fofr / realvisxl-v3-multi-controlnet-lora
RealVisXl V3 with multi-controlnet, lora loading, img2img, inpainting
Prediction
fofr/realvisxl-v3-multi-controlnet-lora:90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daadeIDfz7gt5tbzgesm2yrdue2jo7t7yStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 768
- height
- 768
- prompt
- A detailed photo of an obsidian statue of an astronaut riding a unicorn, bokeh, museum background
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.8
- num_outputs
- 1
- controlnet_1
- soft_edge_hed
- controlnet_2
- none
- controlnet_3
- none
- guidance_scale
- 7.5
- apply_watermark
- 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
- 30
- controlnet_1_conditioning_scale
- 0.8
- controlnet_2_conditioning_scale
- 0.8
- controlnet_3_conditioning_scale
- 0.75
{ "width": 768, "height": 768, "prompt": "A detailed photo of an obsidian statue of an astronaut riding a unicorn, bokeh, museum background", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "controlnet_1": "soft_edge_hed", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 7.5, "apply_watermark": false, "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/JsfCQE8k1lsCinW1yo76yKMQe6R5MRt9WLL3H5T5Ypc5wasq/020e656d-0c71-45c3-a7f5-1facf7d52d4f.png", "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 30, "controlnet_1_conditioning_scale": 0.8, "controlnet_2_conditioning_scale": 0.8, "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"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run fofr/realvisxl-v3-multi-controlnet-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/realvisxl-v3-multi-controlnet-lora:90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daade", { input: { width: 768, height: 768, prompt: "A detailed photo of an obsidian statue of an astronaut riding a unicorn, bokeh, museum background", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.8, num_outputs: 1, controlnet_1: "soft_edge_hed", controlnet_2: "none", controlnet_3: "none", guidance_scale: 7.5, apply_watermark: false, 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/JsfCQE8k1lsCinW1yo76yKMQe6R5MRt9WLL3H5T5Ypc5wasq/020e656d-0c71-45c3-a7f5-1facf7d52d4f.png", controlnet_1_start: 0, controlnet_2_start: 0, controlnet_3_start: 0, num_inference_steps: 30, controlnet_1_conditioning_scale: 0.8, controlnet_2_conditioning_scale: 0.8, 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 fofr/realvisxl-v3-multi-controlnet-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/realvisxl-v3-multi-controlnet-lora:90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daade", input={ "width": 768, "height": 768, "prompt": "A detailed photo of an obsidian statue of an astronaut riding a unicorn, bokeh, museum background", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "controlnet_1": "soft_edge_hed", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 7.5, "apply_watermark": False, "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/JsfCQE8k1lsCinW1yo76yKMQe6R5MRt9WLL3H5T5Ypc5wasq/020e656d-0c71-45c3-a7f5-1facf7d52d4f.png", "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 30, "controlnet_1_conditioning_scale": 0.8, "controlnet_2_conditioning_scale": 0.8, "controlnet_3_conditioning_scale": 0.75 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run fofr/realvisxl-v3-multi-controlnet-lora 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": "fofr/realvisxl-v3-multi-controlnet-lora:90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daade", "input": { "width": 768, "height": 768, "prompt": "A detailed photo of an obsidian statue of an astronaut riding a unicorn, bokeh, museum background", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "controlnet_1": "soft_edge_hed", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 7.5, "apply_watermark": false, "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/JsfCQE8k1lsCinW1yo76yKMQe6R5MRt9WLL3H5T5Ypc5wasq/020e656d-0c71-45c3-a7f5-1facf7d52d4f.png", "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 30, "controlnet_1_conditioning_scale": 0.8, "controlnet_2_conditioning_scale": 0.8, "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": "2024-01-05T14:59:55.290339Z", "created_at": "2024-01-05T14:59:46.178387Z", "data_removed": false, "error": null, "id": "fz7gt5tbzgesm2yrdue2jo7t7y", "input": { "width": 768, "height": 768, "prompt": "A detailed photo of an obsidian statue of an astronaut riding a unicorn, bokeh, museum background", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "controlnet_1": "soft_edge_hed", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 7.5, "apply_watermark": false, "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/JsfCQE8k1lsCinW1yo76yKMQe6R5MRt9WLL3H5T5Ypc5wasq/020e656d-0c71-45c3-a7f5-1facf7d52d4f.png", "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 30, "controlnet_1_conditioning_scale": 0.8, "controlnet_2_conditioning_scale": 0.8, "controlnet_3_conditioning_scale": 0.75 }, "logs": "Using seed: 43888\nUsing given dimensions\nresize took: 0.02s\nPrompt: A detailed photo of an obsidian statue of an astronaut riding a unicorn, bokeh, museum background\nProcessing image with soft_edge_hed\ncontrolnet preprocess took: 0.40s\nUsing txt2img + controlnet pipeline\nLoading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s]\nLoading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 14739.02it/s]\nYou have 1 ControlNets and you have passed 1 prompts. The conditionings will be fixed across the prompts.