✋ This model is not published yet.
You can claim this model if you're @nerdyrodent on GitHub. Contact us.
nerdyrodent
/
vqgan-clip
Image Generation with VQGAN+CLIP
Prediction
nerdyrodent/vqgan-clip:eae144b3IDj7dexlgy4vgdnllhvm3zmxsbqyStatusSucceededSourceWebHardware–Total duration–CreatedInput
- image
- prompts
- A painting in the style of Picasso
- iterations
- 100
- display_frequency
- "20"
{ "image": "https://replicate.delivery/mgxm/e3110a03-8f77-415c-b953-d0f79674b1bb/VanGogh.jpg", "prompts": "A painting in the style of Picasso", "iterations": 100, "display_frequency": "20" }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 nerdyrodent/vqgan-clip using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "nerdyrodent/vqgan-clip:eae144b3ea325b889030f7919d0d1ca7b85be28ad496cf8c98f34f5440b8db32", { input: { image: "https://replicate.delivery/mgxm/e3110a03-8f77-415c-b953-d0f79674b1bb/VanGogh.jpg", prompts: "A painting in the style of Picasso", iterations: 100, display_frequency: "20" } } ); 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 nerdyrodent/vqgan-clip using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "nerdyrodent/vqgan-clip:eae144b3ea325b889030f7919d0d1ca7b85be28ad496cf8c98f34f5440b8db32", input={ "image": "https://replicate.delivery/mgxm/e3110a03-8f77-415c-b953-d0f79674b1bb/VanGogh.jpg", "prompts": "A painting in the style of Picasso", "iterations": 100, "display_frequency": "20" } ) # The nerdyrodent/vqgan-clip model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/nerdyrodent/vqgan-clip/api#output-schema print(item)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 nerdyrodent/vqgan-clip 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": "eae144b3ea325b889030f7919d0d1ca7b85be28ad496cf8c98f34f5440b8db32", "input": { "image": "https://replicate.delivery/mgxm/e3110a03-8f77-415c-b953-d0f79674b1bb/VanGogh.jpg", "prompts": "A painting in the style of Picasso", "iterations": 100, "display_frequency": "20" } }' \ 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/nerdyrodent/vqgan-clip@sha256:eae144b3ea325b889030f7919d0d1ca7b85be28ad496cf8c98f34f5440b8db32 \ -i 'image="https://replicate.delivery/mgxm/e3110a03-8f77-415c-b953-d0f79674b1bb/VanGogh.jpg"' \ -i 'prompts="A painting in the style of Picasso"' \ -i 'iterations=100' \ -i 'display_frequency="20"'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/nerdyrodent/vqgan-clip@sha256:eae144b3ea325b889030f7919d0d1ca7b85be28ad496cf8c98f34f5440b8db32curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "image": "https://replicate.delivery/mgxm/e3110a03-8f77-415c-b953-d0f79674b1bb/VanGogh.jpg", "prompts": "A painting in the style of Picasso", "iterations": 100, "display_frequency": "20" } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2021-11-07T23:10:31.845440Z", "created_at": "2021-11-07T23:07:44.411025Z", "data_removed": false, "error": null, "id": "j7dexlgy4vgdnllhvm3zmxsbqy", "input": { "image": "https://replicate.delivery/mgxm/e3110a03-8f77-415c-b953-d0f79674b1bb/VanGogh.jpg", "prompts": "A painting in the style of Picasso", "iterations": 100, "display_frequency": "20" }, "logs": "Using text prompts: ['A painting in the style of Picasso']\nUsing initial image: /tmp/tmp5droebsm/VanGogh.jpg\nUsing seed: 1028363113455530107\ni: 20, loss: 0.774153, losses: 0.774153\ni: 40, loss: 0.817554, losses: 0.817554\ni: 60, loss: 0.795525, losses: 0.795525\ni: 80, loss: 0.736627, losses: 0.736627\ni: 100, loss: 0.727939, losses: 0.727939", "metrics": { "total_time": 167.434415 }, "output": [ { "file": "https://replicate.delivery/mgxm/ec595056-1098-4087-9b13-8033d70cc5a1/out.png" }, { "file": "https://replicate.delivery/mgxm/7d870a3e-dd7b-4173-953c-e9c34246bbfe/out.png" }, { "file": "https://replicate.delivery/mgxm/a9b42341-581a-44fd-886b-2e2a0333f7d2/out.png" }, { "file": "https://replicate.delivery/mgxm/bc058801-b613-4523-88ff-e705a77cdc6b/out.png" } ], "started_at": "2021-12-04T20:05:52.468028Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/j7dexlgy4vgdnllhvm3zmxsbqy", "cancel": "https://api.replicate.com/v1/predictions/j7dexlgy4vgdnllhvm3zmxsbqy/cancel" }, "version": "eae144b3ea325b889030f7919d0d1ca7b85be28ad496cf8c98f34f5440b8db32" }Using text prompts: ['A painting in the style of Picasso'] Using initial image: /tmp/tmp5droebsm/VanGogh.jpg Using seed: 1028363113455530107 i: 20, loss: 0.774153, losses: 0.774153 i: 40, loss: 0.817554, losses: 0.817554 i: 60, loss: 0.795525, losses: 0.795525 i: 80, loss: 0.736627, losses: 0.736627 i: 100, loss: 0.727939, losses: 0.727939Prediction
