prompthero
/
funko-diffusion
Stable Diffusion fine tuned on Funko Pop
- Public
- 7.7K runs
-
A100 (80GB)
- Paper
Prediction
prompthero/funko-diffusion:85a9b91cIDinvsx64khzgo3dd6xvtcty2w6eStatusSucceededSourceWebHardware–Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- funko style samurai, intricate details, cinematic lighting, art station
- num_outputs
- 1
- guidance_scale
- "7"
- num_inference_steps
- "70"
{ "width": 512, "height": 512, "prompt": "funko style samurai, intricate details, cinematic lighting, art station", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "70" }Install Replicate’s Node.js client library:npm install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run prompthero/funko-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "prompthero/funko-diffusion:85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8", { input: { width: 512, height: 512, prompt: "funko style samurai, intricate details, cinematic lighting, art station", num_outputs: 1, guidance_scale: "7", num_inference_steps: "70" } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:import replicateRun prompthero/funko-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "prompthero/funko-diffusion:85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8", input={ "width": 512, "height": 512, "prompt": "funko style samurai, intricate details, cinematic lighting, art station", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "70" } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run prompthero/funko-diffusion 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": "85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8", "input": { "width": 512, "height": 512, "prompt": "funko style samurai, intricate details, cinematic lighting, art station", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "70" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/prompthero/funko-diffusion@sha256:85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="funko style samurai, intricate details, cinematic lighting, art station"' \ -i 'num_outputs=1' \ -i 'guidance_scale="7"' \ -i 'num_inference_steps="70"'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/prompthero/funko-diffusion@sha256:85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "funko style samurai, intricate details, cinematic lighting, art station", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "70" } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2022-11-15T23:27:17.046731Z", "created_at": "2022-11-15T23:27:11.514671Z", "data_removed": false, "error": null, "id": "invsx64khzgo3dd6xvtcty2w6e", "input": { "width": 512, "height": 512, "prompt": "funko style samurai, intricate details, cinematic lighting, art station", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "70" }, "logs": "Using seed: 29975\nGlobal seed set to 29975\n 0%| | 0/70 [00:00<?, ?it/s]\n 3%|▎ | 2/70 [00:00<00:05, 12.76it/s]\n 6%|▌ | 4/70 [00:00<00:04, 13.39it/s]\n 9%|▊ | 6/70 [00:00<00:04, 13.74it/s]\n 11%|█▏ | 8/70 [00:00<00:04, 13.93it/s]\n 14%|█▍ | 10/70 [00:00<00:04, 14.03it/s]\n 17%|█▋ | 12/70 [00:00<00:04, 13.67it/s]\n 20%|██ | 14/70 [00:01<00:04, 13.74it/s]\n 23%|██▎ | 16/70 [00:01<00:03, 13.86it/s]\n 26%|██▌ | 18/70 [00:01<00:03, 13.80it/s]\n 29%|██▊ | 20/70 [00:01<00:03, 13.93it/s]\n 31%|███▏ | 22/70 [00:01<00:03, 13.99it/s]\n 34%|███▍ | 24/70 [00:01<00:03, 14.07it/s]\n 37%|███▋ | 26/70 [00:01<00:03, 13.83it/s]\n 40%|████ | 28/70 [00:02<00:03, 13.71it/s]\n 43%|████▎ | 30/70 [00:02<00:02, 13.82it/s]\n 46%|████▌ | 32/70 [00:02<00:02, 13.90it/s]\n 49%|████▊ | 34/70 [00:02<00:02, 13.97it/s]\n 51%|█████▏ | 36/70 [00:02<00:02, 13.99it/s]\n 54%|█████▍ | 38/70 [00:02<00:02, 14.04it/s]\n 57%|█████▋ | 40/70 [00:02<00:02, 13.98it/s]\n 60%|██████ | 42/70 [00:03<00:01, 14.06it/s]\n 63%|██████▎ | 44/70 [00:03<00:01, 14.13it/s]\n 66%|██████▌ | 46/70 [00:03<00:01, 14.19it/s]\n 69%|██████▊ | 48/70 [00:03<00:01, 14.22it/s]\n 71%|███████▏ | 50/70 [00:03<00:01, 14.24it/s]\n 74%|███████▍ | 52/70 [00:03<00:01, 14.24it/s]\n 77%|███████▋ | 54/70 [00:03<00:01, 14.16it/s]\n 80%|████████ | 56/70 [00:04<00:00, 14.16it/s]\n 83%|████████▎ | 58/70 [00:04<00:00, 14.11it/s]\n 86%|████████▌ | 60/70 [00:04<00:00, 14.17it/s]\n 89%|████████▊ | 62/70 [00:04<00:00, 14.18it/s]\n 91%|█████████▏| 64/70 [00:04<00:00, 14.22it/s]\n 94%|█████████▍| 66/70 [00:04<00:00, 14.25it/s]\n 97%|█████████▋| 68/70 [00:04<00:00, 14.20it/s]\n100%|██████████| 70/70 [00:05<00:00, 13.75it/s]\n100%|██████████| 70/70 [00:05<00:00, 13.97it/s]", "metrics": { "predict_time": 5.497116, "total_time": 5.53206 }, "output": [ "https://replicate.delivery/pbxt/8x94TXrayZ4jK1nE39E1mJrLUtiV3b4k84wHzGa0MWLVSHAE/out-0.png" ], "started_at": "2022-11-15T23:27:11.549615Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/invsx64khzgo3dd6xvtcty2w6e", "cancel": "https://api.replicate.com/v1/predictions/invsx64khzgo3dd6xvtcty2w6e/cancel" }, "version": "85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8" }Generated inUsing seed: 29975 Global seed set to 29975 0%| | 0/70 [00:00<?, ?it/s] 3%|▎ | 2/70 [00:00<00:05, 12.76it/s] 6%|▌ | 4/70 [00:00<00:04, 13.39it/s] 9%|▊ | 6/70 [00:00<00:04, 13.74it/s] 11%|█▏ | 8/70 [00:00<00:04, 13.93it/s] 14%|█▍ | 10/70 [00:00<00:04, 14.03it/s] 17%|█▋ | 12/70 [00:00<00:04, 13.67it/s] 20%|██ | 14/70 [00:01<00:04, 13.74it/s] 23%|██▎ | 16/70 [00:01<00:03, 13.86it/s] 26%|██▌ | 18/70 [00:01<00:03, 13.80it/s] 29%|██▊ | 20/70 [00:01<00:03, 13.93it/s] 31%|███▏ | 22/70 [00:01<00:03, 13.99it/s] 34%|███▍ | 24/70 [00:01<00:03, 14.07it/s] 37%|███▋ | 26/70 [00:01<00:03, 13.83it/s] 40%|████ | 28/70 [00:02<00:03, 13.71it/s] 43%|████▎ | 30/70 [00:02<00:02, 13.82it/s] 46%|████▌ | 32/70 [00:02<00:02, 13.90it/s] 49%|████▊ | 34/70 [00:02<00:02, 13.97it/s] 51%|█████▏ | 36/70 [00:02<00:02, 13.99it/s] 54%|█████▍ | 38/70 [00:02<00:02, 14.04it/s] 57%|█████▋ | 40/70 [00:02<00:02, 13.98it/s] 60%|██████ | 42/70 [00:03<00:01, 14.06it/s] 63%|██████▎ | 44/70 [00:03<00:01, 14.13it/s] 66%|██████▌ | 46/70 [00:03<00:01, 14.19it/s] 69%|██████▊ | 48/70 [00:03<00:01, 14.22it/s] 71%|███████▏ | 50/70 [00:03<00:01, 14.24it/s] 74%|███████▍ | 52/70 [00:03<00:01, 14.24it/s] 77%|███████▋ | 54/70 [00:03<00:01, 14.16it/s] 80%|████████ | 56/70 [00:04<00:00, 14.16it/s] 83%|████████▎ | 58/70 [00:04<00:00, 14.11it/s] 86%|████████▌ | 60/70 [00:04<00:00, 14.17it/s] 89%|████████▊ | 62/70 [00:04<00:00, 14.18it/s] 91%|█████████▏| 64/70 [00:04<00:00, 14.22it/s] 94%|█████████▍| 66/70 [00:04<00:00, 14.25it/s] 97%|█████████▋| 68/70 [00:04<00:00, 14.20it/s] 100%|██████████| 70/70 [00:05<00:00, 13.75it/s] 100%|██████████| 70/70 [00:05<00:00, 13.97it/s]Prediction