\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:06, 4.62it/s]\n 7%|▋ | 2/30 [00:00<00:06, 4.63it/s]\n 10%|█ | 3/30 [00:00<00:05, 4.63it/s]\n 13%|█▎ | 4/30 [00:00<00:05, 4.62it/s]\n 17%|█▋ | 5/30 [00:01<00:05, 4.62it/s]\n 20%|██ | 6/30 [00:01<00:05, 4.62it/s]\n 23%|██▎ | 7/30 [00:01<00:04, 4.62it/s]\n 27%|██▋ | 8/30 [00:01<00:04, 4.62it/s]\n 30%|███ | 9/30 [00:01<00:04, 4.61it/s]\n 33%|███▎ | 10/30 [00:02<00:04, 4.62it/s]\n 37%|███▋ | 11/30 [00:02<00:04, 4.62it/s]\n 40%|████ | 12/30 [00:02<00:03, 4.62it/s]\n 43%|████▎ | 13/30 [00:02<00:03, 4.62it/s]\n 47%|████▋ | 14/30 [00:03<00:03, 4.62it/s]\n 50%|█████ | 15/30 [00:03<00:03, 4.61it/s]\n 53%|█████▎ | 16/30 [00:03<00:03, 4.61it/s]\n 57%|█████▋ | 17/30 [00:03<00:02, 4.61it/s]\n 60%|██████ | 18/30 [00:03<00:02, 4.61it/s]\n 63%|██████▎ | 19/30 [00:04<00:02, 4.61it/s]\n 67%|██████▋ | 20/30 [00:04<00:02, 4.60it/s]\n 70%|███████ | 21/30 [00:04<00:01, 4.61it/s]\n 73%|███████▎ | 22/30 [00:04<00:01, 4.61it/s]\n 77%|███████▋ | 23/30 [00:04<00:01, 4.60it/s]\n 80%|████████ | 24/30 [00:05<00:01, 4.60it/s]\n 83%|████████▎ | 25/30 [00:05<00:01, 4.60it/s]\n 87%|████████▋ | 26/30 [00:05<00:00, 4.60it/s]\n 90%|█████████ | 27/30 [00:05<00:00, 4.60it/s]\n 93%|█████████▎| 28/30 [00:06<00:00, 4.60it/s]\n 97%|█████████▋| 29/30 [00:06<00:00, 4.60it/s]\n100%|██████████| 30/30 [00:06<00:00, 4.60it/s]\n100%|██████████| 30/30 [00:06<00:00, 4.61it/s]\ninference took: 6.78s\nprediction took: 7.52s", "metrics": { "predict_time": 9.074643, "total_time": 9.111952 }, "output": [ "https://replicate.delivery/pbxt/9gS9zBoS5ppIJhsZD4NfZ0hBOvjwhcxITm1pyX1vW7A1WuEJA/control-0.png", "https://replicate.delivery/pbxt/0yr4nb3krkIqONe8FNZ4Q0xXZDymwptavRMmdaf9OLNqtcJSA/out-0.png" ], "started_at": "2024-01-05T14:59:46.215696Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/fz7gt5tbzgesm2yrdue2jo7t7y", "cancel": "https://api.replicate.com/v1/predictions/fz7gt5tbzgesm2yrdue2jo7t7y/cancel" }, "version": "90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daade" }
Generated inUsing seed: 43888 Using given dimensions resize took: 0.02s Prompt: A detailed photo of an obsidian statue of an astronaut riding a unicorn, bokeh, museum background Processing image with soft_edge_hed controlnet preprocess took: 0.40s Using txt2img + controlnet pipeline Loading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s] Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 14739.02it/s] You have 1 ControlNets and you have passed 1 prompts. The conditionings will be fixed across the prompts. 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:06, 4.62it/s] 7%|▋ | 2/30 [00:00<00:06, 4.63it/s] 10%|█ | 3/30 [00:00<00:05, 4.63it/s] 13%|█▎ | 4/30 [00:00<00:05, 4.62it/s] 17%|█▋ | 5/30 [00:01<00:05, 4.62it/s] 20%|██ | 6/30 [00:01<00:05, 4.62it/s] 23%|██▎ | 7/30 [00:01<00:04, 4.62it/s] 27%|██▋ | 8/30 [00:01<00:04, 4.62it/s] 30%|███ | 9/30 [00:01<00:04, 4.61it/s] 33%|███▎ | 10/30 [00:02<00:04, 4.62it/s] 37%|███▋ | 11/30 [00:02<00:04, 4.62it/s] 40%|████ | 12/30 [00:02<00:03, 4.62it/s] 43%|████▎ | 13/30 [00:02<00:03, 4.62it/s] 47%|████▋ | 14/30 [00:03<00:03, 4.62it/s] 50%|█████ | 15/30 [00:03<00:03, 4.61it/s] 53%|█████▎ | 16/30 [00:03<00:03, 4.61it/s] 57%|█████▋ | 17/30 [00:03<00:02, 4.61it/s] 60%|██████ | 18/30 [00:03<00:02, 4.61it/s] 63%|██████▎ | 19/30 [00:04<00:02, 4.61it/s] 67%|██████▋ | 20/30 [00:04<00:02, 4.60it/s] 70%|███████ | 21/30 [00:04<00:01, 4.61it/s] 73%|███████▎ | 22/30 [00:04<00:01, 4.61it/s] 77%|███████▋ | 23/30 [00:04<00:01, 4.60it/s] 80%|████████ | 24/30 [00:05<00:01, 4.60it/s] 83%|████████▎ | 25/30 [00:05<00:01, 4.60it/s] 87%|████████▋ | 26/30 [00:05<00:00, 4.60it/s] 90%|█████████ | 27/30 [00:05<00:00, 4.60it/s] 93%|█████████▎| 28/30 [00:06<00:00, 4.60it/s] 97%|█████████▋| 29/30 [00:06<00:00, 4.60it/s] 100%|██████████| 30/30 [00:06<00:00, 4.60it/s] 100%|██████████| 30/30 [00:06<00:00, 4.61it/s] inference took: 6.78s prediction took: 7.52s
Prediction
fofr/realvisxl-v3-multi-controlnet-lora:90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daadeIDy4x4qdtbmphesvrgjvnwcn25b4StatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- A portrait photo
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.8
- num_outputs
- 1
- controlnet_1
- depth_leres
- controlnet_2
- none
- controlnet_3
- none
- guidance_scale
- 7.5
- apply_watermark
- negative_prompt
- (worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth
- prompt_strength
- 0.8
- sizing_strategy
- width_height
- controlnet_1_end
- 0.8
- controlnet_2_end
- 1
- controlnet_3_end
- 1
- controlnet_1_start
- 0
- controlnet_2_start
- 0
- controlnet_3_start
- 0
- num_inference_steps
- 30
- controlnet_1_conditioning_scale
- 0.7
- controlnet_2_conditioning_scale
- 0.8
- controlnet_3_conditioning_scale
- 0.75
