fermatresearch / sdxl-lcm-lora-controlnet
An extremely fast all-in-one model to use LCM with SDXL, ControlNet and custom LoRA url's!
- Public
- 14.8K runs
-
A100 (80GB)
- GitHub
Prediction
fermatresearch/sdxl-lcm-lora-controlnet:d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099IDszk7rylbfq6aosmfuvkfczlogmStatusSucceededSourceWebHardwareA100 (80GB)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- shot in the style of sksfer, a boy playing with some toys
- scheduler
- LCM
- lora_scale
- 0.9
- num_outputs
- 1
- lora_weights
- https://pbxt.replicate.delivery/QmdRkthSZmqTEBMgVi17OqpdKkafyLTS6TGmzTF5Qbo9d13IA/trained_model.tar
- batched_prompt
- guidance_scale
- 2
- apply_watermark
- condition_scale
- 0.45
- negative_prompt
- prompt_strength
- 0.8
- controlnet_image
- num_inference_steps
- 6
{ "width": 1024, "height": 1024, "prompt": "shot in the style of sksfer, a boy playing with some toys", "scheduler": "LCM", "lora_scale": 0.9, "num_outputs": 1, "lora_weights": "https://pbxt.replicate.delivery/QmdRkthSZmqTEBMgVi17OqpdKkafyLTS6TGmzTF5Qbo9d13IA/trained_model.tar", "batched_prompt": false, "guidance_scale": 2, "apply_watermark": true, "condition_scale": 0.45, "negative_prompt": "", "prompt_strength": 0.8, "controlnet_image": "https://replicate.delivery/pbxt/JsNziYC0Ha190bMKRDwkR5FpRGDrewOXzGH7mneGnHG4jREV/1f8edf0a-6ae1-4021-8ad2-e866e98d6efd.png", "num_inference_steps": 6 }Install Replicate’s Node.js client library:npm install replicateImport 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 fermatresearch/sdxl-lcm-lora-controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fermatresearch/sdxl-lcm-lora-controlnet:d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099", { input: { width: 1024, height: 1024, prompt: "shot in the style of sksfer, a boy playing with some toys", scheduler: "LCM", lora_scale: 0.9, num_outputs: 1, lora_weights: "https://pbxt.replicate.delivery/QmdRkthSZmqTEBMgVi17OqpdKkafyLTS6TGmzTF5Qbo9d13IA/trained_model.tar", batched_prompt: false, guidance_scale: 2, apply_watermark: true, condition_scale: 0.45, negative_prompt: "", prompt_strength: 0.8, controlnet_image: "https://replicate.delivery/pbxt/JsNziYC0Ha190bMKRDwkR5FpRGDrewOXzGH7mneGnHG4jREV/1f8edf0a-6ae1-4021-8ad2-e866e98d6efd.png", num_inference_steps: 6 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun fermatresearch/sdxl-lcm-lora-controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fermatresearch/sdxl-lcm-lora-controlnet:d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099", input={ "width": 1024, "height": 1024, "prompt": "shot in the style of sksfer, a boy playing with some toys", "scheduler": "LCM", "lora_scale": 0.9, "num_outputs": 1, "lora_weights": "https://pbxt.replicate.delivery/QmdRkthSZmqTEBMgVi17OqpdKkafyLTS6TGmzTF5Qbo9d13IA/trained_model.tar", "batched_prompt": False, "guidance_scale": 2, "apply_watermark": True, "condition_scale": 0.45, "negative_prompt": "", "prompt_strength": 0.8, "controlnet_image": "https://replicate.delivery/pbxt/JsNziYC0Ha190bMKRDwkR5FpRGDrewOXzGH7mneGnHG4jREV/1f8edf0a-6ae1-4021-8ad2-e866e98d6efd.png", "num_inference_steps": 6 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run fermatresearch/sdxl-lcm-lora-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": "fermatresearch/sdxl-lcm-lora-controlnet:d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099", "input": { "width": 1024, "height": 1024, "prompt": "shot in the style of sksfer, a boy playing with some toys", "scheduler": "LCM", "lora_scale": 