nerdyrodent/vqgan-clip:eae144b3IDqvpp5lcrifh43ndy5yggkvsqhqStatusSucceededSourceWebHardware–Total duration–CreatedInput
- prompts
- A cute, smiling, Nerdy Rodent
- iterations
- 300
- display_frequency
- "20"
{ "prompts": "A cute, smiling, Nerdy Rodent", "iterations": 300, "display_frequency": "20" }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 nerdyrodent/vqgan-clip using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "nerdyrodent/vqgan-clip:eae144b3ea325b889030f7919d0d1ca7b85be28ad496cf8c98f34f5440b8db32", { input: { prompts: "A cute, smiling, Nerdy Rodent", iterations: 300, display_frequency: "20" } } ); 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 nerdyrodent/vqgan-clip using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "nerdyrodent/vqgan-clip:eae144b3ea325b889030f7919d0d1ca7b85be28ad496cf8c98f34f5440b8db32", input={ "prompts": "A cute, smiling, Nerdy Rodent", "iterations": 300, "display_frequency": "20" } ) # The nerdyrodent/vqgan-clip model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/nerdyrodent/vqgan-clip/api#output-schema print(item)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 nerdyrodent/vqgan-clip 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": "eae144b3ea325b889030f7919d0d1ca7b85be28ad496cf8c98f34f5440b8db32", "input": { "prompts": "A cute, smiling, Nerdy Rodent", "iterations": 300, "display_frequency": "20" } }' \ 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/nerdyrodent/vqgan-clip@sha256:eae144b3ea325b889030f7919d0d1ca7b85be28ad496cf8c98f34f5440b8db32 \ -i 'prompts="A cute, smiling, Nerdy Rodent"' \ -i 'iterations=300' \ -i 'display_frequency="20"'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/nerdyrodent/vqgan-clip@sha256:eae144b3ea325b889030f7919d0d1ca7b85be28ad496cf8c98f34f5440b8db32curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "prompts": "A cute, smiling, Nerdy Rodent", "iterations": 300, "display_frequency": "20" } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2021-11-07T21:17:22.295324Z", "created_at": "2021-11-07T21:13:04.612779Z", "data_removed": false, "error": null, "id": "qvpp5lcrifh43ndy5yggkvsqhq", "input": { "prompts": "A cute, smiling, Nerdy Rodent", "iterations": 300, "display_frequency": "20" }, "logs": "Using text prompts:\n['A cute, smiling, Nerdy Rodent']\nUsing seed: 10709328912262484355\n\n0it [00:00, ?it/s]\ni: 0, loss: 0.702186, losses: 0.702186\n\n0it [00:00, ?it/s]\n\n1it [00:01, 1.11s/it]\n\n2it [00:01, 1.08it/s]\n\n3it [00:02, 1.16it/s]\n\n4it [00:03, 1.19it/s]\n\n5it [00:04, 1.21it/s]\n\n6it [00:05, 1.22it/s]\n\n7it [00:05, 1.23it/s]\n\n8it [00:06, 1.24it/s]\n\n9it [00:07, 1.24it/s]\n\n10it [00:08, 1.24it/s]\n\n11it [00:09, 1.25it/s]\n\n12it [00:09, 1.25it/s]\n\n13it [00:10, 1.25it/s]\n\n14it [00:11, 1.24it/s]\n\n15it [00:12, 1.25it/s]\n\n16it [00:13, 1.25it/s]\n\n17it [00:13, 1.25it/s]\n\n18it [00:14, 1.25it/s]\n\n19it [00:15, 1.24it/s]\n\n20it [00:16, 1.25it/s]\ni: 20, loss: 0.775673, losses: 0.775673\n\n21it [00:17, 1.01s/it]\n\n22it [00:18, 1.05it/s]\n\n23it [00:19, 1.10it/s]\n\n24it [00:20, 1.14it/s]\n\n25it [00:21, 1.17it/s]\n\n26it [00:21, 1.18it/s]\n\n27it [00:22, 1.20it/s]\n\n28it [00:23, 1.21it/s]\n\n29it [00:24, 1.22it/s]\n\n30it [00:25, 1.22it/s]\n\n31it [00:25, 1.23it/s]\n\n32it [00:26, 1.23it/s]\n\n33it [00:27, 1.24it/s]\n\n34it [00:28, 1.23it/s]\n\n35it [00:29, 1.24it/s]\n\n36it [00:29, 1.24it/s]\n\n37it [00:30, 1.24it/s]\n\n38it [00:31, 1.23it/s]\n\n39it [00:32, 1.23it/s]\n\n40it [00:33, 1.23it/s]\ni: 40, loss: 0.654852, losses: 0.654852\n\n41it [00:34, 1.03s/it]\n\n42it [00:35, 1.04it/s]\n\n43it [00:36, 1.09it/s]\n\n44it [00:37, 1.13it/s]\n\n45it [00:37, 1.16it/s]\n\n46it [00:38, 1.18it/s]\n\n47it [00:39, 1.19it/s]\n\n48it [00:40, 1.20it/s]\n\n49it [00:41, 1.21it/s]\n\n50it [00:42, 1.22it/s]\n\n51it [00:42, 1.22it/s]\n\n52it [00:43, 1.22it/s]\n\n53it [00:44, 1.23it/s]\n\n54it [00:45, 1.23it/s]\n\n55it [00:46, 1.23it/s]\n\n56it [00:46, 1.23it/s]\n\n57it [00:47, 1.23it/s]\n\n58it [00:48, 1.23it/s]\n\n59it [00:49, 1.23it/s]\n\n60it [00:50, 1.23it/s]\ni: 60, loss: 0.739655, losses: 0.739655\n\n61it [00:51, 1.02s/it]\n\n62it [00:52, 1.04it/s]\n\n63it [00:53, 1.09it/s]\n\n64it [00:54, 1.13it/s]\n\n65it [00:54, 1.16it/s]\n\n66it [00:55, 1.18it/s]\n\n67it [00:56, 1.19it/s]\n\n68it [00:57, 1.20it/s]\n\n69it [00:58, 1.21it/s]\n\n70it [00:59, 1.21it/s]\n\n71it [00:59, 1.22it/s]\n\n72it [01:00, 1.22it/s]\n\n73it [01:01, 1.22it/s]\n\n74it [01:02, 1.22it/s]\n\n75it [01:03, 1.23it/s]\n\n76it [01:03, 1.23it/s]\n\n77it [01:04, 1.23it/s]\n\n78it [01:05, 1.23it/s]\n\n79it [01:06, 1.24it/s]\n\n80it [01:07, 1.24it/s]\ni: 80, loss: 0.658038, losses: 0.658038\n\n81it [01:08, 1.01s/it]\n\n82it [01:09, 1.05it/s]\n\n83it [01:10, 1.10it/s]\n\n84it [01:11, 1.14it/s]\n\n85it [01:11, 1.16it/s]\n\n86it [01:12, 1.19it/s]\n\n87it [01:13, 1.20it/s]\n\n88it [01:14, 1.21it/s]\n\n89it [01:15, 1.21it/s]\n\n90it [01:15, 1.22it/s]\n\n91it [01:16, 1.22it/s]\n\n92it [01:17, 1.22it/s]\n\n93it [01:18, 1.23it/s]\n\n94it [01:19, 1.23it/s]\n\n95it [01:19, 1.23it/s]\n\n96it [01:20, 1.23it/s]\n\n97it [01:21, 1.23it/s]\n\n98it [01:22, 1.23it/s]\n\n99it [01:23, 1.23it/s]\n\n100it [01:24, 1.24it/s]\ni: 100, loss: 0.738528, losses: 0.738528\n\n101it [01:25, 1.02s/it]\n\n102it [01:26, 1.05it/s]\n\n103it [01:27, 1.10it/s]\n\n104it [01:27, 1.14it/s]\n\n105it [01:28, 1.17it/s]\n\n106it [01:29, 1.18it/s]\n\n107it [01:30, 1.20it/s]\n\n108it [01:31, 1.20it/s]\n\n109it [01:32, 1.21it/s]\n\n110it [01:32, 1.21it/s]\n\n111it [01:33, 1.22it/s]\n\n112it [01:34, 1.22it/s]\n\n113it [01:35, 1.22it/s]\n\n114it [01:36, 1.23it/s]\n\n115it [01:36, 1.23it/s]\n\n116it [01:37, 1.23it/s]\n\n117it [01:38, 1.23it/s]\n\n118it [01:39, 1.23it/s]\n\n119it [01:40, 1.23it/s]\n\n120it [01:40, 1.23it/s]\ni: 120, loss: 0.746543, losses: 0.746543\n\n121it [01:42, 1.03s/it]\n\n122it [01:43, 1.04it/s]\n\n123it [01:44, 1.09it/s]\n\n124it [01:44, 1.13it/s]\n\n125it [01:45, 1.15it/s]\n\n126it [01:46, 1.17it/s]\n\n127it [01:47, 1.19it/s]\n\n128it [01:48, 1.21it/s]\n\n129it [01:48, 1.21it/s]\n\n130it [01:49, 1.22it/s]\n\n131it [01:50, 1.22it/s]\n\n132it [01:51, 1.22it/s]\n\n133it [01:52, 1.23it/s]\n\n134it [01:53, 1.23it/s]\n\n135it [01:53, 1.23it/s]\n\n136it [01:54, 1.23it/s]\n\n137it [01:55, 1.23it/s]\n\n138it [01:56, 1.23it/s]\n\n139it [01:57, 1.23it/s]\n\n140it [01:57, 1.23it/s]\ni: 140, loss: 0.731374, losses: 0.731374\n\n141it [01:59, 1.02s/it]\n\n142it [02:00, 1.05it/s]\n\n143it [02:01, 1.10it/s]\n\n144it [02:01, 1.14it/s]\n\n145it [02:02, 1.17it/s]\n\n146it [02:03, 1.18it/s]\n\n147it [02:04, 1.19it/s]\n\n148it [02:05, 1.20it/s]\n\n149it [02:05, 1.21it/s]\n\n150it [02:06, 1.22it/s]\n\n151it [02:07, 1.22it/s]\n\n152it [02:08, 1.22it/s]\n\n153it [02:09, 1.22it/s]\n\n154it [02:09, 1.22it/s]\n\n155it [02:10, 1.22it/s]\n\n156it [02:11, 1.23it/s]\n\n157it [02:12, 1.23it/s]\n\n158it [02:13, 1.24it/s]\n\n159it [02:14, 1.23it/s]\n\n160it [02:14, 1.23it/s]\ni: 160, loss: 0.653238, losses: 0.653238\n\n161it [02:16, 1.02s/it]\n\n162it [02:17, 1.05it/s]\n\n163it [02:17, 1.09it/s]\n\n164it [02:18, 1.13it/s]\n\n165it [02:19, 1.16it/s]\n\n166it [02:20, 1.18it/s]\n\n167it [02:21, 1.19it/s]\n\n168it [02:22, 1.20it/s]\n\n169it [02:22, 1.21it/s]\n\n170it [02:23, 1.21it/s]\n\n171it [02:24, 1.22it/s]\n\n172it [02:25, 1.22it/s]\n\n173it [02:26, 1.22it/s]\n\n174it [02:26, 1.22it/s]\n\n175it [02:27, 1.23it/s]\n\n176it [02:28, 1.22it/s]\n\n177it [02:29, 1.23it/s]\n\n178it [02:30, 1.23it/s]\n\n179it [02:31, 1.23it/s]\n\n180it [02:31, 1.23it/s]\ni: 180, loss: 0.73129, losses: 0.73129\n\n181it [02:33, 1.02s/it]\n\n182it [02:34, 1.04it/s]\n\n183it [02:34, 1.10it/s]\n\n184it [02:35, 1.13it/s]\n\n185it [02:36, 1.16it/s]\n\n186it [02:37, 1.18it/s]\n\n187it [02:38, 1.20it/s]\n\n188it [02:39, 1.21it/s]\n\n189it [02:39, 1.21it/s]\n\n190it [02:40, 1.22it/s]\n\n191it [02:41, 1.22it/s]\n\n192it [02:42, 1.22it/s]\n\n193it [02:43, 1.22it/s]\n\n194it [02:43, 1.22it/s]\n\n195it [02:44, 1.23it/s]\n\n196it [02:45, 1.23it/s]\n\n197it [02:46, 1.23it/s]\n\n198it [02:47, 1.23it/s]\n\n199it [02:47, 1.23it/s]\n\n200it [02:48, 1.23it/s]\ni: 200, loss: 0.657069, losses: 0.657069\n\n201it [02:50, 1.02s/it]\n\n202it [02:51, 1.05it/s]\n\n203it [02:51, 1.10it/s]\n\n204it [02:52, 1.14it/s]\n\n205it [02:53, 1.16it/s]\n\n206it [02:54, 1.18it/s]\n\n207it [02:55, 1.20it/s]\n\n208it [02:55, 1.20it/s]\n\n209it [02:56, 1.21it/s]\n\n210it [02:57, 1.22it/s]\n\n211it [02:58, 1.22it/s]\n\n212it [02:59, 1.22it/s]\n\n213it [03:00, 1.22it/s]\n\n214it [03:00, 1.23it/s]\n\n215it [03:01, 1.23it/s]\n\n216it [03:02, 1.23it/s]\n\n217it [03:03, 1.23it/s]\n\n218it [03:04, 1.22it/s]\n\n219it [03:04, 1.23it/s]\n\n220it [03:05, 1.23it/s]\ni: 220, loss: 0.774646, losses: 0.774646\n\n221it [03:07, 1.03s/it]\n\n222it [03:08, 1.04it/s]\n\n223it [03:08, 1.09it/s]\n\n224it [03:09, 1.12it/s]\n\n225it [03:10, 1.15it/s]\n\n226it [03:11, 1.17it/s]\n\n227it [03:12, 1.20it/s]\n\n228it [03:12, 1.21it/s]\n\n229it [03:13, 1.21it/s]\n\n230it [03:14, 1.22it/s]\n\n231it [03:15, 1.23it/s]\n\n232it [03:16, 1.23it/s]\n\n233it [03:16, 1.23it/s]\n\n234it [03:17, 1.23it/s]\n\n235it [03:18, 1.23it/s]\n\n236it [03:19, 1.23it/s]\n\n237it [03:20, 1.23it/s]\n\n238it [03:21, 1.22it/s]\n\n239it [03:21, 1.23it/s]\n\n240it [03:22, 1.23it/s]\ni: 240, loss: 0.644417, losses: 0.644417\n\n241it [03:24, 1.01s/it]\n\n242it [03:24, 1.05it/s]\n\n243it [03:25, 1.10it/s]\n\n244it [03:26, 1.13it/s]\n\n245it [03:27, 1.15it/s]\n\n246it [03:28, 1.18it/s]\n\n247it [03:29, 1.19it/s]\n\n248it [03:29, 1.21it/s]\n\n249it [03:30, 1.21it/s]\n\n250it [03:31, 1.22it/s]\n\n251it [03:32, 1.22it/s]\n\n252it [03:33, 1.22it/s]\n\n253it [03:33, 1.23it/s]\n\n254it [03:34, 1.23it/s]\n\n255it [03:35, 1.23it/s]\n\n256it [03:36, 1.23it/s]\n\n257it [03:37, 1.23it/s]\n\n258it [03:37, 1.23it/s]\n\n259it [03:38, 1.22it/s]\n\n260it [03:39, 1.22it/s]\ni: 260, loss: 0.763826, losses: 0.763826\n\n261it [03:41, 1.02s/it]\n\n262it [03:41, 1.05it/s]\n\n263it [03:42, 1.10it/s]\n\n264it [03:43, 1.13it/s]\n\n265it [03:44, 1.16it/s]\n\n266it [03:45, 1.18it/s]\n\n267it [03:45, 1.20it/s]\n\n268it [03:46, 1.21it/s]\n\n269it [03:47, 1.22it/s]\n\n270it [03:48, 1.22it/s]\n\n271it [03:49, 1.22it/s]\n\n272it [03:50, 1.23it/s]\n\n273it [03:50, 1.23it/s]\n\n274it [03:51, 1.23it/s]\n\n275it [03:52, 1.23it/s]\n\n276it [03:53, 1.23it/s]\n\n277it [03:54, 1.23it/s]\n\n278it [03:54, 1.23it/s]\n\n279it [03:55, 1.23it/s]\n\n280it [03:56, 1.24it/s]\ni: 280, loss: 0.654698, losses: 0.654698\n\n281it [03:58, 1.01s/it]\n\n282it [03:58, 1.05it/s]\n\n283it [03:59, 1.09it/s]\n\n284it [04:00, 1.13it/s]\n\n285it [04:01, 1.16it/s]\n\n286it [04:02, 1.18it/s]\n\n287it [04:02, 1.20it/s]\n\n288it [04:03, 1.21it/s]\n\n289it [04:04, 1.21it/s]\n\n290it [04:05, 1.22it/s]\n\n291it [04:06, 1.23it/s]\n\n292it [04:06, 1.23it/s]\n\n293it [04:07, 1.23it/s]\n\n294it [04:08, 1.23it/s]\n\n295it [04:09, 1.23it/s]\n\n296it [04:10, 1.23it/s]\n\n297it [04:11, 1.23it/s]\n\n298it [04:11, 1.23it/s]\n\n299it [04:12, 1.23it/s]\n\n300it [04:13, 1.23it/s]\ni: 300, loss: 0.759079, losses: 0.759079\ni: 300, loss: 0.759079, losses: 0.759079\n\n300it [04:15, 1.17it/s]", "metrics": {}, "output": [ { "file": "https://replicate.delivery/mgxm/2b238c63-cad2-4ff4-92a1-f39e31f47497/out.png" }, { "file": "https://replicate.delivery/mgxm/da275ff1-a2c7-4198-a0cd-a45c9c7170bb/out.png" }, { "file": "https://replicate.delivery/mgxm/10524399-5524-45ad-9d43-138990723e1a/out.png" }, { "file": "https://replicate.delivery/mgxm/6b8c0e99-d494-4624-8603-bbf99c3a7fbf/out.png" }, { "file": "https://replicate.delivery/mgxm/5ddefefe-3698-4a99-83e5-08fa2a198799/out.png" }, { "file": "https://replicate.delivery/mgxm/4a53ec73-3b33-4731-90be-079cd3af16b5/out.png" }, { "file": "https://replicate.delivery/mgxm/c46a895b-a2a3-449e-8aa0-f1ee58c4467e/out.png" }, { "file": "https://replicate.delivery/mgxm/c8edeba5-732c-4beb-b7cf-e2428b709f53/out.png" }, { "file": "https://replicate.delivery/mgxm/25ad9781-458c-4b8f-b81c-d11136667140/out.png" }, { "file": "https://replicate.delivery/mgxm/419f8b49-17ea-4e52-8e89-d4e1cc1af614/out.png" }, { "file": "https://replicate.delivery/mgxm/3daa3f9f-29de-4d22-a4ef-55e9c3d66f08/out.png" }, { "file": "https://replicate.delivery/mgxm/1e8e8d99-0b47-472a-bc82-7da89166edc0/out.png" }, { "file": "https://replicate.delivery/mgxm/5cd27e68-e5df-4150-98a2-36371d9e31ce/out.png" }, { "file": "https://replicate.delivery/mgxm/9e0f4f16-b5cd-4be0-9865-bdcb2027f19a/out.png" }, { "file": "https://replicate.delivery/mgxm/21e91b8b-eb0b-49e8-a252-c736c539b5e8/out.png" }, { "file": "https://replicate.delivery/mgxm/a1fdb746-acf9-4279-9daf-8954468fd545/out.png" } ], "started_at": null, "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/qvpp5lcrifh43ndy5yggkvsqhq", "cancel": "https://api.replicate.com/v1/predictions/qvpp5lcrifh43ndy5yggkvsqhq/cancel" }, "version": "2a50e42e8b68a193d58a21fa7990e1677c0ae93f85e022a4fbd38985cc8c4772" }Using text prompts: ['A cute, smiling, Nerdy Rodent'] Using seed: 10709328912262484355 0it [00:00, ?it/s] i: 0, loss: 0.702186, losses: 0.702186 0it [00:00, ?it/s] 1it [00:01, 1.11s/it] 2it [00:01, 1.08it/s] 3it [00:02, 1.16it/s] 4it [00:03, 1.19it/s] 5it [00:04, 1.21it/s] 6it [00:05, 1.22it/s] 7it [00:05, 1.23it/s] 8it [00:06, 1.24it/s] 9it [00:07, 1.24it/s] 10it [00:08, 1.24it/s] 11it [00:09, 1.25it/s] 12it [00:09, 1.25it/s] 13it [00:10, 1.25it/s] 14it [00:11, 1.24it/s] 15it [00:12, 1.25it/s] 16it [00:13, 1.25it/s] 17it [00:13, 1.25it/s] 18it [00:14, 1.25it/s] 19it [00:15, 1.24it/s] 20it [00:16, 1.25it/s] i: 20, loss: 0.775673, losses: 0.775673 21it [00:17, 1.01s/it] 22it [00:18, 1.05it/s] 23it [00:19, 1.10it/s] 24it [00:20, 1.14it/s] 25it [00:21, 1.17it/s] 26it [00:21, 1.18it/s] 27it [00:22, 1.20it/s] 28it [00:23, 1.21it/s] 29it [00:24, 1.22it/s] 30it [00:25, 1.22it/s] 31it [00:25, 1.23it/s] 32it [00:26, 1.23it/s] 33it [00:27, 1.24it/s] 34it [00:28, 1.23it/s] 35it [00:29, 1.24it/s] 36it [00:29, 1.24it/s] 37it [00:30, 1.24it/s] 38it [00:31, 1.23it/s] 39it [00:32, 1.23it/s] 40it [00:33, 1.23it/s] i: 40, loss: 0.654852, losses: 0.654852 41it [00:34, 1.03s/it] 42it [00:35, 1.04it/s] 43it [00:36, 1.09it/s] 44it [00:37, 1.13it/s] 45it [00:37, 1.16it/s] 46it [00:38, 1.18it/s] 47it [00:39, 1.19it/s] 48it [00:40, 1.20it/s] 49it [00:41, 1.21it/s] 50it [00:42, 1.22it/s] 51it [00:42, 1.22it/s] 52it [00:43, 1.22it/s] 53it [00:44, 1.23it/s] 54it [00:45, 1.23it/s] 55it [00:46, 1.23it/s] 56it [00:46, 1.23it/s] 57it [00:47, 1.23it/s] 58it [00:48, 1.23it/s] 59it [00:49, 1.23it/s] 60it [00:50, 1.23it/s] i: 60, loss: 0.739655, losses: 0.739655 61it [00:51, 1.02s/it] 62it [00:52, 1.04it/s] 63it [00:53, 1.09it/s] 64it [00:54, 1.13it/s] 65it [00:54, 1.16it/s] 66it [00:55, 1.18it/s] 67it [00:56, 1.19it/s] 68it [00:57, 1.20it/s] 69it [00:58, 1.21it/s] 70it [00:59, 1.21it/s] 71it [00:59, 1.22it/s] 72it [01:00, 1.22it/s] 73it [01:01, 1.22it/s] 74it [01:02, 1.22it/s] 75it [01:03, 1.23it/s] 76it [01:03, 1.23it/s] 77it [01:04, 1.23it/s] 78it [01:05, 1.23it/s] 79it [01:06, 1.24it/s] 80it [01:07, 1.24it/s] i: 80, loss: 0.658038, losses: 0.658038 81it [01:08, 1.01s/it] 82it [01:09, 1.05it/s] 83it [01:10, 1.10it/s] 84it [01:11, 1.14it/s] 85it [01:11, 1.16it/s] 86it [01:12, 1.19it/s] 87it [01:13, 1.20it/s] 88it [01:14, 1.21it/s] 89it [01:15, 1.21it/s] 90it [01:15, 1.22it/s] 91it [01:16, 1.22it/s] 92it [01:17, 1.22it/s] 93it [01:18, 1.23it/s] 94it [01:19, 1.23it/s] 95it [01:19, 1.23it/s] 96it [01:20, 1.23it/s] 97it [01:21, 1.23it/s] 98it [01:22, 1.23it/s] 99it [01:23, 1.23it/s] 100it [01:24, 1.24it/s] i: 100, loss: 0.738528, losses: 