{ "width": 1024, "height": 1024, "prompt": "A portrait photo", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "controlnet_1": "depth_leres", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 7.5, "apply_watermark": false, "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "prompt_strength": 0.8, "sizing_strategy": "width_height", "controlnet_1_end": 0.8, "controlnet_2_end": 1, "controlnet_3_end": 1, "controlnet_1_image": "https://replicate.delivery/pbxt/KAqHYd651SOhdam7anTmK9afE0mkAjw6tyCJclrpNdg80rmO/replicate-prediction-mufyjjdb3rml2luds2pjnbhzbi.png", "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 30, "controlnet_1_conditioning_scale": 0.7, "controlnet_2_conditioning_scale": 0.8, "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"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run fofr/realvisxl-v3-multi-controlnet-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/realvisxl-v3-multi-controlnet-lora:90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daade", { input: { width: 1024, height: 1024, prompt: "A portrait photo", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.8, num_outputs: 1, controlnet_1: "depth_leres", controlnet_2: "none", controlnet_3: "none", guidance_scale: 7.5, apply_watermark: false, negative_prompt: "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", prompt_strength: 0.8, sizing_strategy: "width_height", controlnet_1_end: 0.8, controlnet_2_end: 1, controlnet_3_end: 1, controlnet_1_image: "https://replicate.delivery/pbxt/KAqHYd651SOhdam7anTmK9afE0mkAjw6tyCJclrpNdg80rmO/replicate-prediction-mufyjjdb3rml2luds2pjnbhzbi.png", controlnet_1_start: 0, controlnet_2_start: 0, controlnet_3_start: 0, num_inference_steps: 30, controlnet_1_conditioning_scale: 0.7, controlnet_2_conditioning_scale: 0.8, 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 fofr/realvisxl-v3-multi-controlnet-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/realvisxl-v3-multi-controlnet-lora:90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daade", input={ "width": 1024, "height": 1024, "prompt": "A portrait photo", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "controlnet_1": "depth_leres", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 7.5, "apply_watermark": False, "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "prompt_strength": 0.8, "sizing_strategy": "width_height", "controlnet_1_end": 0.8, "controlnet_2_end": 1, "controlnet_3_end": 1, "controlnet_1_image": "https://replicate.delivery/pbxt/KAqHYd651SOhdam7anTmK9afE0mkAjw6tyCJclrpNdg80rmO/replicate-prediction-mufyjjdb3rml2luds2pjnbhzbi.png", "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 30, "controlnet_1_conditioning_scale": 0.7, "controlnet_2_conditioning_scale": 0.8, "controlnet_3_conditioning_scale": 0.75 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run fofr/realvisxl-v3-multi-controlnet-lora 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": "fofr/realvisxl-v3-multi-controlnet-lora:90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daade", "input": { "width": 1024, "height": 1024, "prompt": "A portrait photo", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "controlnet_1": "depth_leres", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 7.5, "apply_watermark": false, "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "prompt_strength": 0.8, "sizing_strategy": "width_height", "controlnet_1_end": 0.8, "controlnet_2_end": 1, "controlnet_3_end": 1, "controlnet_1_image": "https://replicate.delivery/pbxt/KAqHYd651SOhdam7anTmK9afE0mkAjw6tyCJclrpNdg80rmO/replicate-prediction-mufyjjdb3rml2luds2pjnbhzbi.png", "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 30, "controlnet_1_conditioning_scale": 0.7, "controlnet_2_conditioning_scale": 0.8, "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": "2024-01-05T15:21:05.346198Z", "created_at": "2024-01-05T15:20:51.902691Z", "data_removed": false, "error": null, "id": "y4x4qdtbmphesvrgjvnwcn25b4", "input": { "width": 1024, "height": 1024, "prompt": "A portrait photo", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "controlnet_1": "depth_leres", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 7.5, "apply_watermark": false, "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "prompt_strength": 0.8, "sizing_strategy": "width_height", "controlnet_1_end": 0.8, "controlnet_2_end": 1, "controlnet_3_end": 1, "controlnet_1_image": "https://replicate.delivery/pbxt/KAqHYd651SOhdam7anTmK9afE0mkAjw6tyCJclrpNdg80rmO/replicate-prediction-mufyjjdb3rml2luds2pjnbhzbi.png", "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 30, "controlnet_1_conditioning_scale": 0.7, "controlnet_2_conditioning_scale": 0.8, "controlnet_3_conditioning_scale": 0.75 }, "logs": "Using seed: 53171\nUsing given dimensions\nresize took: 0.03s\nPrompt: A portrait photo\nProcessing image with depth_leres\ncontrolnet preprocess took: 1.02s\nUsing txt2img + controlnet pipeline\nLoading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s]\nLoading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 11993.52it/s]\nYou have 1 ControlNets and you have passed 1 prompts. The conditionings will be fixed across the prompts.