0.9, "num_outputs": 1, "lora_weights": "https://pbxt.replicate.delivery/QmdRkthSZmqTEBMgVi17OqpdKkafyLTS6TGmzTF5Qbo9d13IA/trained_model.tar", "batched_prompt": false, "guidance_scale": 2, "apply_watermark": true, "condition_scale": 0.45, "negative_prompt": "", "prompt_strength": 0.8, "controlnet_image": "https://replicate.delivery/pbxt/JsNziYC0Ha190bMKRDwkR5FpRGDrewOXzGH7mneGnHG4jREV/1f8edf0a-6ae1-4021-8ad2-e866e98d6efd.png", "num_inference_steps": 6 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-11-14T15:26:54.484430Z", "created_at": "2023-11-14T15:26:50.711437Z", "data_removed": false, "error": null, "id": "szk7rylbfq6aosmfuvkfczlogm", "input": { "width": 1024, "height": 1024, "prompt": "shot in the style of sksfer, a boy playing with some toys", "scheduler": "LCM", "lora_scale": 0.9, "num_outputs": 1, "lora_weights": "https://pbxt.replicate.delivery/QmdRkthSZmqTEBMgVi17OqpdKkafyLTS6TGmzTF5Qbo9d13IA/trained_model.tar", "batched_prompt": false, "guidance_scale": 2, "apply_watermark": true, "condition_scale": 0.45, "negative_prompt": "", "prompt_strength": 0.8, "controlnet_image": "https://replicate.delivery/pbxt/JsNziYC0Ha190bMKRDwkR5FpRGDrewOXzGH7mneGnHG4jREV/1f8edf0a-6ae1-4021-8ad2-e866e98d6efd.png", "num_inference_steps": 6 }, "logs": "Using seed: 59453\nskipping loading .. weights already loaded\nPrompt: shot in the style of <s0><s1>, a boy playing with some toys\nThe config attributes {'skip_prk_steps': True} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.\n 0%| | 0/6 [00:00<?, ?it/s]\n 17%|█▋ | 1/6 [00:00<00:01, 4.77it/s]\n 33%|███▎ | 2/6 [00:00<00:00, 4.77it/s]\n 50%|█████ | 3/6 [00:00<00:00, 4.77it/s]\n 67%|██████▋ | 4/6 [00:00<00:00, 4.76it/s]\n 83%|████████▎ | 5/6 [00:01<00:00, 4.76it/s]\n100%|██████████| 6/6 [00:01<00:00, 4.76it/s]\n100%|██████████| 6/6 [00:01<00:00, 4.76it/s]", "metrics": { "predict_time": 3.715988, "total_time": 3.772993 }, "output": [ "https://replicate.delivery/pbxt/URStBauvk2KTHl0Be5UaczWxPPdeX5cDm4fyvQYYQ876dowjA/out-0.png" ], "started_at": "2023-11-14T15:26:50.768442Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/szk7rylbfq6aosmfuvkfczlogm", "cancel": "https://api.replicate.com/v1/predictions/szk7rylbfq6aosmfuvkfczlogm/cancel" }, "version": "d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099" }Generated inUsing seed: 59453 skipping loading .. weights already loaded Prompt: shot in the style of <s0><s1>, a boy playing with some toys The config attributes {'skip_prk_steps': True} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file. 0%| | 0/6 [00:00<?, ?it/s] 17%|█▋ | 1/6 [00:00<00:01, 4.77it/s] 33%|███▎ | 2/6 [00:00<00:00, 4.77it/s] 50%|█████ | 3/6 [00:00<00:00, 4.77it/s] 67%|██████▋ | 4/6 [00:00<00:00, 4.76it/s] 83%|████████▎ | 5/6 [00:01<00:00, 4.76it/s] 100%|██████████| 6/6 [00:01<00:00, 4.76it/s] 100%|██████████| 6/6 [00:01<00:00, 4.76it/s]Prediction
fermatresearch/sdxl-lcm-lora-controlnet:d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099IDoyv45a3boeblmulzcxh7iujdgaStatusSucceededSourceWebHardwareA100 (80GB)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- shot in the style of sksfer, a boy in the beach playing with some toys shot in the style of sksfer, a boy in space playing with some toys
- scheduler
- LCM
- lora_scale
- 0.94
- num_outputs
- 1
- lora_weights
- https://pbxt.replicate.delivery/QmdRkthSZmqTEBMgVi17OqpdKkafyLTS6TGmzTF5Qbo9d13IA/trained_model.tar
- batched_prompt
- guidance_scale
- 2
- apply_watermark
- condition_scale
- 0.45
- prompt_strength
- 0.8
- controlnet_image