0.738528 101it [01:25, 1.02s/it] 102it [01:26, 1.05it/s] 103it [01:27, 1.10it/s] 104it [01:27, 1.14it/s] 105it [01:28, 1.17it/s] 106it [01:29, 1.18it/s] 107it [01:30, 1.20it/s] 108it [01:31, 1.20it/s] 109it [01:32, 1.21it/s] 110it [01:32, 1.21it/s] 111it [01:33, 1.22it/s] 112it [01:34, 1.22it/s] 113it [01:35, 1.22it/s] 114it [01:36, 1.23it/s] 115it [01:36, 1.23it/s] 116it [01:37, 1.23it/s] 117it [01:38, 1.23it/s] 118it [01:39, 1.23it/s] 119it [01:40, 1.23it/s] 120it [01:40, 1.23it/s] i: 120, loss: 0.746543, losses: 0.746543 121it [01:42, 1.03s/it] 122it [01:43, 1.04it/s] 123it [01:44, 1.09it/s] 124it [01:44, 1.13it/s] 125it [01:45, 1.15it/s] 126it [01:46, 1.17it/s] 127it [01:47, 1.19it/s] 128it [01:48, 1.21it/s] 129it [01:48, 1.21it/s] 130it [01:49, 1.22it/s] 131it [01:50, 1.22it/s] 132it [01:51, 1.22it/s] 133it [01:52, 1.23it/s] 134it [01:53, 1.23it/s] 135it [01:53, 1.23it/s] 136it [01:54, 1.23it/s] 137it [01:55, 1.23it/s] 138it [01:56, 1.23it/s] 139it [01:57, 1.23it/s] 140it [01:57, 1.23it/s] i: 140, loss: 0.731374, losses: 0.731374 141it [01:59, 1.02s/it] 142it [02:00, 1.05it/s] 143it [02:01, 1.10it/s] 144it [02:01, 1.14it/s] 145it [02:02, 1.17it/s] 146it [02:03, 1.18it/s] 147it [02:04, 1.19it/s] 148it [02:05, 1.20it/s] 149it [02:05, 1.21it/s] 150it [02:06, 1.22it/s] 151it [02:07, 1.22it/s] 152it [02:08, 1.22it/s] 153it [02:09, 1.22it/s] 154it [02:09, 1.22it/s] 155it [02:10, 1.22it/s] 156it [02:11, 1.23it/s] 157it [02:12, 1.23it/s] 158it [02:13, 1.24it/s] 159it [02:14, 1.23it/s] 160it [02:14, 1.23it/s] i: 160, loss: 0.653238, losses: 0.653238 161it [02:16, 1.02s/it] 162it [02:17, 1.05it/s] 163it [02:17, 1.09it/s] 164it [02:18, 1.13it/s] 165it [02:19, 1.16it/s] 166it [02:20, 1.18it/s] 167it [02:21, 1.19it/s] 168it [02:22, 1.20it/s] 169it [02:22, 1.21it/s] 170it [02:23, 1.21it/s] 171it [02:24, 1.22it/s] 172it [02:25, 1.22it/s] 173it [02:26, 1.22it/s] 174it [02:26, 1.22it/s] 175it [02:27, 1.23it/s] 176it [02:28, 1.22it/s] 177it [02:29, 1.23it/s] 178it [02:30, 1.23it/s] 179it [02:31, 1.23it/s] 180it [02:31, 1.23it/s] i: 180, loss: 0.73129, losses: 0.73129 181it [02:33, 1.02s/it] 182it [02:34, 1.04it/s] 183it [02:34, 1.10it/s] 184it [02:35, 1.13it/s] 185it [02:36, 1.16it/s] 186it [02:37, 1.18it/s] 187it [02:38, 1.20it/s] 188it [02:39, 1.21it/s] 189it [02:39, 1.21it/s] 190it [02:40, 1.22it/s] 191it [02:41, 1.22it/s] 192it [02:42, 1.22it/s] 193it [02:43, 1.22it/s] 194it [02:43, 1.22it/s] 195it [02:44, 1.23it/s] 196it [02:45, 1.23it/s] 197it [02:46, 1.23it/s] 198it [02:47, 1.23it/s] 199it [02:47, 1.23it/s] 200it [02:48, 1.23it/s] i: 200, loss: 0.657069, losses: 0.657069 201it [02:50, 1.02s/it] 202it [02:51, 1.05it/s] 203it [02:51, 1.10it/s] 204it [02:52, 1.14it/s] 205it [02:53, 1.16it/s] 206it [02:54, 1.18it/s] 207it [02:55, 1.20it/s] 208it [02:55, 1.20it/s] 209it [02:56, 1.21it/s] 210it [02:57, 1.22it/s] 211it [02:58, 1.22it/s] 212it [02:59, 1.22it/s] 213it [03:00, 1.22it/s] 214it [03:00, 1.23it/s] 215it [03:01, 1.23it/s] 216it [03:02, 1.23it/s] 217it [03:03, 1.23it/s] 218it [03:04, 1.22it/s] 219it [03:04, 1.23it/s] 220it [03:05, 1.23it/s] i: 220, loss: 0.774646, losses: 0.774646 221it [03:07, 1.03s/it] 222it [03:08, 1.04it/s] 223it [03:08, 1.09it/s] 224it [03:09, 1.12it/s] 225it [03:10, 1.15it/s] 226it [03:11, 1.17it/s] 227it [03:12, 1.20it/s] 228it [03:12, 1.21it/s] 229it [03:13, 1.21it/s] 230it [03:14, 1.22it/s] 231it [03:15, 1.23it/s] 232it [03:16, 1.23it/s] 233it [03:16, 1.23it/s] 234it [03:17, 1.23it/s] 235it [03:18, 1.23it/s] 236it [03:19, 1.23it/s] 237it [03:20, 1.23it/s] 238it [03:21, 1.22it/s] 239it [03:21, 1.23it/s] 240it [03:22, 1.23it/s] i: 240, loss: 0.644417, losses: 0.644417 241it [03:24, 1.01s/it] 242it [03:24, 1.05it/s] 243it [03:25, 1.10it/s] 244it [03:26, 1.13it/s] 245it [03:27, 1.15it/s] 246it [03:28, 1.18it/s] 247it [03:29, 1.19it/s] 248it [03:29, 1.21it/s] 249it [03:30, 1.21it/s] 250it [03:31, 1.22it/s] 251it [03:32, 1.22it/s] 252it [03:33, 1.22it/s] 253it [03:33, 1.23it/s] 254it [03:34, 1.23it/s] 255it [03:35, 1.23it/s] 