prompthero/funko-diffusion:85a9b91cIDa7gksfyu3fcs3glxa7fz3l7pseStatusSucceededSourceWebHardware–Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- funko style cute anime girl wearing a fox hat
- num_outputs
- 1
- guidance_scale
- "7"
- num_inference_steps
- "50"
{ "width": 512, "height": 512, "prompt": "funko style cute anime girl wearing a fox hat", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "50" }Install Replicate’s Node.js client library:npm install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run prompthero/funko-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "prompthero/funko-diffusion:85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8", { input: { width: 512, height: 512, prompt: "funko style cute anime girl wearing a fox hat", num_outputs: 1, guidance_scale: "7", num_inference_steps: "50" } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:import replicateRun prompthero/funko-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "prompthero/funko-diffusion:85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8", input={ "width": 512, "height": 512, "prompt": "funko style cute anime girl wearing a fox hat", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "50" } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run prompthero/funko-diffusion 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": "85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8", "input": { "width": 512, "height": 512, "prompt": "funko style cute anime girl wearing a fox hat", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "50" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/prompthero/funko-diffusion@sha256:85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="funko style cute anime girl wearing a fox hat"' \ -i 'num_outputs=1' \ -i 'guidance_scale="7"' \ -i 'num_inference_steps="50"'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/prompthero/funko-diffusion@sha256:85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "funko style cute anime girl wearing a fox hat", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "50" } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2022-11-15T23:30:24.210907Z", "created_at": "2022-11-15T23:30:20.081447Z", "data_removed": false, "error": null, "id": "a7gksfyu3fcs3glxa7fz3l7pse", "input": { "width": 512, "height": 512, "prompt": "funko style cute anime girl wearing a fox hat", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "50" }, "logs": "Using seed: 10471\nGlobal seed set to 10471\n 0%| | 0/50 [00:00<?, ?it/s]\n 4%|▍ | 2/50 [00:00<00:03, 12.57it/s]\n 8%|▊ | 4/50 [00:00<00:03, 13.02it/s]\n 12%|█▏ | 6/50 [00:00<00:03, 13.48it/s]\n 16%|█▌ | 8/50 [00:00<00:03, 13.80it/s]\n 20%|██ | 10/50 [00:00<00:02, 13.97it/s]\n 24%|██▍ | 12/50 [00:00<00:02, 14.11it/s]\n 28%|██▊ | 14/50 [00:01<00:02, 14.21it/s]\n 32%|███▏ | 16/50 [00:01<00:02, 14.28it/s]\n 36%|███▌ | 18/50 [00:01<00:02, 14.09it/s]\n 40%|████ | 20/50 [00:01<00:02, 14.18it/s]\n 44%|████▍ | 22/50 [00:01<00:01, 14.28it/s]\n 48%|████▊ | 24/50 [00:01<00:01, 14.33it/s]\n 52%|█████▏ | 26/50 [00:01<00:01, 14.18it/s]\n 56%|█████▌ | 28/50 [00:01<00:01, 14.24it/s]\n 60%|██████ | 30/50 [00:02<00:01, 14.29it/s]\n 64%|██████▍ | 32/50 [00:02<00:01, 14.07it/s]\n 68%|██████▊ | 34/50 [00:02<00:01, 14.07it/s]\n 72%|███████▏ | 36/50 [00:02<00:00, 14.11it/s]\n 76%|███████▌ | 38/50 [00:02<00:00, 14.12it/s]\n 80%|████████ | 40/50 [00:02<00:00, 14.15it/s]\n 84%|████████▍ | 42/50 [00:02<00:00, 14.16it/s]\n 88%|████████▊ | 44/50 [00:03<00:00, 14.20it/s]\n 92%|█████████▏| 46/50 [00:03<00:00, 14.04it/s]\n 96%|█████████▌| 48/50 [00:03<00:00, 14.07it/s]\n100%|██████████| 50/50 [00:03<00:00, 14.13it/s]\n100%|██████████| 50/50 [00:03<00:00, 14.08it/s]", "metrics": { "predict_time": 4.088951, "total_time": 4.12946 }, "output": [ "https://replicate.delivery/pbxt/eNlIp5fWsGt7oki3JUQK4HyufDFvJqMIlbOD1DLos9Dfw0BAB/out-0.png" ], "started_at": "2022-11-15T23:30:20.121956Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/a7gksfyu3fcs3glxa7fz3l7pse", "cancel": "https://api.replicate.com/v1/predictions/a7gksfyu3fcs3glxa7fz3l7pse/cancel" }, "version": "85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8" }Generated inUsing seed: 10471 Global seed set to 10471 0%| | 0/50 [00:00<?, ?it/s] 4%|▍ | 2/50 [00:00<00:03, 12.57it/s] 8%|▊ | 4/50 [00:00<00:03, 13.02it/s] 12%|█▏ | 6/50 [00:00<00:03, 13.48it/s] 16%|█▌ | 8/50 [00:00<00:03, 13.80it/s] 20%|██ | 10/50 [00:00<00:02, 13.97it/s] 24%|██▍ | 12/50 [00:00<00:02, 14.11it/s] 28%|██▊ | 14/50 [00:01<00:02, 14.21it/s] 32%|███▏ | 16/50 [00:01<00:02, 14.28it/s] 36%|███▌ | 18/50 [00:01<00:02, 14.09it/s] 40%|████ | 20/50 [00:01<00:02, 14.18it/s] 44%|████▍ | 22/50 [00:01<00:01, 14.28it/s] 48%|████▊ | 24/50 [00:01<00:01, 14.33it/s] 52%|█████▏ | 26/50 [00:01<00:01, 14.18it/s] 56%|█████▌ | 28/50 [00:01<00:01, 14.24it/s] 60%|██████ | 30/50 [00:02<00:01, 14.29it/s] 64%|██████▍ | 32/50 [00:02<00:01, 14.07it/s] 68%|██████▊ | 34/50 [00:02<00:01, 14.07it/s] 72%|███████▏ | 36/50 [00:02<00:00, 14.11it/s] 76%|███████▌ | 38/50 [00:02<00:00, 14.12it/s] 80%|████████ | 40/50 [00:02<00:00, 14.15it/s] 84%|████████▍ | 42/50 [00:02<00:00, 14.16it/s] 88%|████████▊ | 44/50 [00:03<00:00, 14.20it/s] 92%|█████████▏| 46/50 [00:03<00:00, 14.04it/s] 96%|█████████▌| 48/50 [00:03<00:00, 14.07it/s] 100%|██████████| 50/50 [00:03<00:00, 14.13it/s] 100%|██████████| 50/50 [00:03<00:00, 14.08it/s]Prediction
prompthero/funko-diffusion:85a9b91cIDvfnuw7hmerd55hz3r24gmo4ylyStatusSucceededSourceWebHardware–Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- funko style of hyperrealistic full length portrait of gorgeous goddess| standing in field full of flowers| intricate| elegant| realistic| cinematic| character design| concept art| highly detailed| illustration| digital art| digital painting| depth of field
- num_outputs
- 1
- guidance_scale
- "7"
- num_inference_steps
- "50"
{ "width": 512, "height": 512, "prompt": "funko style of hyperrealistic full length portrait of gorgeous goddess| standing in field full of flowers| intricate| elegant| realistic| cinematic| character design| concept art| highly detailed| illustration| digital art| digital painting| depth of field", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "50" }Install Replicate’s Node.js client library:npm install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run prompthero/funko-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "prompthero/funko-diffusion:85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8", { input: { width: 512, height: 512, prompt: "funko