- num_inference_steps
- 6
{ "width": 1024, "height": 1024, "prompt": "shot in the style of sksfer, a boy in the beach playing with some toys\nshot in the style of sksfer, a boy in space playing with some toys", "scheduler": "LCM", "lora_scale": 0.94, "num_outputs": 1, "lora_weights": "https://pbxt.replicate.delivery/QmdRkthSZmqTEBMgVi17OqpdKkafyLTS6TGmzTF5Qbo9d13IA/trained_model.tar", "batched_prompt": true, "guidance_scale": 2, "apply_watermark": true, "condition_scale": 0.45, "prompt_strength": 0.8, "controlnet_image": "https://replicate.delivery/pbxt/JsNziYC0Ha190bMKRDwkR5FpRGDrewOXzGH7mneGnHG4jREV/1f8edf0a-6ae1-4021-8ad2-e866e98d6efd.png", "num_inference_steps": 6 }Install Replicate’s Node.js client library:npm install replicateImport 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 fermatresearch/sdxl-lcm-lora-controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fermatresearch/sdxl-lcm-lora-controlnet:d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099", { input: { width: 1024, height: 1024, prompt: "shot in the style of sksfer, a boy in the beach playing with some toys\nshot in the style of sksfer, a boy in space playing with some toys", scheduler: "LCM", lora_scale: 0.94, num_outputs: 1, lora_weights: "https://pbxt.replicate.delivery/QmdRkthSZmqTEBMgVi17OqpdKkafyLTS6TGmzTF5Qbo9d13IA/trained_model.tar", batched_prompt: true, guidance_scale: 2, apply_watermark: true, condition_scale: 0.45, prompt_strength: 0.8, controlnet_image: "https://replicate.delivery/pbxt/JsNziYC0Ha190bMKRDwkR5FpRGDrewOXzGH7mneGnHG4jREV/1f8edf0a-6ae1-4021-8ad2-e866e98d6efd.png", num_inference_steps: 6 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun fermatresearch/sdxl-lcm-lora-controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fermatresearch/sdxl-lcm-lora-controlnet:d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099", input={ "width": 1024, "height": 1024, "prompt": "shot in the style of sksfer, a boy in the beach playing with some toys\nshot in the style of sksfer, a boy in space playing with some toys", "scheduler": "LCM", "lora_scale": 0.94, "num_outputs": 1, "lora_weights": "https://pbxt.replicate.delivery/QmdRkthSZmqTEBMgVi17OqpdKkafyLTS6TGmzTF5Qbo9d13IA/trained_model.tar", "batched_prompt": True, "guidance_scale": 2, "apply_watermark": True, "condition_scale": 0.45, "prompt_strength": 0.8, "controlnet_image": "https://replicate.delivery/pbxt/JsNziYC0Ha190bMKRDwkR5FpRGDrewOXzGH7mneGnHG4jREV/1f8edf0a-6ae1-4021-8ad2-e866e98d6efd.png", "num_inference_steps": 6 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run fermatresearch/sdxl-lcm-lora-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": "fermatresearch/sdxl-lcm-lora-controlnet:d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099", "input": { "width": 1024, "height": 1024, "prompt": "shot in the style of sksfer, a boy in the beach playing with some toys\\nshot in the style of sksfer, a boy in space playing with some toys", "scheduler": "LCM", "lora_scale": 0.94, "num_outputs": 1, "lora_weights": "https://pbxt.replicate.delivery/QmdRkthSZmqTEBMgVi17OqpdKkafyLTS6TGmzTF5Qbo9d13IA/trained_model.tar", "batched_prompt": true, "guidance_scale": 2, "apply_watermark": true, "condition_scale": 0.45, "prompt_strength": 0.8, "controlnet_image": "https://replicate.delivery/pbxt/JsNziYC0Ha190bMKRDwkR5FpRGDrewOXzGH7mneGnHG4jREV/1f8edf0a-6ae1-4021-8ad2-e866e98d6efd.png", "num_inference_steps": 6 