256it [03:36, 1.23it/s] 257it [03:37, 1.23it/s] 258it [03:37, 1.23it/s] 259it [03:38, 1.22it/s] 260it [03:39, 1.22it/s] i: 260, loss: 0.763826, losses: 0.763826 261it [03:41, 1.02s/it] 262it [03:41, 1.05it/s] 263it [03:42, 1.10it/s] 264it [03:43, 1.13it/s] 265it [03:44, 1.16it/s] 266it [03:45, 1.18it/s] 267it [03:45, 1.20it/s] 268it [03:46, 1.21it/s] 269it [03:47, 1.22it/s] 270it [03:48, 1.22it/s] 271it [03:49, 1.22it/s] 272it [03:50, 1.23it/s] 273it [03:50, 1.23it/s] 274it [03:51, 1.23it/s] 275it [03:52, 1.23it/s] 276it [03:53, 1.23it/s] 277it [03:54, 1.23it/s] 278it [03:54, 1.23it/s] 279it [03:55, 1.23it/s] 280it [03:56, 1.24it/s] i: 280, loss: 0.654698, losses: 0.654698 281it [03:58, 1.01s/it] 282it [03:58, 1.05it/s] 283it [03:59, 1.09it/s] 284it [04:00, 1.13it/s] 285it [04:01, 1.16it/s] 286it [04:02, 1.18it/s] 287it [04:02, 1.20it/s] 288it [04:03, 1.21it/s] 289it [04:04, 1.21it/s] 290it [04:05, 1.22it/s] 291it [04:06, 1.23it/s] 292it [04:06, 1.23it/s] 293it [04:07, 1.23it/s] 294it [04:08, 1.23it/s] 295it [04:09, 1.23it/s] 296it [04:10, 1.23it/s] 297it [04:11, 1.23it/s] 298it [04:11, 1.23it/s] 299it [04:12, 1.23it/s] 300it [04:13, 1.23it/s] i: 300, loss: 0.759079, losses: 0.759079 i: 300, loss: 0.759079, losses: 0.759079 300it [04:15, 1.17it/s]Prediction
nerdyrodent/vqgan-clip:eae144b3Input
- prompts
- A painting of an apple in a fruit bowl | psychedelic | surreal:0.5 | weird:0.25
- iterations
- 300
- display_frequency
- "20"
{ "prompts": "A painting of an apple in a fruit bowl | psychedelic | surreal:0.5 | weird:0.25", "iterations": 300, "display_frequency": "20" }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 nerdyrodent/vqgan-clip using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "nerdyrodent/vqgan-clip:eae144b3ea325b889030f7919d0d1ca7b85be28ad496cf8c98f34f5440b8db32", { input: { prompts: "A painting of an apple in a fruit bowl | psychedelic | surreal:0.5 | weird:0.25", iterations: 300, display_frequency: "20" } } ); 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 nerdyrodent/vqgan-clip using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "nerdyrodent/vqgan-clip:eae144b3ea325b889030f7919d0d1ca7b85be28ad496cf8c98f34f5440b8db32", input={ "prompts": "A painting of an apple in a fruit bowl | psychedelic | surreal:0.5 | weird:0.25", "iterations": 300, "display_frequency": "20" } ) # The nerdyrodent/vqgan-clip model can stream output as it's running. # The predict method returns an iterator, and you can iterate over that output. for item in output: # https://replicate.com/nerdyrodent/vqgan-clip/api#output-schema print(item)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 nerdyrodent/vqgan-clip 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": "eae144b3ea325b889030f7919d0d1ca7b85be28ad496cf8c98f34f5440b8db32", "input": { "prompts": "A painting of an apple in a fruit bowl | psychedelic | surreal:0.5 | weird:0.25", "iterations": 300, "display_frequency": "20" } }' \ 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/nerdyrodent/vqgan-clip@sha256:eae144b3ea325b889030f7919d0d1ca7b85be28ad496cf8c98f34f5440b8db32 \ -i 'prompts="A painting of an apple in a fruit bowl | psychedelic | surreal:0.5 | weird:0.25"' \ -i 'iterations=300' \ -i 'display_frequency="20"'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/nerdyrodent/vqgan-clip@sha256:eae144b3ea325b889030f7919d0d1ca7b85be28ad496cf8c98f34f5440b8db32curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "prompts": "A painting of an apple in a fruit bowl | psychedelic | surreal:0.5 | weird:0.25", "iterations": 300, "display_frequency": "20" } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2021-11-07T23:11:24.201884Z", "created_at": "2021-11-07T23:06:16.256481Z", "data_removed": false, "error": null, "id": "c3r5cva5vjcjzppduqkvncgr6e", "input": { "prompts": "A painting of an apple in a fruit bowl | psychedelic | surreal:0.5 | weird:0.25", "iterations": 300, "display_frequency": "20" }, "logs": "Using text prompts: ['A painting of an apple in a fruit