chenxwh
/
sdxl-flash
Fast sdxl with higher quality
- Public
- 640.3K runs
-
L40S
Prediction
chenxwh/sdxl-flash:001bb811IDv2eyr8xqg9rgm0cfppntg8fgwgStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedby @chenxwhInput
- width
- 1024
- height
- 1024
- prompt
- a cat eating a piece of cheese
- guidance_scale
- 3
- negative_prompt
- (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW
- num_inference_steps
- 15
{ "width": 1024, "height": 1024, "prompt": "a cat eating a piece of cheese", "guidance_scale": 3, "negative_prompt": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", "num_inference_steps": 15 }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/sdxl-flash using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/sdxl-flash:001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1", { input: { width: 1024, height: 1024, prompt: "a cat eating a piece of cheese", guidance_scale: 3, negative_prompt: "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", num_inference_steps: 15 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/sdxl-flash using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/sdxl-flash:001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1", input={ "width": 1024, "height": 1024, "prompt": "a cat eating a piece of cheese", "guidance_scale": 3, "negative_prompt": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", "num_inference_steps": 15 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/sdxl-flash 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": "001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1", "input": { "width": 1024, "height": 1024, "prompt": "a cat eating a piece of cheese", "guidance_scale": 3, "negative_prompt": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", "num_inference_steps": 15 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cog
If you don’t have Homebrew, there are other installation options available.
Pull and run chenxwh/sdxl-flash using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/chenxwh/sdxl-flash@sha256:001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="a cat eating a piece of cheese"' \ -i 'guidance_scale=3' \ -i 'negative_prompt="(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW"' \ -i 'num_inference_steps=15'
To learn more, take a look at the Cog documentation.
Pull and run chenxwh/sdxl-flash using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/chenxwh/sdxl-flash@sha256:001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "a cat eating a piece of cheese", "guidance_scale": 3, "negative_prompt": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", "num_inference_steps": 15 } }' \ http://localhost:5000/predictions
Output
{ "completed_at": "2024-05-26T16:11:26.070725Z", "created_at": "2024-05-26T16:11:20.834000Z", "data_removed": false, "error": null, "id": "v2eyr8xqg9rgm0cfppntg8fgwg", "input": { "width": 1024, "height": 1024, "prompt": "a cat eating a piece of cheese", "guidance_scale": 3, "negative_prompt": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", "num_inference_steps": 15 }, "logs": "Using seed: 36273\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:00<00:02, 5.36it/s]\n 13%|█▎ | 2/15 [00:00<00:02, 5.31it/s]\n 20%|██ | 3/15 [00:00<00:02, 5.29it/s]\n 27%|██▋ | 4/15 [00:00<00:02, 5.28it/s]\n 33%|███▎ | 5/15 [00:00<00:01, 5.27it/s]\n 40%|████ | 6/15 [00:01<00:01, 5.26it/s]\n 47%|████▋ | 7/15 [00:01<00:01, 5.26it/s]\n 53%|█████▎ | 8/15 [00:01<00:01, 5.26it/s]\n 60%|██████ | 9/15 [00:01<00:01, 5.25it/s]\n 67%|██████▋ | 10/15 [00:01<00:00, 5.25it/s]\n 73%|███████▎ | 11/15 [00:02<00:00, 5.25it/s]\n 80%|████████ | 12/15 [00:02<00:00, 5.25it/s]\n 87%|████████▋ | 13/15 [00:02<00:00, 5.25it/s]\n 93%|█████████▎| 14/15 [00:02<00:00, 5.25it/s]\n100%|██████████| 15/15 [00:02<00:00, 5.25it/s]\n100%|██████████| 15/15 [00:02<00:00, 5.26it/s]", "metrics": { "predict_time": 5.182221, "total_time": 5.236725 }, "output": "https://replicate.delivery/pbxt/evVDJfQiwNrSmkvmtV6LnH2iAewmgzBlQxDOWfePufgHLREuE/out.png", "started_at": "2024-05-26T16:11:20.888504Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/v2eyr8xqg9rgm0cfppntg8fgwg", "cancel": "https://api.replicate.com/v1/predictions/v2eyr8xqg9rgm0cfppntg8fgwg/cancel" }, "version": "7c43fc4ceba891974c9f893763cd7c06d43d1b0e5f48aa891e5ada06d2e623ba" }