style of hyperrealistic full length portrait of gorgeous goddess| standing in field full of flowers| intricate| elegant| realistic| cinematic| character design| concept art| highly detailed| illustration| digital art| digital painting| depth of field", num_outputs: 1, guidance_scale: "7", num_inference_steps: "50" } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:import replicateRun prompthero/funko-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "prompthero/funko-diffusion:85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8", input={ "width": 512, "height": 512, "prompt": "funko style of hyperrealistic full length portrait of gorgeous goddess| standing in field full of flowers| intricate| elegant| realistic| cinematic| character design| concept art| highly detailed| illustration| digital art| digital painting| depth of field", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "50" } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run prompthero/funko-diffusion 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": "85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8", "input": { "width": 512, "height": 512, "prompt": "funko style of hyperrealistic full length portrait of gorgeous goddess| standing in field full of flowers| intricate| elegant| realistic| cinematic| character design| concept art| highly detailed| illustration| digital art| digital painting| depth of field", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "50" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/prompthero/funko-diffusion@sha256:85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="funko style of hyperrealistic full length portrait of gorgeous goddess| standing in field full of flowers| intricate| elegant| realistic| cinematic| character design| concept art| highly detailed| illustration| digital art| digital painting| depth of field"' \ -i 'num_outputs=1' \ -i 'guidance_scale="7"' \ -i 'num_inference_steps="50"'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/prompthero/funko-diffusion@sha256:85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "funko style of hyperrealistic full length portrait of gorgeous goddess| standing in field full of flowers| intricate| elegant| realistic| cinematic| character design| concept art| highly detailed| illustration| digital art| digital painting| depth of field", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "50" } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2022-11-15T23:31:03.176427Z", "created_at": "2022-11-15T23:30:59.030571Z", "data_removed": false, "error": null, "id": "vfnuw7hmerd55hz3r24gmo4yly", "input": { "width": 512, "height": 512, "prompt": "funko style of hyperrealistic full length portrait of gorgeous goddess| standing in field full of flowers| intricate| elegant| realistic| cinematic| character design| concept art| highly detailed| illustration| digital art| digital painting| depth of field", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "50" }, "logs": "Using seed: 1755\nGlobal seed set to 1755\n 0%| | 0/50 [00:00<?, ?it/s]\n 4%|▍ | 2/50 [00:00<00:03, 13.06it/s]\n 8%|▊ | 4/50 [00:00<00:03, 13.24it/s]\n 12%|█▏ | 6/50 [00:00<00:03, 13.66it/s]\n 16%|█▌ | 8/50 [00:00<00:03, 13.77it/s]\n 20%|██ | 10/50 [00:00<00:02, 13.85it/s]\n 24%|██▍ | 12/50 [00:00<00:02, 13.93it/s]\n 28%|██▊ | 14/50 [00:01<00:02, 13.98it/s]\n 32%|███▏ | 16/50 [00:01<00:02, 14.07it/s]\n 36%|███▌ | 18/50 [00:01<00:02, 14.10it/s]\n 40%|████ | 20/50 [00:01<00:02, 14.07it/s]\n 44%|████▍ | 22/50 [00:01<00:02, 13.97it/s]\n 48%|████▊ | 24/50 [00:01<00:01, 14.04it/s]\n 52%|█████▏ | 26/50 [00:01<00:01, 14.03it/s]\n 56%|█████▌ | 28/50 [00:02<00:01, 14.07it/s]\n 60%|██████ | 30/50 [00:02<00:01, 14.07it/s]\n 64%|██████▍ | 32/50 [00:02<00:01, 13.98it/s]\n 68%|██████▊ | 34/50 [00:02<00:01, 13.73it/s]\n 72%|███████▏ | 36/50 [00:02<00:01, 13.80it/s]\n 76%|███████▌ | 38/50 [00:02<00:00, 13.86it/s]\n 80%|████████ | 40/50 [00:02<00:00, 13.98it/s]\n 84%|████████▍ | 42/50 [00:03<00:00, 14.01it/s]\n 88%|████████▊ | 44/50 [00:03<00:00, 14.06it/s]\n 92%|█████████▏| 46/50 [00:03<00:00, 14.00it/s]\n 96%|█████████▌| 48/50 [00:03<00:00, 13.91it/s]\n100%|██████████| 50/50 [00:03<00:00, 13.93it/s]\n100%|██████████| 50/50 [00:03<00:00, 13.92it/s]", "metrics": { "predict_time": 4.11105, "total_time": 4.145856 }, "output": [ "https://replicate.delivery/pbxt/AKYKbvhgl06rPdPdFq6nJYMJpzTsQOEQiiJWh8x5ncqNTHAE/out-0.png" ], "started_at": "2022-11-15T23:30:59.065377Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/vfnuw7hmerd55hz3r24gmo4yly", "cancel": "https://api.replicate.com/v1/predictions/vfnuw7hmerd55hz3r24gmo4yly/cancel" }, "version": "85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8" }Generated inUsing seed: 1755 Global seed set to 1755 0%| | 0/50 [00:00<?, ?it/s] 4%|▍ | 2/50 [00:00<00:03, 13.06it/s] 8%|▊ | 4/50 [00:00<00:03, 13.24it/s] 12%|█▏ | 6/50 [00:00<00:03, 13.66it/s] 16%|█▌ | 8/50 [00:00<00:03, 13.77it/s] 20%|██ | 10/50 [00:00<00:02, 13.85it/s] 24%|██▍ | 12/50 [00:00<00:02, 13.93it/s] 28%|██▊ | 14/50 [00:01<00:02, 13.98it/s] 32%|███▏ | 16/50 [00:01<00:02, 14.07it/s] 36%|███▌ | 18/50 [00:01<00:02, 14.10it/s] 40%|████ | 20/50 [00:01<00:02, 14.07it/s] 44%|████▍ | 22/50 [00:01<00:02, 13.97it/s] 48%|████▊ | 24/50 [00:01<00:01, 14.04it/s] 52%|█████▏ | 26/50 [00:01<00:01, 14.03it/s] 56%|█████▌ | 28/50 [00:02<00:01, 14.07it/s] 60%|██████ | 30/50 [00:02<00:01, 14.07it/s] 64%|██████▍ | 32/50 [00:02<00:01, 13.98it/s] 68%|██████▊ | 34/50 [00:02<00:01, 13.73it/s] 72%|███████▏ | 36/50 [00:02<00:01, 13.80it/s] 76%|███████▌ | 38/50 [00:02<00:00, 13.86it/s] 80%|████████ | 40/50 [00:02<00:00, 13.98it/s] 84%|████████▍ | 42/50 [00:03<00:00, 14.01it/s] 88%|████████▊ | 44/50 [00:03<00:00, 14.06it/s] 92%|█████████▏| 46/50 [00:03<00:00, 14.00it/s] 96%|█████████▌| 48/50 [00:03<00:00, 13.91it/s] 100%|██████████| 50/50 [00:03<00:00, 13.93it/s] 100%|██████████| 50/50 [00:03<00:00, 13.92it/s]Prediction
prompthero/funko-diffusion:85a9b91cID6wcxyhbot5bghancnp3rpzaufuStatusSucceededSourceWebHardware–Total durationCreatedInput
- width
- 512
- height
- 512
- prompt
- funko style of hyperrealistic full length portrait of gorgeous goddess| standing in field full of flowers| intricate| elegant| realistic| cinematic| character design| concept art| highly detailed| illustration| digital art| digital painting| depth of field
- num_outputs
- 1
- guidance_scale
- "7"
- num_inference_steps
- "50"