bowl ', ' psychedelic ', ' surreal:0.5 ', ' weird:0.25']\nUsing seed: 8621515100840653640\ni: 20, loss: 2.47025, losses: 0.924426, 0.874087, 0.446568, 0.225171\ni: 40, loss: 2.36236, losses: 0.84798, 0.848477, 0.442402, 0.223502\ni: 60, loss: 2.2411, losses: 0.744462, 0.839277, 0.435993, 0.22137\ni: 80, loss: 2.18987, losses: 0.717057, 0.820296, 0.432167, 0.220355\ni: 100, loss: 2.23944, losses: 0.763108, 0.828086, 0.43029, 0.217957\ni: 120, loss: 2.2094, losses: 0.744955, 0.818292, 0.428057, 0.218097\ni: 140, loss: 2.15879, losses: 0.711274, 0.803224, 0.426697, 0.217595\ni: 160, loss: 2.2357, losses: 0.764989, 0.823443, 0.429317, 0.217955\ni: 180, loss: 2.25737, losses: 0.776168, 0.832335, 0.430852, 0.218018\ni: 200, loss: 2.12797, losses: 0.688591, 0.795802, 0.426389, 0.217184\ni: 220, loss: 2.1958, losses: 0.741135, 0.808642, 0.428548, 0.217474\ni: 240, loss: 2.18421, losses: 0.730992, 0.808825, 0.427092, 0.217301\ni: 260, loss: 2.13522, losses: 0.694769, 0.797994, 0.425379, 0.21708\ni: 280, loss: 2.21432, losses: 0.744744, 0.825513, 0.426722, 0.217345\ni: 300, loss: 2.20758, losses: 0.749836, 0.812126, 0.428777, 0.216845", "metrics": { "total_time": 307.945403 }, "output": [ { "file": "https://replicate.delivery/mgxm/e7826c81-fd6b-4b56-85ac-b7d78511062e/out.png" }, { "file": "https://replicate.delivery/mgxm/c25aee14-8ad8-416f-9722-da62ce7dc723/out.png" }, { "file": "https://replicate.delivery/mgxm/e754b9b7-1e12-4f5e-927c-0ba93c5bc726/out.png" }, { "file": "https://replicate.delivery/mgxm/3845ff92-ed37-47ed-91d4-de6e87eddeb6/out.png" }, { "file": "https://replicate.delivery/mgxm/4aae236f-80e8-4891-9049-95e65793d2a5/out.png" }, { "file": "https://replicate.delivery/mgxm/f61f49df-c4e9-4007-a088-c245c4b0ba26/out.png" }, { "file": "https://replicate.delivery/mgxm/74efa7cb-8048-49c2-a606-e73452b13171/out.png" }, { "file": "https://replicate.delivery/mgxm/f43d09db-3fa8-4c13-952b-9bccca611324/out.png" }, { "file": "https://replicate.delivery/mgxm/d00f908e-54fd-422c-a5e1-0b7f92c3de26/out.png" }, { "file": "https://replicate.delivery/mgxm/a41afcae-03b5-4807-b51b-820d0ef6c224/out.png" }, { "file": "https://replicate.delivery/mgxm/e7bf609b-1a61-424f-8e5a-a54460ded55c/out.png" }, { "file": "https://replicate.delivery/mgxm/d8424bc4-d989-42a3-bb93-bb76dad7d7bd/out.png" }, { "file": "https://replicate.delivery/mgxm/eed10cfa-1733-456c-a201-724ba5b6847e/out.png" }, { "file": "https://replicate.delivery/mgxm/f2ef1a9e-5f31-4774-a4db-7de1f319fa02/out.png" } ], "started_at": "2021-11-30T17:28:12.980660Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/c3r5cva5vjcjzppduqkvncgr6e", "cancel": "https://api.replicate.com/v1/predictions/c3r5cva5vjcjzppduqkvncgr6e/cancel" }, "version": "eae144b3ea325b889030f7919d0d1ca7b85be28ad496cf8c98f34f5440b8db32" }Using text prompts: ['A painting of an apple in a fruit bowl ', ' psychedelic ', ' surreal:0.5 ', ' weird:0.25'] Using seed: 8621515100840653640 i: 20, loss: 2.47025, losses: 0.924426, 0.874087, 0.446568, 0.225171 i: 40, loss: 2.36236, losses: 0.84798, 0.848477, 0.442402, 0.223502 i: 60, loss: 2.2411, losses: 0.744462, 0.839277, 0.435993, 0.22137 i: 80, loss: 2.18987, losses: 0.717057, 0.820296, 0.432167, 0.220355 i: 100, loss: 2.23944, losses: 0.763108, 0.828086, 0.43029, 0.217957 i: 120, loss: 2.2094, losses: 0.744955, 0.818292, 0.428057, 0.218097 i: 140, loss: 2.15879, losses: 0.711274, 0.803224, 0.426697, 0.217595 i: 160, loss: 2.2357, losses: 0.764989, 0.823443, 0.429317, 0.217955 i: 180, loss: 2.25737, losses: 0.776168, 0.832335, 0.430852, 0.218018 i: 200, loss: 2.12797, losses: 0.688591, 0.795802, 0.426389, 0.217184 i: 220, loss: 2.1958, losses: 0.741135, 0.808642, 0.428548, 0.217474 i: 240, loss: 2.18421, losses: 0.730992, 0.808825, 0.427092, 0.217301 i: 260, loss: 2.13522, losses: 0.694769, 0.797994, 0.425379, 0.21708 i: 280, loss: 2.21432, losses: 0.744744, 0.825513, 0.426722, 0.217345 i: 300, loss: 2.20758, losses: 0.749836, 0.812126, 0.428777, 0.216845
Want to make some of these yourself?
Run this model