Generated inUsing seed: 36273 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:00<00:02, 5.36it/s] 13%|█▎ | 2/15 [00:00<00:02, 5.31it/s] 20%|██ | 3/15 [00:00<00:02, 5.29it/s] 27%|██▋ | 4/15 [00:00<00:02, 5.28it/s] 33%|███▎ | 5/15 [00:00<00:01, 5.27it/s] 40%|████ | 6/15 [00:01<00:01, 5.26it/s] 47%|████▋ | 7/15 [00:01<00:01, 5.26it/s] 53%|█████▎ | 8/15 [00:01<00:01, 5.26it/s] 60%|██████ | 9/15 [00:01<00:01, 5.25it/s] 67%|██████▋ | 10/15 [00:01<00:00, 5.25it/s] 73%|███████▎ | 11/15 [00:02<00:00, 5.25it/s] 80%|████████ | 12/15 [00:02<00:00, 5.25it/s] 87%|████████▋ | 13/15 [00:02<00:00, 5.25it/s] 93%|█████████▎| 14/15 [00:02<00:00, 5.25it/s] 100%|██████████| 15/15 [00:02<00:00, 5.25it/s] 100%|██████████| 15/15 [00:02<00:00, 5.26it/s]
Prediction
chenxwh/sdxl-flash:001bb811ID5mvrjq1m2drgj0cfppsswcweagStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- An alien grasping a sign board contain word 'Flash', sketch, detailed
- guidance_scale
- 3
- negative_prompt
- (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW
- num_inference_steps
- 15
{ "width": 1024, "height": 1024, "prompt": "An alien grasping a sign board contain word 'Flash', sketch, detailed", "guidance_scale": 3, "negative_prompt": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", "num_inference_steps": 15 }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/sdxl-flash using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/sdxl-flash:001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1", { input: { width: 1024, height: 1024, prompt: "An alien grasping a sign board contain word 'Flash', sketch, detailed", guidance_scale: 3, negative_prompt: "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", num_inference_steps: 15 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/sdxl-flash using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/sdxl-flash:001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1", input={ "width": 1024, "height": 1024, "prompt": "An alien grasping a sign board contain word 'Flash', sketch, detailed", "guidance_scale": 3, "negative_prompt": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", "num_inference_steps": 15 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/sdxl-flash 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": "001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1", "input": { "width": 1024, "height": 1024, "prompt": "An alien grasping a sign board contain word \'Flash\', sketch, detailed", "guidance_scale": 3, "negative_prompt": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", "num_inference_steps": 15 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cog
If you don’t have Homebrew, there are other installation options available.
Pull and run chenxwh/sdxl-flash using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/chenxwh/sdxl-flash@sha256:001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1 \ -i 'width=1024' \ -i 'height=1024' \ -i $'prompt="An alien grasping a sign board contain word \'Flash\', sketch, detailed"' \ -i 'guidance_scale=3' \ -i 'negative_prompt="(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW"' \ -i 'num_inference_steps=15'
To learn more, take a look at the Cog documentation.
Pull and run chenxwh/sdxl-flash using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/chenxwh/sdxl-flash@sha256:001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "An alien grasping a sign board contain word \'Flash\', sketch, detailed", "guidance_scale": 3, "negative_prompt": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", "num_inference_steps": 15 } }' \ http://localhost:5000/predictions
Output