{ "width": 512, "height": 512, "prompt": "funko style of hyperrealistic full length portrait of gorgeous goddess| standing in field full of flowers| intricate| elegant| realistic| cinematic| character design| concept art| highly detailed| illustration| digital art| digital painting| depth of field", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "50" }Install Replicate’s Node.js client library:npm install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run prompthero/funko-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "prompthero/funko-diffusion:85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8", { input: { width: 512, height: 512, prompt: "funko style of hyperrealistic full length portrait of gorgeous goddess| standing in field full of flowers| intricate| elegant| realistic| cinematic| character design| concept art| highly detailed| illustration| digital art| digital painting| depth of field", num_outputs: 1, guidance_scale: "7", num_inference_steps: "50" } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:import replicateRun prompthero/funko-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "prompthero/funko-diffusion:85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8", input={ "width": 512, "height": 512, "prompt": "funko style of hyperrealistic full length portrait of gorgeous goddess| standing in field full of flowers| intricate| elegant| realistic| cinematic| character design| concept art| highly detailed| illustration| digital art| digital painting| depth of field", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "50" } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run prompthero/funko-diffusion 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": "85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8", "input": { "width": 512, "height": 512, "prompt": "funko style of hyperrealistic full length portrait of gorgeous goddess| standing in field full of flowers| intricate| elegant| realistic| cinematic| character design| concept art| highly detailed| illustration| digital art| digital painting| depth of field", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "50" } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/prompthero/funko-diffusion@sha256:85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8 \ -i 'width=512' \ -i 'height=512' \ -i 'prompt="funko style of hyperrealistic full length portrait of gorgeous goddess| standing in field full of flowers| intricate| elegant| realistic| cinematic| character design| concept art| highly detailed| illustration| digital art| digital painting| depth of field"' \ -i 'num_outputs=1' \ -i 'guidance_scale="7"' \ -i 'num_inference_steps="50"'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/prompthero/funko-diffusion@sha256:85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 512, "height": 512, "prompt": "funko style of hyperrealistic full length portrait of gorgeous goddess| standing in field full of flowers| intricate| elegant| realistic| cinematic| character design| concept art| highly detailed| illustration| digital art| digital painting| depth of field", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "50" } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2022-11-15T23:31:30.944025Z", "created_at": "2022-11-15T23:31:26.380012Z", "data_removed": false, "error": null, "id": "6wcxyhbot5bghancnp3rpzaufu", "input": { "width": 512, "height": 512, "prompt": "funko style of hyperrealistic