\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:08, 3.38it/s]\n 7%|▋ | 2/30 [00:00<00:08, 3.39it/s]\n 10%|█ | 3/30 [00:00<00:07, 3.39it/s]\n 13%|█▎ | 4/30 [00:01<00:07, 3.39it/s]\n 17%|█▋ | 5/30 [00:01<00:07, 3.39it/s]\n 20%|██ | 6/30 [00:01<00:07, 3.39it/s]\n 23%|██▎ | 7/30 [00:02<00:06, 3.39it/s]\n 27%|██▋ | 8/30 [00:02<00:06, 3.39it/s]\n 30%|███ | 9/30 [00:02<00:06, 3.39it/s]\n 33%|███▎ | 10/30 [00:02<00:05, 3.39it/s]\n 37%|███▋ | 11/30 [00:03<00:05, 3.39it/s]\n 40%|████ | 12/30 [00:03<00:05, 3.38it/s]\n 43%|████▎ | 13/30 [00:03<00:05, 3.38it/s]\n 47%|████▋ | 14/30 [00:04<00:04, 3.38it/s]\n 50%|█████ | 15/30 [00:04<00:04, 3.38it/s]\n 53%|█████▎ | 16/30 [00:04<00:04, 3.38it/s]\n 57%|█████▋ | 17/30 [00:05<00:03, 3.38it/s]\n 60%|██████ | 18/30 [00:05<00:03, 3.37it/s]\n 63%|██████▎ | 19/30 [00:05<00:03, 3.37it/s]\n 67%|██████▋ | 20/30 [00:05<00:02, 3.37it/s]\n 70%|███████ | 21/30 [00:06<00:02, 3.37it/s]\n 73%|███████▎ | 22/30 [00:06<00:02, 3.37it/s]\n 77%|███████▋ | 23/30 [00:06<00:02, 3.36it/s]\n 80%|████████ | 24/30 [00:07<00:01, 3.36it/s]\n 83%|████████▎ | 25/30 [00:07<00:01, 3.37it/s]\n 87%|████████▋ | 26/30 [00:07<00:01, 3.36it/s]\n 90%|█████████ | 27/30 [00:07<00:00, 3.36it/s]\n 93%|█████████▎| 28/30 [00:08<00:00, 3.36it/s]\n 97%|█████████▋| 29/30 [00:08<00:00, 3.36it/s]\n100%|██████████| 30/30 [00:08<00:00, 3.36it/s]\n100%|██████████| 30/30 [00:08<00:00, 3.37it/s]\ninference took: 9.32s\nprediction took: 10.80s", "metrics": { "predict_time": 13.40519, "total_time": 13.443507 }, "output": [ "https://replicate.delivery/pbxt/fhMfQLuhWArDrUZAGIRlj6eHrrFIiJ7qRIFrCaKCZ8XfF0lIB/control-0.png", "https://replicate.delivery/pbxt/et60juO5esrGAkeXcrnh4vr8bNz28jaacMJeCcxQjXAAG0lIB/out-0.png" ], "started_at": "2024-01-05T15:20:51.941008Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/y4x4qdtbmphesvrgjvnwcn25b4", "cancel": "https://api.replicate.com/v1/predictions/y4x4qdtbmphesvrgjvnwcn25b4/cancel" }, "version": "90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daade" }
Generated inUsing seed: 53171 Using given dimensions resize took: 0.03s Prompt: A portrait photo Processing image with depth_leres controlnet preprocess took: 1.02s Using txt2img + controlnet pipeline Loading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s] Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 11993.52it/s] You have 1 ControlNets and you have passed 1 prompts. The conditionings will be fixed across the prompts. 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:08, 3.38it/s] 7%|▋ | 2/30 [00:00<00:08, 3.39it/s] 10%|█ | 3/30 [00:00<00:07, 3.39it/s] 13%|█▎ | 4/30 [00:01<00:07, 3.39it/s] 17%|█▋ | 5/30 [00:01<00:07, 3.39it/s] 20%|██ | 6/30 [00:01<00:07, 3.39it/s] 23%|██▎ | 7/30 [00:02<00:06, 3.39it/s] 27%|██▋ | 8/30 [00:02<00:06, 3.39it/s] 30%|███ | 9/30 [00:02<00:06, 3.39it/s] 33%|███▎ | 10/30 [00:02<00:05, 3.39it/s] 37%|███▋ | 11/30 [00:03<00:05, 3.39it/s] 40%|████ | 12/30 [00:03<00:05, 3.38it/s] 43%|████▎ | 13/30 [00:03<00:05, 3.38it/s] 47%|████▋ | 14/30 [00:04<00:04, 3.38it/s] 50%|█████ | 15/30 [00:04<00:04, 3.38it/s] 53%|█████▎ | 16/30 [00:04<00:04, 3.38it/s] 57%|█████▋ | 17/30 [00:05<00:03, 3.38it/s] 60%|██████ | 18/30 [00:05<00:03, 3.37it/s] 63%|██████▎ | 19/30 [00:05<00:03, 3.37it/s] 67%|██████▋ | 20/30 [00:05<00:02, 3.37it/s] 70%|███████ | 21/30 [00:06<00:02, 3.37it/s] 73%|███████▎ | 22/30 [00:06<00:02, 3.37it/s] 77%|███████▋ | 23/30 [00:06<00:02, 3.36it/s] 80%|████████ | 24/30 [00:07<00:01, 3.36it/s] 83%|████████▎ | 25/30 [00:07<00:01, 3.37it/s] 87%|████████▋ | 26/30 [00:07<00:01, 3.36it/s] 90%|█████████ | 27/30 [00:07<00:00, 3.36it/s] 93%|█████████▎| 28/30 [00:08<00:00, 3.36it/s] 97%|█████████▋| 29/30 [00:08<00:00, 3.36it/s] 100%|██████████| 30/30 [00:08<00:00, 3.36it/s] 100%|██████████| 30/30 [00:08<00:00, 3.37it/s] inference took: 9.32s prediction took: 10.80s
Prediction
fofr/realvisxl-v3-multi-controlnet-lora:90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daadeID66toqj3bmu6zvqr4bj2hlmbsmuStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 768
- height
- 768
- prompt
- A detailed photo of an astronaut riding a unicorn through a field of flowers
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.8
- num_outputs
- 1
- controlnet_1
- soft_edge_hed
- controlnet_2
- none
- controlnet_3
- none
- guidance_scale
- 7.5
- apply_watermark
- negative_prompt
- 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
- 30
- controlnet_1_conditioning_scale
- 0.8
- controlnet_2_conditioning_scale
- 0.8
- controlnet_3_conditioning_scale
- 0.75
{ "width": 768, "height": 768, "prompt": "A detailed photo of an astronaut riding a unicorn through a field of flowers", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "controlnet_1": "soft_edge_hed", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 7.5, "apply_watermark": false, "negative_prompt": "", "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/JsfCQE8k1lsCinW1yo76yKMQe6R5MRt9WLL3H5T5Ypc5wasq/020e656d-0c71-45c3-a7f5-1facf7d52d4f.png", "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 30, "controlnet_1_conditioning_scale": 0.8, "controlnet_2_conditioning_scale": 0.8, "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"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run fofr/realvisxl-v3-multi-controlnet-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/realvisxl-v3-multi-controlnet-lora:90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daade", { input: { width: 768, height: 768, prompt: "A detailed