{ "completed_at": "2024-05-26T16:19:35.386341Z", "created_at": "2024-05-26T16:19:31.475000Z", "data_removed": false, "error": null, "id": "5mvrjq1m2drgj0cfppsswcweag", "input": { "width": 1024, "height": 1024, "prompt": "An alien grasping a sign board contain word 'Flash', sketch, detailed", "guidance_scale": 3, "negative_prompt": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", "num_inference_steps": 15 }, "logs": "Using seed: 58253\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:00<00:02, 5.39it/s]\n 13%|█▎ | 2/15 [00:00<00:02, 5.37it/s]\n 20%|██ | 3/15 [00:00<00:02, 5.36it/s]\n 27%|██▋ | 4/15 [00:00<00:02, 5.35it/s]\n 33%|███▎ | 5/15 [00:00<00:01, 5.31it/s]\n 40%|████ | 6/15 [00:01<00:01, 5.30it/s]\n 47%|████▋ | 7/15 [00:01<00:01, 5.30it/s]\n 53%|█████▎ | 8/15 [00:01<00:01, 5.30it/s]\n 60%|██████ | 9/15 [00:01<00:01, 5.31it/s]\n 67%|██████▋ | 10/15 [00:01<00:00, 5.31it/s]\n 73%|███████▎ | 11/15 [00:02<00:00, 5.30it/s]\n 80%|████████ | 12/15 [00:02<00:00, 5.30it/s]\n 87%|████████▋ | 13/15 [00:02<00:00, 5.29it/s]\n 93%|█████████▎| 14/15 [00:02<00:00, 5.29it/s]\n100%|██████████| 15/15 [00:02<00:00, 5.29it/s]\n100%|██████████| 15/15 [00:02<00:00, 5.31it/s]", "metrics": { "predict_time": 3.903115, "total_time": 3.911341 }, "output": "https://replicate.delivery/pbxt/otjl8dFxCJpvLJegR2b1510WcJeGskQEalBXIDgXzssWMR4SA/out.png", "started_at": "2024-05-26T16:19:31.483226Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/5mvrjq1m2drgj0cfppsswcweag", "cancel": "https://api.replicate.com/v1/predictions/5mvrjq1m2drgj0cfppsswcweag/cancel" }, "version": "001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1" }
Generated inUsing seed: 58253 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:00<00:02, 5.39it/s] 13%|█▎ | 2/15 [00:00<00:02, 5.37it/s] 20%|██ | 3/15 [00:00<00:02, 5.36it/s] 27%|██▋ | 4/15 [00:00<00:02, 5.35it/s] 33%|███▎ | 5/15 [00:00<00:01, 5.31it/s] 40%|████ | 6/15 [00:01<00:01, 5.30it/s] 47%|████▋ | 7/15 [00:01<00:01, 5.30it/s] 53%|█████▎ | 8/15 [00:01<00:01, 5.30it/s] 60%|██████ | 9/15 [00:01<00:01, 5.31it/s] 67%|██████▋ | 10/15 [00:01<00:00, 5.31it/s] 73%|███████▎ | 11/15 [00:02<00:00, 5.30it/s] 80%|████████ | 12/15 [00:02<00:00, 5.30it/s] 87%|████████▋ | 13/15 [00:02<00:00, 5.29it/s] 93%|█████████▎| 14/15 [00:02<00:00, 5.29it/s] 100%|██████████| 15/15 [00:02<00:00, 5.29it/s] 100%|██████████| 15/15 [00:02<00:00, 5.31it/s]
Prediction
chenxwh/sdxl-flash:001bb811ID8838yzanmdrgm0cfppvsgpkb3cStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a rabbit made out of lego
- guidance_scale
- 3
- negative_prompt
- (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW
- num_inference_steps
- 15
{ "width": 1024, "height": 1024, "prompt": "a rabbit made out of lego", "guidance_scale": 3, "negative_prompt": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", "num_inference_steps": 15 }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/sdxl-flash using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/sdxl-flash:001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1", { input: { width: 1024, height: 1024, prompt: "a rabbit made out of lego", guidance_scale: 3, negative_prompt: "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", num_inference_steps: 15 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/sdxl-flash using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/sdxl-flash:001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1", input={ "width": 1024, "height": 1024, "prompt": "a rabbit made out of lego", "guidance_scale": 3, "negative_prompt": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", "num_inference_steps": 15 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/sdxl-flash 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": "001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1", "input": { "width": 1024, "height": 1024, "prompt": "a rabbit made out of lego", "guidance_scale": 3, "negative_prompt": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", "num_inference_steps": 15 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cog
If you don’t have Homebrew, there are other installation options available.
Pull and run chenxwh/sdxl-flash using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/chenxwh/sdxl-flash@sha256:001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="a rabbit made out of lego"' \ -i 'guidance_scale=3' \ -i 'negative_prompt="(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW"' \ -i 'num_inference_steps=15'
To learn more, take a look at the Cog documentation.