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-11-14T15:37:12.594409Z", "created_at": "2023-11-14T15:37:06.634761Z", "data_removed": false, "error": null, "id": "oyv45a3boeblmulzcxh7iujdga", "input": { "width": 1024, "height": 1024, "prompt": "shot in the style of sksfer, a boy in the beach playing with some toys\nshot in the style of sksfer, a boy in space playing with some toys", "scheduler": "LCM", "lora_scale": 0.94, "num_outputs": 1, "lora_weights": "https://pbxt.replicate.delivery/QmdRkthSZmqTEBMgVi17OqpdKkafyLTS6TGmzTF5Qbo9d13IA/trained_model.tar", "batched_prompt": true, "guidance_scale": 2, "apply_watermark": true, "condition_scale": 0.45, "prompt_strength": 0.8, "controlnet_image": "https://replicate.delivery/pbxt/JsNziYC0Ha190bMKRDwkR5FpRGDrewOXzGH7mneGnHG4jREV/1f8edf0a-6ae1-4021-8ad2-e866e98d6efd.png", "num_inference_steps": 6 }, "logs": "Using seed: 16224\nskipping loading .. weights already loaded\nPrompt: shot in the style of <s0><s1>, a boy in the beach playing with some toys\nshot in the style of <s0><s1>, a boy in space playing with some toys\nThe config attributes {'skip_prk_steps': True} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.\n 0%| | 0/6 [00:00<?, ?it/s]\n 17%|█▋ | 1/6 [00:00<00:01, 2.69it/s]\n 33%|███▎ | 2/6 [00:00<00:01, 2.68it/s]\n 50%|█████ | 3/6 [00:01<00:01, 2.68it/s]\n 67%|██████▋ | 4/6 [00:01<00:00, 2.68it/s]\n 83%|████████▎ | 5/6 [00:01<00:00, 2.67it/s]\n100%|██████████| 6/6 [00:02<00:00, 2.67it/s]\n100%|██████████| 6/6 [00:02<00:00, 2.67it/s]", "metrics": { "predict_time": 5.925552, "total_time": 5.959648 }, "output": [ "https://replicate.delivery/pbxt/OLm0L3nN6P7pLRJUg3w5KJxrNXzhbsKglzoqDeI3OItTMK8IA/out-0.png", "https://replicate.delivery/pbxt/j1OoUUt9f30WDiqS0L94TvZ9CRLGolnxdbgd46AsncJUMK8IA/out-1.png" ], "started_at": "2023-11-14T15:37:06.668857Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/oyv45a3boeblmulzcxh7iujdga", "cancel": "https://api.replicate.com/v1/predictions/oyv45a3boeblmulzcxh7iujdga/cancel" }, "version": "d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099" }Generated inUsing seed: 16224 skipping loading .. weights already loaded Prompt: shot in the style of <s0><s1>, a boy in the beach playing with some toys shot in the style of <s0><s1>, a boy in space playing with some toys The config attributes {'skip_prk_steps': True} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file. 0%| | 0/6 [00:00<?, ?it/s] 17%|█▋ | 1/6 [00:00<00:01, 2.69it/s] 33%|███▎ | 2/6 [00:00<00:01, 2.68it/s] 50%|█████ | 3/6 [00:01<00:01, 2.68it/s] 67%|██████▋ | 4/6 [00:01<00:00, 2.68it/s] 83%|████████▎ | 5/6 [00:01<00:00, 2.67it/s] 100%|██████████| 6/6 [00:02<00:00, 2.67it/s] 100%|██████████| 6/6 [00:02<00:00, 2.67it/s]Prediction
fermatresearch/sdxl-lcm-lora-controlnet:d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099IDqzjv5ldb37obheulhdn7j2rq3aStatusSucceededSourceWebHardwareA100 (80GB)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- close-up photography of a panda standing in the rain at night in a yellow jacket, under a clear umbrella, urban setting, in a street lit by lamps, facing camera, leica 35mm summilux
- scheduler
- LCM
- lora_scale
- 0.9
- num_outputs
- 1
- batched_prompt
- guidance_scale
- 1
- apply_watermark
- condition_scale
- 0.45
- prompt_strength
- 0.8
- num_inference_steps
- 5