photo of an astronaut riding a unicorn through a field of flowers", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.8, num_outputs: 1, controlnet_1: "soft_edge_hed", controlnet_2: "none", controlnet_3: "none", guidance_scale: 7.5, apply_watermark: false, negative_prompt: "", 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/JsfCQE8k1lsCinW1yo76yKMQe6R5MRt9WLL3H5T5Ypc5wasq/020e656d-0c71-45c3-a7f5-1facf7d52d4f.png", controlnet_1_start: 0, controlnet_2_start: 0, controlnet_3_start: 0, num_inference_steps: 30, controlnet_1_conditioning_scale: 0.8, controlnet_2_conditioning_scale: 0.8, 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 fofr/realvisxl-v3-multi-controlnet-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/realvisxl-v3-multi-controlnet-lora:90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daade", input={ "width": 768, "height": 768, "prompt": "A detailed photo of an astronaut riding a unicorn through a field of flowers", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "controlnet_1": "soft_edge_hed", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 7.5, "apply_watermark": False, "negative_prompt": "", "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/JsfCQE8k1lsCinW1yo76yKMQe6R5MRt9WLL3H5T5Ypc5wasq/020e656d-0c71-45c3-a7f5-1facf7d52d4f.png", "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 30, "controlnet_1_conditioning_scale": 0.8, "controlnet_2_conditioning_scale": 0.8, "controlnet_3_conditioning_scale": 0.75 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run fofr/realvisxl-v3-multi-controlnet-lora 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": "fofr/realvisxl-v3-multi-controlnet-lora:90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daade", "input": { "width": 768, "height": 768, "prompt": "A detailed photo of an astronaut riding a unicorn through a field of flowers", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "controlnet_1": "soft_edge_hed", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 7.5, "apply_watermark": false, "negative_prompt": "", "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/JsfCQE8k1lsCinW1yo76yKMQe6R5MRt9WLL3H5T5Ypc5wasq/020e656d-0c71-45c3-a7f5-1facf7d52d4f.png", "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 30, "controlnet_1_conditioning_scale": 0.8, "controlnet_2_conditioning_scale": 0.8, "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": "2024-01-05T15:22:42.927298Z", "created_at": "2024-01-05T15:22:33.560461Z", "data_removed": false, "error": null, "id": "66toqj3bmu6zvqr4bj2hlmbsmu", "input": { "width": 768, "height": 768, "prompt": "A detailed photo of an astronaut riding a unicorn through a field of flowers", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "controlnet_1": "soft_edge_hed", "controlnet_2": "none", "controlnet_3": "none", "guidance_scale": 7.5, "apply_watermark": false, "negative_prompt": "", "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/JsfCQE8k1lsCinW1yo76yKMQe6R5MRt9WLL3H5T5Ypc5wasq/020e656d-0c71-45c3-a7f5-1facf7d52d4f.png", "controlnet_1_start": 0, "controlnet_2_start": 0, "controlnet_3_start": 0, "num_inference_steps": 30, "controlnet_1_conditioning_scale": 0.8, "controlnet_2_conditioning_scale": 0.8, "controlnet_3_conditioning_scale": 0.75 }, "logs": "Using seed: 19498\nUsing given dimensions\nresize took: 0.02s\nPrompt: A detailed photo of an astronaut riding a unicorn through a field of flowers\nProcessing image with soft_edge_hed\ncontrolnet preprocess took: 0.43s\nUsing txt2img + controlnet pipeline\nLoading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s]\nLoading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 15485.30it/s]\nYou have 1 ControlNets and you have passed 1 prompts. The conditionings will be fixed across the prompts.\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:06, 4.63it/s]\n 7%|▋ | 2/30 [00:00<00:06, 4.62it/s]\n 10%|█ | 3/30 [00:00<00:05, 4.62it/s]\n 13%|█▎ | 4/30 [00:00<00:05, 4.62it/s]\n 17%|█▋ | 5/30 [00:01<00:05, 4.63it/s]\n 20%|██ | 6/30 [00:01<00:05, 4.63it/s]\n 23%|██▎ | 7/30 [00:01<00:04, 4.62it/s]\n 27%|██▋ | 8/30 [00:01<00:04, 4.62it/s]\n 30%|███ | 9/30 [00:01<00:04, 4.63it/s]\n 33%|███▎ | 10/30 [00:02<00:04, 4.63it/s]\n 37%|███▋ | 11/30 [00:02<00:04, 4.62it/s]\n 40%|████ | 12/30 [00:02<00:03, 4.62it/s]\n 43%|████▎ | 13/30 [00:02<00:03, 4.62it/s]\n 47%|████▋ | 14/30 [00:03<00:03, 4.62it/s]\n 50%|█████ | 15/30 [00:03<00:03, 4.62it/s]\n 53%|█████▎ | 16/30 [00:03<00:03, 4.62it/s]\n 57%|█████▋ | 17/30 [00:03<00:02, 4.62it/s]\n 60%|██████ | 18/30 [00:03<00:02, 4.62it/s]\n 63%|██████▎ | 19/30 [00:04<00:02, 4.62it/s]\n 67%|██████▋ | 20/30 [00:04<00:02, 4.62it/s]\n 70%|███████ | 21/30 [00:04<00:01, 4.62it/s]\n 73%|███████▎ | 22/30 [00:04<00:01, 4.61it/s]\n 77%|███████▋ | 23/30 [00:04<00:01, 4.62it/s]\n 80%|████████ | 24/30 [00:05<00:01, 4.62it/s]\n 83%|████████▎ | 25/30 [00:05<00:01, 4.62it/s]\n 87%|████████▋ | 26/30 [00:05<00:00, 4.62it/s]\n 90%|█████████ | 27/30 [00:05<00:00, 4.61it/s]\n 93%|█████████▎| 28/30 [00:06<00:00, 4.61it/s]\n 97%|█████████▋| 29/30 [00:06<00:00, 4.61it/s]\n100%|██████████| 30/30 [00:06<00:00, 4.61it/s]\n100%|██████████| 30/30 [00:06<00:00, 4.62it/s]\ninference took: 6.76s\nprediction took: 7.43s", "metrics": { "predict_time": 9.328726, "total_time": 9.366837 }, "output": [ "https://replicate.delivery/pbxt/2hRD2xil2dq5IxJz0wC403uh1ckANw7srVhHxbPfn52ghuEJA/control-0.png", "https://replicate.delivery/pbxt/mUtp8mKk8yI0EJ5olzsnpkeTbAcmy2OTEqnXXc8EFGLhhuEJA/out-0.png" ], "started_at": "2024-01-05T15:22:33.598572Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/66toqj3bmu6zvqr4bj2hlmbsmu", "cancel": "https://api.replicate.com/v1/predictions/66toqj3bmu6zvqr4bj2hlmbsmu/cancel" }, "version": "90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daade" }