Pull and run chenxwh/sdxl-flash using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/chenxwh/sdxl-flash@sha256:001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "a rabbit made out of lego", "guidance_scale": 3, "negative_prompt": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", "num_inference_steps": 15 } }' \ http://localhost:5000/predictions
Output
{ "completed_at": "2024-05-26T16:24:06.300501Z", "created_at": "2024-05-26T16:24:02.211000Z", "data_removed": false, "error": null, "id": "8838yzanmdrgm0cfppvsgpkb3c", "input": { "width": 1024, "height": 1024, "prompt": "a rabbit made out of lego", "guidance_scale": 3, "negative_prompt": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", "num_inference_steps": 15 }, "logs": "Using seed: 58542\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:00<00:02, 5.35it/s]\n 13%|█▎ | 2/15 [00:00<00:02, 5.33it/s]\n 20%|██ | 3/15 [00:00<00:02, 5.34it/s]\n 27%|██▋ | 4/15 [00:00<00:02, 5.34it/s]\n 33%|███▎ | 5/15 [00:00<00:01, 5.33it/s]\n 40%|████ | 6/15 [00:01<00:01, 5.32it/s]\n 47%|████▋ | 7/15 [00:01<00:01, 5.32it/s]\n 53%|█████▎ | 8/15 [00:01<00:01, 5.32it/s]\n 60%|██████ | 9/15 [00:01<00:01, 5.32it/s]\n 67%|██████▋ | 10/15 [00:01<00:00, 5.32it/s]\n 73%|███████▎ | 11/15 [00:02<00:00, 5.31it/s]\n 80%|████████ | 12/15 [00:02<00:00, 5.32it/s]\n 87%|████████▋ | 13/15 [00:02<00:00, 5.32it/s]\n 93%|█████████▎| 14/15 [00:02<00:00, 5.32it/s]\n100%|██████████| 15/15 [00:02<00:00, 5.31it/s]\n100%|██████████| 15/15 [00:02<00:00, 5.32it/s]", "metrics": { "predict_time": 4.07974, "total_time": 4.089501 }, "output": "https://replicate.delivery/pbxt/hNfZpqplg7TVaiux0R9PxiBeorxxqL4vwgOhPmfdn6sLhiwlA/out.png", "started_at": "2024-05-26T16:24:02.220761Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/8838yzanmdrgm0cfppvsgpkb3c", "cancel": "https://api.replicate.com/v1/predictions/8838yzanmdrgm0cfppvsgpkb3c/cancel" }, "version": "001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1" }
Generated inUsing seed: 58542 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:00<00:02, 5.35it/s] 13%|█▎ | 2/15 [00:00<00:02, 5.33it/s] 20%|██ | 3/15 [00:00<00:02, 5.34it/s] 27%|██▋ | 4/15 [00:00<00:02, 5.34it/s] 33%|███▎ | 5/15 [00:00<00:01, 5.33it/s] 40%|████ | 6/15 [00:01<00:01, 5.32it/s] 47%|████▋ | 7/15 [00:01<00:01, 5.32it/s] 53%|█████▎ | 8/15 [00:01<00:01, 5.32it/s] 60%|██████ | 9/15 [00:01<00:01, 5.32it/s] 67%|██████▋ | 10/15 [00:01<00:00, 5.32it/s] 73%|███████▎ | 11/15 [00:02<00:00, 5.31it/s] 80%|████████ | 12/15 [00:02<00:00, 5.32it/s] 87%|████████▋ | 13/15 [00:02<00:00, 5.32it/s] 93%|█████████▎| 14/15 [00:02<00:00, 5.32it/s] 100%|██████████| 15/15 [00:02<00:00, 5.31it/s] 100%|██████████| 15/15 [00:02<00:00, 5.32it/s]
Prediction
chenxwh/sdxl-flash:001bb811ID7sfd86xb2nrgm0cfppwsq7px60StatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedby @chenxwhInput
- width
- 1024
- height
- 1024
- prompt
- a cartoon of a IRONMAN fighting with HULK, wall painting
- guidance_scale
- 3
- negative_prompt
- (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW
- num_inference_steps
- 15
{ "width": 1024, "height": 1024, "prompt": "a cartoon of a IRONMAN fighting with HULK, wall painting", "guidance_scale": 3, "negative_prompt": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", "num_inference_steps": 15 }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run chenxwh/sdxl-flash using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "chenxwh/sdxl-flash:001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1", { input: { width: 1024, height: 1024, prompt: "a cartoon of a IRONMAN fighting with HULK, wall painting", guidance_scale: 3, negative_prompt: "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", num_inference_steps: 15 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run chenxwh/sdxl-flash using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "chenxwh/sdxl-flash:001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1", input={ "width": 1024, "height": 1024, "prompt": "a cartoon of a IRONMAN fighting with HULK, wall painting", "guidance_scale": 3, "negative_prompt": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", "num_inference_steps": 15 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run chenxwh/sdxl-flash 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": "001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1", "input": { "width": 1024, "height": 1024, "prompt": "a cartoon of a IRONMAN fighting with HULK, wall painting", "guidance_scale": 3, "negative_prompt": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", "num_inference_steps": 15 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cog
If you don’t have Homebrew, there are other installation options available.