{ "width": 1024, "height": 1024, "prompt": "close-up photography of a panda standing in the rain at night in a yellow jacket, under a clear umbrella, urban setting, in a street lit by lamps, facing camera, leica 35mm summilux", "scheduler": "LCM", "lora_scale": 0.9, "num_outputs": 1, "batched_prompt": false, "guidance_scale": 1, "apply_watermark": true, "condition_scale": 0.45, "prompt_strength": 0.8, "num_inference_steps": 5 }Install Replicate’s Node.js client library:npm install replicateImport 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 fermatresearch/sdxl-lcm-lora-controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fermatresearch/sdxl-lcm-lora-controlnet:d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099", { input: { width: 1024, height: 1024, prompt: "close-up photography of a panda standing in the rain at night in a yellow jacket, under a clear umbrella, urban setting, in a street lit by lamps, facing camera, leica 35mm summilux", scheduler: "LCM", lora_scale: 0.9, num_outputs: 1, batched_prompt: false, guidance_scale: 1, apply_watermark: true, condition_scale: 0.45, prompt_strength: 0.8, num_inference_steps: 5 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun fermatresearch/sdxl-lcm-lora-controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fermatresearch/sdxl-lcm-lora-controlnet:d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099", input={ "width": 1024, "height": 1024, "prompt": "close-up photography of a panda standing in the rain at night in a yellow jacket, under a clear umbrella, urban setting, in a street lit by lamps, facing camera, leica 35mm summilux", "scheduler": "LCM", "lora_scale": 0.9, "num_outputs": 1, "batched_prompt": False, "guidance_scale": 1, "apply_watermark": True, "condition_scale": 0.45, "prompt_strength": 0.8, "num_inference_steps": 5 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run fermatresearch/sdxl-lcm-lora-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": "fermatresearch/sdxl-lcm-lora-controlnet:d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099", "input": { "width": 1024, "height": 1024, "prompt": "close-up photography of a panda standing in the rain at night in a yellow jacket, under a clear umbrella, urban setting, in a street lit by lamps, facing camera, leica 35mm summilux", "scheduler": "LCM", "lora_scale": 0.9, "num_outputs": 1, "batched_prompt": false, "guidance_scale": 1, "apply_watermark": true, "condition_scale": 0.45, "prompt_strength": 0.8, "num_inference_steps": 5 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-11-14T15:57:14.617938Z", "created_at": "2023-11-14T15:57:12.229356Z", "data_removed": false, "error": null, "id": "qzjv5ldb37obheulhdn7j2rq3a", "input": { "width": 1024, "height": 1024, "prompt": "close-up photography of a panda standing in the rain at night in a yellow jacket, under a clear umbrella, urban setting, in a street lit by lamps, facing camera, leica 35mm summilux", "scheduler": "LCM", "lora_scale": 0.9, "num_outputs": 1, "batched_prompt": false, "guidance_scale": 1, "apply_watermark": true, "condition_scale": 0.45, "prompt_strength": 0.8, "num_inference_steps": 5 }, "logs": "Using seed: 23332\nPrompt: close-up photography of a panda standing in the rain at night in a yellow jacket, under a clear umbrella, urban setting, in a street lit by lamps, facing camera, leica 35mm summilux\ntxt2img mode\nThe config attributes {'skip_prk_steps': True} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.