Generated inUsing seed: 19498 Using given dimensions resize took: 0.02s Prompt: A detailed photo of an astronaut riding a unicorn through a field of flowers Processing image with soft_edge_hed controlnet preprocess took: 0.43s Using txt2img + controlnet pipeline Loading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s] Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 15485.30it/s] You have 1 ControlNets and you have passed 1 prompts. The conditionings will be fixed across the prompts. 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:06, 4.63it/s] 7%|▋ | 2/30 [00:00<00:06, 4.62it/s] 10%|█ | 3/30 [00:00<00:05, 4.62it/s] 13%|█▎ | 4/30 [00:00<00:05, 4.62it/s] 17%|█▋ | 5/30 [00:01<00:05, 4.63it/s] 20%|██ | 6/30 [00:01<00:05, 4.63it/s] 23%|██▎ | 7/30 [00:01<00:04, 4.62it/s] 27%|██▋ | 8/30 [00:01<00:04, 4.62it/s] 30%|███ | 9/30 [00:01<00:04, 4.63it/s] 33%|███▎ | 10/30 [00:02<00:04, 4.63it/s] 37%|███▋ | 11/30 [00:02<00:04, 4.62it/s] 40%|████ | 12/30 [00:02<00:03, 4.62it/s] 43%|████▎ | 13/30 [00:02<00:03, 4.62it/s] 47%|████▋ | 14/30 [00:03<00:03, 4.62it/s] 50%|█████ | 15/30 [00:03<00:03, 4.62it/s] 53%|█████▎ | 16/30 [00:03<00:03, 4.62it/s] 57%|█████▋ | 17/30 [00:03<00:02, 4.62it/s] 60%|██████ | 18/30 [00:03<00:02, 4.62it/s] 63%|██████▎ | 19/30 [00:04<00:02, 4.62it/s] 67%|██████▋ | 20/30 [00:04<00:02, 4.62it/s] 70%|███████ | 21/30 [00:04<00:01, 4.62it/s] 73%|███████▎ | 22/30 [00:04<00:01, 4.61it/s] 77%|███████▋ | 23/30 [00:04<00:01, 4.62it/s] 80%|████████ | 24/30 [00:05<00:01, 4.62it/s] 83%|████████▎ | 25/30 [00:05<00:01, 4.62it/s] 87%|████████▋ | 26/30 [00:05<00:00, 4.62it/s] 90%|█████████ | 27/30 [00:05<00:00, 4.61it/s] 93%|█████████▎| 28/30 [00:06<00:00, 4.61it/s] 97%|█████████▋| 29/30 [00:06<00:00, 4.61it/s] 100%|██████████| 30/30 [00:06<00:00, 4.61it/s] 100%|██████████| 30/30 [00:06<00:00, 4.62it/s] inference took: 6.76s prediction took: 7.43s
Prediction
fofr/realvisxl-v3-multi-controlnet-lora:90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daadeIDfkcqnklbo35y3aig7mgfe526qqStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- A detailed photo of an astronaut riding a unicorn through a field of flowers
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.8
- num_outputs
- 1
- controlnet_1
- soft_edge_hed
- controlnet_2
- illusion
- controlnet_3
- none
- guidance_scale
- 7.5
- apply_watermark
- negative_prompt
- low quality, worst quality, ugly, soft, blurry
- prompt_strength
- 0.8
- sizing_strategy
- width_height
- controlnet_1_end
- 0.8
- controlnet_2_end
- 0.65
- controlnet_3_end
- 1
- controlnet_1_start
- 0
- controlnet_2_start
- 0.08
- controlnet_3_start
- 0
- num_inference_steps
- 50
- controlnet_1_conditioning_scale
- 0.5
- controlnet_2_conditioning_scale
- 1
- controlnet_3_conditioning_scale
- 0.75
{ "width": 1024, "height": 1024, "prompt": "A detailed photo of an astronaut riding a unicorn through a field of flowers", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "controlnet_1": "soft_edge_hed", "controlnet_2": "illusion", "controlnet_3": "none", "guidance_scale": 7.5, "apply_watermark": false, "negative_prompt": "low quality, worst quality, ugly, soft, blurry", "prompt_strength": 0.8, "sizing_strategy": "width_height", "controlnet_1_end": 0.8, "controlnet_2_end": 0.65, "controlnet_3_end": 1, "controlnet_1_image": "https://replicate.delivery/pbxt/JsfCQE8k1lsCinW1yo76yKMQe6R5MRt9WLL3H5T5Ypc5wasq/020e656d-0c71-45c3-a7f5-1facf7d52d4f.png", "controlnet_1_start": 0, "controlnet_2_image": "https://replicate.delivery/pbxt/KAqPeqxKt8MVPNru3R9YaIiKHVuRAoOxKIk1ICtvrUpQ2XXY/spiral_black_transparent-2513050263.jpg", "controlnet_2_start": 0.08, "controlnet_3_start": 0, "num_inference_steps": 50, "controlnet_1_conditioning_scale": 0.5, "controlnet_2_conditioning_scale": 1, "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"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run fofr/realvisxl-v3-multi-controlnet-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/realvisxl-v3-multi-controlnet-lora:90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daade", { input: { width: 1024, height: 1024, prompt: "A detailed photo of an astronaut riding a unicorn through a field of flowers", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.8, num_outputs: 1, controlnet_1: "soft_edge_hed", controlnet_2: "illusion", controlnet_3: "none", guidance_scale: 7.5, apply_watermark: false, negative_prompt: "low quality, worst quality, ugly, soft, blurry", prompt_strength: 0.8, sizing_strategy: "width_height", controlnet_1_end: 0.8, controlnet_2_end: 0.65, controlnet_3_end: 1, controlnet_1_image: "https://replicate.delivery/pbxt/JsfCQE8k1lsCinW1yo76yKMQe6R5MRt9WLL3H5T5Ypc5wasq/020e656d-0c71-45c3-a7f5-1facf7d52d4f.png", controlnet_1_start: 