Pull and run chenxwh/sdxl-flash using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/chenxwh/sdxl-flash@sha256:001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="a cartoon of a IRONMAN fighting with HULK, wall painting"' \ -i 'guidance_scale=3' \ -i 'negative_prompt="(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW"' \ -i 'num_inference_steps=15'
To learn more, take a look at the Cog documentation.
Pull and run chenxwh/sdxl-flash using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/chenxwh/sdxl-flash@sha256:001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "a cartoon of a IRONMAN fighting with HULK, wall painting", "guidance_scale": 3, "negative_prompt": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", "num_inference_steps": 15 } }' \ http://localhost:5000/predictions
Output
{ "completed_at": "2024-05-26T16:26:39.167736Z", "created_at": "2024-05-26T16:26:35.157000Z", "data_removed": false, "error": null, "id": "7sfd86xb2nrgm0cfppwsq7px60", "input": { "width": 1024, "height": 1024, "prompt": "a cartoon of a IRONMAN fighting with HULK, wall painting", "guidance_scale": 3, "negative_prompt": "(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW", "num_inference_steps": 15 }, "logs": "Using seed: 16342\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:00<00:02, 5.35it/s]\n 13%|█▎ | 2/15 [00:00<00:02, 5.32it/s]\n 20%|██ | 3/15 [00:00<00:02, 5.31it/s]\n 27%|██▋ | 4/15 [00:00<00:02, 5.32it/s]\n 33%|███▎ | 5/15 [00:00<00:01, 5.30it/s]\n 40%|████ | 6/15 [00:01<00:01, 5.30it/s]\n 47%|████▋ | 7/15 [00:01<00:01, 5.30it/s]\n 53%|█████▎ | 8/15 [00:01<00:01, 5.31it/s]\n 60%|██████ | 9/15 [00:01<00:01, 5.31it/s]\n 67%|██████▋ | 10/15 [00:01<00:00, 5.30it/s]\n 73%|███████▎ | 11/15 [00:02<00:00, 5.30it/s]\n 80%|████████ | 12/15 [00:02<00:00, 5.30it/s]\n 87%|████████▋ | 13/15 [00:02<00:00, 5.30it/s]\n 93%|█████████▎| 14/15 [00:02<00:00, 5.30it/s]\n100%|██████████| 15/15 [00:02<00:00, 5.30it/s]\n100%|██████████| 15/15 [00:02<00:00, 5.30it/s]", "metrics": { "predict_time": 4.001051, "total_time": 4.010736 }, "output": "https://replicate.delivery/pbxt/pSklDUFpup6uJpDcHzwFnloNRrUMUZ6uomV1bxeNGOSfSR4SA/out.png", "started_at": "2024-05-26T16:26:35.166685Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/7sfd86xb2nrgm0cfppwsq7px60", "cancel": "https://api.replicate.com/v1/predictions/7sfd86xb2nrgm0cfppwsq7px60/cancel" }, "version": "001bb81139b01780380407b4106ac681df46108e002eafbeb9ccb2d8faca42e1" }
Generated inUsing seed: 16342 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:00<00:02, 5.35it/s] 13%|█▎ | 2/15 [00:00<00:02, 5.32it/s] 20%|██ | 3/15 [00:00<00:02, 5.31it/s] 27%|██▋ | 4/15 [00:00<00:02, 5.32it/s] 33%|███▎ | 5/15 [00:00<00:01, 5.30it/s] 40%|████ | 6/15 [00:01<00:01, 5.30it/s] 47%|████▋ | 7/15 [00:01<00:01, 5.30it/s] 53%|█████▎ | 8/15 [00:01<00:01, 5.31it/s] 60%|██████ | 9/15 [00:01<00:01, 5.31it/s] 67%|██████▋ | 10/15 [00:01<00:00, 5.30it/s] 73%|███████▎ | 11/15 [00:02<00:00, 5.30it/s] 80%|████████ | 12/15 [00:02<00:00, 5.30it/s] 87%|████████▋ | 13/15 [00:02<00:00, 5.30it/s] 93%|█████████▎| 14/15 [00:02<00:00, 5.30it/s] 100%|██████████| 15/15 [00:02<00:00, 5.30it/s] 100%|██████████| 15/15 [00:02<00:00, 5.30it/s]
Want to make some of these yourself?
Run this model