\n 0%| | 0/5 [00:00<?, ?it/s]\n 40%|████ | 2/5 [00:00<00:00, 14.77it/s]\n 80%|████████ | 4/5 [00:00<00:00, 14.76it/s]\n100%|██████████| 5/5 [00:00<00:00, 14.76it/s]", "metrics": { "predict_time": 2.355979, "total_time": 2.388582 }, "output": [ "https://replicate.delivery/pbxt/Yn8RIIhYFBICO1fouwFoTGArYzRmeTSm7dtSB2qJwxSZrU4RA/out-0.png" ], "started_at": "2023-11-14T15:57:12.261959Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/qzjv5ldb37obheulhdn7j2rq3a", "cancel": "https://api.replicate.com/v1/predictions/qzjv5ldb37obheulhdn7j2rq3a/cancel" }, "version": "d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099" }Generated inUsing seed: 23332 Prompt: close-up photography of a panda standing in the rain at night in a yellow jacket, under a clear umbrella, urban setting, in a street lit by lamps, facing camera, leica 35mm summilux txt2img mode The config attributes {'skip_prk_steps': True} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file. 0%| | 0/5 [00:00<?, ?it/s] 40%|████ | 2/5 [00:00<00:00, 14.77it/s] 80%|████████ | 4/5 [00:00<00:00, 14.76it/s] 100%|██████████| 5/5 [00:00<00:00, 14.76it/s]Prediction
fermatresearch/sdxl-lcm-lora-controlnet:d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099IDcnp463tbdv7stxo4j6fyuocan4StatusSucceededSourceWebHardwareA100 (80GB)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- shot in the style of sksfer, a turtle shot in the style of sksfer, a shark
- scheduler
- LCM
- lora_scale
- 0.8
- num_outputs
- 1
- lora_weights
- https://pbxt.replicate.delivery/3wwmvGfvB4weYkJMAR2JJNMXu7RPtd8Hc5ONP3IP23fioXfGB/trained_model.tar
- batched_prompt
- guidance_scale
- 2
- apply_watermark
- condition_scale
- 0.45
- negative_prompt
- prompt_strength
- 0.8
- num_inference_steps
- 6
{ "width": 1024, "height": 1024, "prompt": "shot in the style of sksfer, a turtle\nshot in the style of sksfer, a shark", "scheduler": "LCM", "lora_scale": 0.8, "num_outputs": 1, "lora_weights": "https://pbxt.replicate.delivery/3wwmvGfvB4weYkJMAR2JJNMXu7RPtd8Hc5ONP3IP23fioXfGB/trained_model.tar", "batched_prompt": true, "guidance_scale": 2, "apply_watermark": true, "condition_scale": 0.45, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 6 }Install Replicate’s Node.js client library:npm install replicateImport 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 fermatresearch/sdxl-lcm-lora-controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fermatresearch/sdxl-lcm-lora-controlnet:d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099", { input: { width: 1024, height: 1024, prompt: "shot in the style of sksfer, a turtle\nshot in the style of sksfer, a shark", scheduler: "LCM", lora_scale: 0.8, num_outputs: 1, lora_weights: "https://pbxt.replicate.delivery/3wwmvGfvB4weYkJMAR2JJNMXu7RPtd8Hc5ONP3IP23fioXfGB/trained_model.tar", batched_prompt: true, guidance_scale: 2, apply_watermark: true, condition_scale: 0.45, negative_prompt: "", prompt_strength: 0.8, num_inference_steps: 6 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateImport the client:import replicateRun fermatresearch/sdxl-lcm-lora-controlnet using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fermatresearch/sdxl-lcm-lora-controlnet:d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099", input={ "width": 1024, "height": 1024, "prompt": "shot in the style of sksfer, a turtle\nshot in the style of sksfer, a shark", "scheduler": "LCM", "lora_scale": 0.8, "num_outputs": 1, "lora_weights": "https://pbxt.replicate.delivery/3wwmvGfvB4weYkJMAR2JJNMXu7RPtd8Hc5ONP3IP23fioXfGB/trained_model.tar", "batched_prompt": True, "guidance_scale": 2, "apply_watermark": True, "condition_scale": 0.45, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 6 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())To learn more, take a look at the guide on getting started with Python.
