 0.75, "controlnet_3_conditioning_scale": 0.75 }, "logs": "Using seed: 1114593514\nUsing given dimensions\nresize took: 0.00s\nPrompt: The 90s, a beautiful woman with a radiant smile and long hair, dressed in summer attire\nUsing txt2img pipeline\n 0%| | 0/4 [00:00<?, ?it/s]\n 25%|██▌ | 1/4 [00:00<00:00, 9.15it/s]\n 50%|█████ | 2/4 [00:00<00:00, 9.07it/s]\n 75%|███████▌ | 3/4 [00:00<00:00, 9.03it/s]\n100%|██████████| 4/4 [00:00<00:00, 9.00it/s]\n100%|██████████| 4/4 [00:00<00:00, 9.02it/s]\ninference took: 1.02s\nprediction took: 1.44s", "metrics": { "predict_time": 1.959136, "total_time": 1.977522 }, "output": [ "https://replicate.delivery/pbxt/P9pvO6rpXs4wDpzPkCebbQkassehZa7SGik0t6rDDMHmfm1kA/out-0.png" ], "started_at": "2024-02-27T06:49:09.171146Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/einq5ntbkgrvquihdvi6vyzdoe", "cancel": "https://api.replicate.com/v1/predictions/einq5ntbkgrvquihdvi6vyzdoe/cancel" }, "version": "d5116b11698b41d34c322cbd7b0bf068015e47831af0527de7a178dc59c5f2ee" }
Generated inUsing seed: 1114593514 Using given dimensions resize took: 0.00s Prompt: The 90s, a beautiful woman with a radiant smile and long hair, dressed in summer attire Using txt2img pipeline 0%| | 0/4 [00:00<?, ?it/s] 25%|██▌ | 1/4 [00:00<00:00, 9.15it/s] 50%|█████ | 2/4 [00:00<00:00, 9.07it/s] 75%|███████▌ | 3/4 [00:00<00:00, 9.03it/s] 100%|██████████| 4/4 [00:00<00:00, 9.00it/s] 100%|██████████| 4/4 [00:00<00:00, 9.02it/s] inference took: 1.02s prediction took: 1.44s
Want to make some of these yourself?
Run this model