full length portrait of gorgeous goddess| standing in field full of flowers| intricate| elegant| realistic| cinematic| character design| concept art| highly detailed| illustration| digital art| digital painting| depth of field", "num_outputs": 1, "guidance_scale": "7", "num_inference_steps": "50" }, "logs": "Using seed: 25889\nGlobal seed set to 25889\n 0%| | 0/50 [00:00<?, ?it/s]\n 4%|▍ | 2/50 [00:00<00:03, 13.45it/s]\n 8%|▊ | 4/50 [00:00<00:03, 13.67it/s]\n 12%|█▏ | 6/50 [00:00<00:03, 13.90it/s]\n 16%|█▌ | 8/50 [00:00<00:02, 14.04it/s]\n 20%|██ | 10/50 [00:00<00:02, 14.12it/s]\n 24%|██▍ | 12/50 [00:00<00:02, 14.06it/s]\n 28%|██▊ | 14/50 [00:01<00:02, 13.51it/s]\n 32%|███▏ | 16/50 [00:01<00:02, 13.64it/s]\n 36%|███▌ | 18/50 [00:01<00:02, 13.73it/s]\n 40%|████ | 20/50 [00:01<00:02, 13.88it/s]\n 44%|████▍ | 22/50 [00:01<00:01, 14.01it/s]\n 48%|████▊ | 24/50 [00:01<00:01, 13.97it/s]\n 52%|█████▏ | 26/50 [00:01<00:01, 14.08it/s]\n 56%|█████▌ | 28/50 [00:02<00:01, 13.91it/s]\n 60%|██████ | 30/50 [00:02<00:01, 13.58it/s]\n 64%|██████▍ | 32/50 [00:02<00:01, 13.73it/s]\n 68%|██████▊ | 34/50 [00:02<00:01, 13.88it/s]\n 72%|███████▏ | 36/50 [00:02<00:01, 13.86it/s]\n 76%|███████▌ | 38/50 [00:02<00:00, 13.91it/s]\n 80%|████████ | 40/50 [00:02<00:00, 14.07it/s]\n 84%|████████▍ | 42/50 [00:03<00:00, 13.85it/s]\n 88%|████████▊ | 44/50 [00:03<00:00, 13.92it/s]\n 92%|█████████▏| 46/50 [00:03<00:00, 14.07it/s]\n 96%|█████████▌| 48/50 [00:03<00:00, 14.03it/s]\n100%|██████████| 50/50 [00:03<00:00, 14.02it/s]\n100%|██████████| 50/50 [00:03<00:00, 13.90it/s]", "metrics": { "predict_time": 4.529426, "total_time": 4.564013 }, "output": [ "https://replicate.delivery/pbxt/jScIkNLGOVq2G5wVjS6Y4oBlKmXgvRfjiUAfjQFTWVISNdAQA/out-0.png" ], "started_at": "2022-11-15T23:31:26.414599Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/6wcxyhbot5bghancnp3rpzaufu", "cancel": "https://api.replicate.com/v1/predictions/6wcxyhbot5bghancnp3rpzaufu/cancel" }, "version": "85a9b91c85d1a6d74a045286af193530215cb384e55ec1eaab5611a8e36030f8" }Generated inUsing seed: 25889 Global seed set to 25889 0%| | 0/50 [00:00<?, ?it/s] 4%|▍ | 2/50 [00:00<00:03, 13.45it/s] 8%|▊ | 4/50 [00:00<00:03, 13.67it/s] 12%|█▏ | 6/50 [00:00<00:03, 13.90it/s] 16%|█▌ | 8/50 [00:00<00:02, 14.04it/s] 20%|██ | 10/50 [00:00<00:02, 14.12it/s] 24%|██▍ | 12/50 [00:00<00:02, 14.06it/s] 28%|██▊ | 14/50 [00:01<00:02, 13.51it/s] 32%|███▏ | 16/50 [00:01<00:02, 13.64it/s] 36%|███▌ | 18/50 [00:01<00:02, 13.73it/s] 40%|████ | 20/50 [00:01<00:02, 13.88it/s] 44%|████▍ | 22/50 [00:01<00:01, 14.01it/s] 48%|████▊ | 24/50 [00:01<00:01, 13.97it/s] 52%|█████▏ | 26/50 [00:01<00:01, 14.08it/s] 56%|█████▌ | 28/50 [00:02<00:01, 13.91it/s] 60%|██████ | 30/50 [00:02<00:01, 13.58it/s] 64%|██████▍ | 32/50 [00:02<00:01, 13.73it/s] 68%|██████▊ | 34/50 [00:02<00:01, 13.88it/s] 72%|███████▏ | 36/50 [00:02<00:01, 13.86it/s] 76%|███████▌ | 38/50 [00:02<00:00, 13.91it/s] 80%|████████ | 40/50 [00:02<00:00, 14.07it/s] 84%|████████▍ | 42/50 [00:03<00:00, 13.85it/s] 88%|████████▊ | 44/50 [00:03<00:00, 13.92it/s] 92%|█████████▏| 46/50 [00:03<00:00, 14.07it/s] 96%|█████████▌| 48/50 [00:03<00:00, 14.03it/s] 100%|██████████| 50/50 [00:03<00:00, 14.02it/s] 100%|██████████| 50/50 [00:03<00:00, 13.90it/s]
Want to make some of these yourself?
Run this model