0, controlnet_2_image: "https://replicate.delivery/pbxt/KAqPeqxKt8MVPNru3R9YaIiKHVuRAoOxKIk1ICtvrUpQ2XXY/spiral_black_transparent-2513050263.jpg", controlnet_2_start: 0.08, controlnet_3_start: 0, num_inference_steps: 50, controlnet_1_conditioning_scale: 0.5, controlnet_2_conditioning_scale: 1, 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 fofr/realvisxl-v3-multi-controlnet-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/realvisxl-v3-multi-controlnet-lora:90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daade", input={ "width": 1024, "height": 1024, "prompt": "A detailed photo of an astronaut riding a unicorn through a field of flowers", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "controlnet_1": "soft_edge_hed", "controlnet_2": "illusion", "controlnet_3": "none", "guidance_scale": 7.5, "apply_watermark": False, "negative_prompt": "low quality, worst quality, ugly, soft, blurry", "prompt_strength": 0.8, "sizing_strategy": "width_height", "controlnet_1_end": 0.8, "controlnet_2_end": 0.65, "controlnet_3_end": 1, "controlnet_1_image": "https://replicate.delivery/pbxt/JsfCQE8k1lsCinW1yo76yKMQe6R5MRt9WLL3H5T5Ypc5wasq/020e656d-0c71-45c3-a7f5-1facf7d52d4f.png", "controlnet_1_start": 0, "controlnet_2_image": "https://replicate.delivery/pbxt/KAqPeqxKt8MVPNru3R9YaIiKHVuRAoOxKIk1ICtvrUpQ2XXY/spiral_black_transparent-2513050263.jpg", "controlnet_2_start": 0.08, "controlnet_3_start": 0, "num_inference_steps": 50, "controlnet_1_conditioning_scale": 0.5, "controlnet_2_conditioning_scale": 1, "controlnet_3_conditioning_scale": 0.75 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run fofr/realvisxl-v3-multi-controlnet-lora 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": "fofr/realvisxl-v3-multi-controlnet-lora:90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daade", "input": { "width": 1024, "height": 1024, "prompt": "A detailed photo of an astronaut riding a unicorn through a field of flowers", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "controlnet_1": "soft_edge_hed", "controlnet_2": "illusion", "controlnet_3": "none", "guidance_scale": 7.5, "apply_watermark": false, "negative_prompt": "low quality, worst quality, ugly, soft, blurry", "prompt_strength": 0.8, "sizing_strategy": "width_height", "controlnet_1_end": 0.8, "controlnet_2_end": 0.65, "controlnet_3_end": 1, "controlnet_1_image": "https://replicate.delivery/pbxt/JsfCQE8k1lsCinW1yo76yKMQe6R5MRt9WLL3H5T5Ypc5wasq/020e656d-0c71-45c3-a7f5-1facf7d52d4f.png", "controlnet_1_start": 0, "controlnet_2_image": "https://replicate.delivery/pbxt/KAqPeqxKt8MVPNru3R9YaIiKHVuRAoOxKIk1ICtvrUpQ2XXY/spiral_black_transparent-2513050263.jpg", "controlnet_2_start": 0.08, "controlnet_3_start": 0, "num_inference_steps": 50, "controlnet_1_conditioning_scale": 0.5, "controlnet_2_conditioning_scale": 1, "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": "2024-01-05T15:29:50.723676Z", "created_at": "2024-01-05T15:29:23.467941Z", "data_removed": false, "error": null, "id": "fkcqnklbo35y3aig7mgfe526qq", "input": { "width": 1024, "height": 1024, "prompt": "A detailed photo of an astronaut riding a unicorn through a field of flowers", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.8, "num_outputs": 1, "controlnet_1": "soft_edge_hed", "controlnet_2": "illusion", "controlnet_3": "none", "guidance_scale": 7.5, "apply_watermark": false, "negative_prompt": "low quality, worst quality, ugly, soft, blurry", "prompt_strength": 0.8, "sizing_strategy": "width_height", "controlnet_1_end": 0.8, "controlnet_2_end": 0.65, "controlnet_3_end": 1, "controlnet_1_image": "https://replicate.delivery/pbxt/JsfCQE8k1lsCinW1yo76yKMQe6R5MRt9WLL3H5T5Ypc5wasq/020e656d-0c71-45c3-a7f5-1facf7d52d4f.png", "controlnet_1_start": 0, "controlnet_2_image": "https://replicate.delivery/pbxt/KAqPeqxKt8MVPNru3R9YaIiKHVuRAoOxKIk1ICtvrUpQ2XXY/spiral_black_transparent-2513050263.jpg", "controlnet_2_start": 0.08, "controlnet_3_start": 0, "num_inference_steps": 50, "controlnet_1_conditioning_scale": 0.5, "controlnet_2_conditioning_scale": 1, "controlnet_3_conditioning_scale": 0.75 }, "logs": "Using seed: 50913\nUsing given dimensions\nresize took: 0.04s\nPrompt: A detailed photo of an astronaut riding a unicorn through a field of flowers\nProcessing image with soft_edge_hed\ncontrolnet preprocess took: 0.42s\nUsing txt2img + controlnet pipeline\nLoading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s]\nLoading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 13751.82it/s]\nYou have 2 ControlNets and you have passed 1 prompts. The conditionings will be fixed across the prompts.