Run fermatresearch/sdxl-lcm-lora-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": "fermatresearch/sdxl-lcm-lora-controlnet:d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099", "input": { "width": 1024, "height": 1024, "prompt": "shot in the style of sksfer, a turtle\\nshot in the style of sksfer, a shark", "scheduler": "LCM", "lora_scale": 0.8, "num_outputs": 1, "lora_weights": "https://pbxt.replicate.delivery/3wwmvGfvB4weYkJMAR2JJNMXu7RPtd8Hc5ONP3IP23fioXfGB/trained_model.tar", "batched_prompt": true, "guidance_scale": 2, "apply_watermark": true, "condition_scale": 0.45, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 6 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-11-14T17:45:06.131126Z", "created_at": "2023-11-14T17:45:01.694236Z", "data_removed": false, "error": null, "id": "cnp463tbdv7stxo4j6fyuocan4", "input": { "width": 1024, "height": 1024, "prompt": "shot in the style of sksfer, a turtle\nshot in the style of sksfer, a shark", "scheduler": "LCM", "lora_scale": 0.8, "num_outputs": 1, "lora_weights": "https://pbxt.replicate.delivery/3wwmvGfvB4weYkJMAR2JJNMXu7RPtd8Hc5ONP3IP23fioXfGB/trained_model.tar", "batched_prompt": true, "guidance_scale": 2, "apply_watermark": true, "condition_scale": 0.45, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 6 }, "logs": "Using seed: 55809\nskipping loading .. weights already loaded\nPrompt: shot in the style of <s0><s1>, a turtle\nshot in the style of <s0><s1>, a shark\ntxt2img mode\nThe config attributes {'skip_prk_steps': True} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.\n 0%| | 0/6 [00:00<?, ?it/s]\n 17%|█▋ | 1/6 [00:00<00:01, 3.53it/s]\n 33%|███▎ | 2/6 [00:00<00:01, 3.57it/s]\n 50%|█████ | 3/6 [00:00<00:00, 3.58it/s]\n 67%|██████▋ | 4/6 [00:01<00:00, 3.58it/s]\n 83%|████████▎ | 5/6 [00:01<00:00, 3.58it/s]\n100%|██████████| 6/6 [00:01<00:00, 3.58it/s]\n100%|██████████| 6/6 [00:01<00:00, 3.58it/s]", "metrics": { "predict_time": 4.420398, "total_time": 4.43689 }, "output": [ "https://replicate.delivery/pbxt/PafGz8HNYfn33EmPNia9Jgzf20VyZ5EKJUBv5wfautMGCZhHB/out-0.png", "https://replicate.delivery/pbxt/eSEOB2syOpXqTitL99fHW8fngsadla7EqTVgH2f96bQECZhHB/out-1.png" ], "started_at": "2023-11-14T17:45:01.710728Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/cnp463tbdv7stxo4j6fyuocan4", "cancel": "https://api.replicate.com/v1/predictions/cnp463tbdv7stxo4j6fyuocan4/cancel" }, "version": "d9db096aec79855d1f42d2bd4fc89f2b1ddf7dcd00118a0e21b8f1d5c03be099" }Generated inUsing seed: 55809 skipping loading .. weights already loaded Prompt: shot in the style of <s0><s1>, a turtle shot in the style of <s0><s1>, a shark txt2img mode The config attributes {'skip_prk_steps': True} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file. 0%| | 0/6 [00:00<?, ?it/s] 17%|█▋ | 1/6 [00:00<00:01, 3.53it/s] 33%|███▎ | 2/6 [00:00<00:01, 3.57it/s] 50%|█████ | 3/6 [00:00<00:00, 3.58it/s] 67%|██████▋ | 4/6 [00:01<00:00, 3.58it/s] 83%|████████▎ | 5/6 [00:01<00:00, 3.58it/s] 100%|██████████| 6/6 [00:01<00:00, 3.58it/s] 100%|██████████| 6/6 [00:01<00:00, 3.58it/s]
Want to make some of these yourself?
Run this model