\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:22, 2.17it/s]\n 4%|▍ | 2/50 [00:00<00:22, 2.17it/s]\n 6%|▌ | 3/50 [00:01<00:21, 2.17it/s]\n 8%|▊ | 4/50 [00:01<00:21, 2.17it/s]\n 10%|█ | 5/50 [00:02<00:20, 2.17it/s]\n 12%|█▏ | 6/50 [00:02<00:20, 2.17it/s]\n 14%|█▍ | 7/50 [00:03<00:19, 2.17it/s]\n 16%|█▌ | 8/50 [00:03<00:19, 2.17it/s]\n 18%|█▊ | 9/50 [00:04<00:18, 2.17it/s]\n 20%|██ | 10/50 [00:04<00:18, 2.16it/s]\n 22%|██▏ | 11/50 [00:05<00:18, 2.16it/s]\n 24%|██▍ | 12/50 [00:05<00:17, 2.16it/s]\n 26%|██▌ | 13/50 [00:06<00:17, 2.16it/s]\n 28%|██▊ | 14/50 [00:06<00:16, 2.16it/s]\n 30%|███ | 15/50 [00:06<00:16, 2.16it/s]\n 32%|███▏ | 16/50 [00:07<00:15, 2.16it/s]\n 34%|███▍ | 17/50 [00:07<00:15, 2.16it/s]\n 36%|███▌ | 18/50 [00:08<00:14, 2.16it/s]\n 38%|███▊ | 19/50 [00:08<00:14, 2.16it/s]\n 40%|████ | 20/50 [00:09<00:13, 2.16it/s]\n 42%|████▏ | 21/50 [00:09<00:13, 2.16it/s]\n 44%|████▍ | 22/50 [00:10<00:12, 2.16it/s]\n 46%|████▌ | 23/50 [00:10<00:12, 2.16it/s]\n 48%|████▊ | 24/50 [00:11<00:12, 2.15it/s]\n 50%|█████ | 25/50 [00:11<00:11, 2.15it/s]\n 52%|█████▏ | 26/50 [00:12<00:11, 2.15it/s]\n 54%|█████▍ | 27/50 [00:12<00:10, 2.15it/s]\n 56%|█████▌ | 28/50 [00:12<00:10, 2.15it/s]\n 58%|█████▊ | 29/50 [00:13<00:09, 2.15it/s]\n 60%|██████ | 30/50 [00:13<00:09, 2.15it/s]\n 62%|██████▏ | 31/50 [00:14<00:08, 2.15it/s]\n 64%|██████▍ | 32/50 [00:14<00:08, 2.15it/s]\n 66%|██████▌ | 33/50 [00:15<00:07, 2.15it/s]\n 68%|██████▊ | 34/50 [00:15<00:07, 2.15it/s]\n 70%|███████ | 35/50 [00:16<00:06, 2.15it/s]\n 72%|███████▏ | 36/50 [00:16<00:06, 2.15it/s]\n 74%|███████▍ | 37/50 [00:17<00:06, 2.15it/s]\n 76%|███████▌ | 38/50 [00:17<00:05, 2.15it/s]\n 78%|███████▊ | 39/50 [00:18<00:05, 2.15it/s]\n 80%|████████ | 40/50 [00:18<00:04, 2.15it/s]\n 82%|████████▏ | 41/50 [00:19<00:04, 2.15it/s]\n 84%|████████▍ | 42/50 [00:19<00:03, 2.15it/s]\n 86%|████████▌ | 43/50 [00:19<00:03, 2.15it/s]\n 88%|████████▊ | 44/50 [00:20<00:02, 2.15it/s]\n 90%|█████████ | 45/50 [00:20<00:02, 2.15it/s]\n 92%|█████████▏| 46/50 [00:21<00:01, 2.15it/s]\n 94%|█████████▍| 47/50 [00:21<00:01, 2.14it/s]\n 96%|█████████▌| 48/50 [00:22<00:00, 2.15it/s]\n 98%|█████████▊| 49/50 [00:22<00:00, 2.15it/s]\n100%|██████████| 50/50 [00:23<00:00, 2.15it/s]\n100%|██████████| 50/50 [00:23<00:00, 2.16it/s]\ninference took: 23.66s\nprediction took: 24.44s", "metrics": { "predict_time": 27.217987, "total_time": 27.255735 }, "output": [ "https://replicate.delivery/pbxt/L6Goc02N7fXcfEoirX3vE1TUpqJpUFXf0lrtUuzIaPsYT6SkA/control-0.png", "https://replicate.delivery/pbxt/vpb5gbXNqtpTBJgfwkU8EMTtCbfs4YuUZkTLbh579SOtJdJSA/control-1.png", "https://replicate.delivery/pbxt/Pjd50izNdzJDFJlfczALREnyfGIedK4HufhEVV3tVCK4m0lIB/out-0.png" ], "started_at": "2024-01-05T15:29:23.505689Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/fkcqnklbo35y3aig7mgfe526qq", "cancel": "https://api.replicate.com/v1/predictions/fkcqnklbo35y3aig7mgfe526qq/cancel" }, "version": "90a4a3604cd637cb9f1a2bdae1cfa9ed869362ca028814cdce310a78e27daade" }
Generated inUsing seed: 50913 Using given dimensions resize took: 0.04s Prompt: A detailed photo of an astronaut riding a unicorn through a field of flowers Processing image with soft_edge_hed controlnet preprocess took: 0.42s Using txt2img + controlnet pipeline Loading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s] Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 13751.82it/s] You have 2 ControlNets and you have passed 1 prompts. The conditionings will be fixed across the prompts. 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:22, 2.17it/s] 4%|▍ | 2/50 [00:00<00:22, 2.17it/s] 6%|▌ | 3/50 [00:01<00:21, 2.17it/s] 8%|▊ | 4/50 [00:01<00:21, 2.17it/s] 10%|█ | 5/50 [00:02<00:20, 2.17it/s] 12%|█▏ | 6/50 [00:02<00:20, 2.17it/s] 14%|█▍ | 7/50 [00:03<00:19, 2.17it/s] 16%|█▌ | 8/50 [00:03<00:19, 2.17it/s] 18%|█▊ | 9/50 [00:04<00:18, 2.17it/s] 20%|██ | 10/50 [00:04<00:18, 2.16it/s] 22%|██▏ | 11/50 [00:05<00:18, 2.16it/s] 24%|██▍ | 12/50 [00:05<00:17, 2.16it/s] 26%|██▌ | 13/50 [00:06<00:17, 2.16it/s] 28%|██▊ | 14/50 [00:06<00:16, 2.16it/s] 30%|███ | 15/50 [00:06<00:16, 2.16it/s] 32%|███▏ | 16/50 [00:07<00:15, 2.16it/s] 34%|███▍ | 17/50 [00:07<00:15, 2.16it/s] 36%|███▌ | 18/50 [00:08<00:14, 2.16it/s] 38%|███▊ | 19/50 [00:08<00:14, 2.16it/s] 40%|████ | 20/50 [00:09<00:13, 2.16it/s] 42%|████▏ | 21/50 [00:09<00:13, 2.16it/s] 44%|████▍ | 22/50 [00:10<00:12, 2.16it/s] 46%|████▌ | 23/50 [00:10<00:12, 2.16it/s] 48%|████▊ | 24/50 [00:11<00:12, 2.15it/s] 50%|█████ | 25/50 [00:11<00:11, 2.15it/s] 52%|█████▏ | 26/50 [00:12<00:11, 2.15it/s] 54%|█████▍ | 27/50 [00:12<00:10, 2.15it/s] 56%|█████▌ | 28/50 [00:12<00:10, 2.15it/s] 58%|█████▊ | 29/50 [00:13<00:09, 2.15it/s] 60%|██████ | 30/50 [00:13<00:09, 2.15it/s] 62%|██████▏ | 31/50 [00:14<00:08, 2.15it/s] 64%|██████▍ | 32/50 [00:14<00:08, 2.15it/s] 66%|██████▌ | 33/50 [00:15<00:07, 2.15it/s] 68%|██████▊ | 34/50 [00:15<00:07, 2.15it/s] 70%|███████ | 35/50 [00:16<00:06, 2.15it/s] 72%|███████▏ | 36/50 [00:16<00:06, 2.15it/s] 74%|███████▍ | 37/50 [00:17<00:06, 2.15it/s] 76%|███████▌ | 38/50 [00:17<00:05, 2.15it/s] 78%|███████▊ | 39/50 [00:18<00:05, 2.15it/s] 80%|████████ | 40/50 [00:18<00:04, 2.15it/s] 82%|████████▏ | 41/50 [00:19<00:04, 2.15it/s] 84%|████████▍ | 42/50 [00:19<00:03, 2.15it/s] 86%|████████▌ | 43/50 [00:19<00:03, 2.15it/s] 88%|████████▊ | 44/50 [00:20<00:02, 2.15it/s] 90%|█████████ | 45/50 [00:20<00:02, 2.15it/s] 92%|█████████▏| 46/50 [00:21<00:01, 2.15it/s] 94%|█████████▍| 47/50 [00:21<00:01, 2.14it/s] 96%|█████████▌| 48/50 [00:22<00:00, 2.15it/s] 98%|█████████▊| 49/50 [00:22<00:00, 2.15it/s] 100%|██████████| 50/50 [00:23<00:00, 2.15it/s] 100%|██████████| 50/50 [00:23<00:00, 2.16it/s] inference took: 23.66s prediction took: 24.44s
Want to make some of these yourself?
Run this model