Versions
Failed to load versions. Head to the versions page to see all versions for this model.
You're looking at a specific version of this model. Jump to the model overview.
lucataco /aura-flow-v0.2:e784141e
Input
Run this model in Node.js with one line of code:
npx create-replicate --model=lucataco/aura-flow-v0.2
or set up a project from scratch
Install Replicate’s Node.js client library:
npm install replicateSet the
REPLICATE_API_TOKEN environment 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";
import fs from "node:fs";
const replicate = new Replicate({
auth: process.env.REPLICATE_API_TOKEN,
});Run lucataco/aura-flow-v0.2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"lucataco/aura-flow-v0.2:e784141e567364018b6c24297273e910b80c468c60ccb2a2a6642c034c7d43ee",
{
input: {
cfg: 3.5,
shift: 1,
width: 1024,
height: 1024,
prompt: "A hyper-detailed, close-up view inside a magical snow globe. The word \"Snow\" is intricately formed from miniature snowflakes and frost patterns, suspended in the center of the globe. Surrounding the word, a miniature winter wonderland unfolds in exquisite detail. Tiny evergreen trees, their branches laden with snow, create a dense forest. A frozen lake reflects the scene like a mirror, with microscopic ice skaters etching patterns on its surface. A miniature log cabin nestles in the trees, warm light spilling from its windows and smoke curling from the chimney. Tiny deer and rabbits leave intricate tracks in the snow. Countless snowflakes of varying sizes and intricate designs swirl around the scene, some caught in mid-fall, others settled on surfaces. The globe's glass is visible at the edges, slightly distorting the view and adding to the magical atmosphere. The lighting suggests a setting sun, casting long shadows and bathing the scene in a warm, golden glow that contrasts with the cool blues and whites of the snow. Every element is rendered in minute detail, inviting the viewer to explore the miniature world within the snow globe.",
sampler: "uni_pc",
scheduler: "normal",
output_format: "webp",
output_quality: 80,
negative_prompt: "",
number_of_images: 1
}
}
);
// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"
// To write the file to disk:
fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:
pip install replicateSet the
REPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:
import replicateRun lucataco/aura-flow-v0.2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"lucataco/aura-flow-v0.2:e784141e567364018b6c24297273e910b80c468c60ccb2a2a6642c034c7d43ee",
input={
"cfg": 3.5,
"shift": 1,
"width": 1024,
"height": 1024,
"prompt": "A hyper-detailed, close-up view inside a magical snow globe. The word \"Snow\" is intricately formed from miniature snowflakes and frost patterns, suspended in the center of the globe. Surrounding the word, a miniature winter wonderland unfolds in exquisite detail. Tiny evergreen trees, their branches laden with snow, create a dense forest. A frozen lake reflects the scene like a mirror, with microscopic ice skaters etching patterns on its surface. A miniature log cabin nestles in the trees, warm light spilling from its windows and smoke curling from the chimney. Tiny deer and rabbits leave intricate tracks in the snow. Countless snowflakes of varying sizes and intricate designs swirl around the scene, some caught in mid-fall, others settled on surfaces. The globe's glass is visible at the edges, slightly distorting the view and adding to the magical atmosphere. The lighting suggests a setting sun, casting long shadows and bathing the scene in a warm, golden glow that contrasts with the cool blues and whites of the snow. Every element is rendered in minute detail, inviting the viewer to explore the miniature world within the snow globe.",
"sampler": "uni_pc",
"scheduler": "normal",
"output_format": "webp",
"output_quality": 80,
"negative_prompt": "",
"number_of_images": 1
}
)
print(output)To learn more, take a look at the guide on getting started with Python.
Set the
REPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run lucataco/aura-flow-v0.2 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": "lucataco/aura-flow-v0.2:e784141e567364018b6c24297273e910b80c468c60ccb2a2a6642c034c7d43ee",
"input": {
"cfg": 3.5,
"shift": 1,
"width": 1024,
"height": 1024,
"prompt": "A hyper-detailed, close-up view inside a magical snow globe. The word \\"Snow\\" is intricately formed from miniature snowflakes and frost patterns, suspended in the center of the globe. Surrounding the word, a miniature winter wonderland unfolds in exquisite detail. Tiny evergreen trees, their branches laden with snow, create a dense forest. A frozen lake reflects the scene like a mirror, with microscopic ice skaters etching patterns on its surface. A miniature log cabin nestles in the trees, warm light spilling from its windows and smoke curling from the chimney. Tiny deer and rabbits leave intricate tracks in the snow. Countless snowflakes of varying sizes and intricate designs swirl around the scene, some caught in mid-fall, others settled on surfaces. The globe\'s glass is visible at the edges, slightly distorting the view and adding to the magical atmosphere. The lighting suggests a setting sun, casting long shadows and bathing the scene in a warm, golden glow that contrasts with the cool blues and whites of the snow. Every element is rendered in minute detail, inviting the viewer to explore the miniature world within the snow globe.",
"sampler": "uni_pc",
"scheduler": "normal",
"output_format": "webp",
"output_quality": 80,
"negative_prompt": "",
"number_of_images": 1
}
}' \
https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Add a payment method to run this model.
Sign in with GitHub
By signing in, you agree to our
terms of service and privacy policy
Output
{
"completed_at": "2024-07-27T18:27:55.344422Z",
"created_at": "2024-07-27T18:27:00.480000Z",
"data_removed": false,
"error": null,
"id": "6ghkhk9k01rj60cgynsaddg43g",
"input": {
"cfg": 3.5,
"shift": 1,
"width": 1024,
"height": 1024,
"prompt": "A hyper-detailed, close-up view inside a magical snow globe. The word \"Snow\" is intricately formed from miniature snowflakes and frost patterns, suspended in the center of the globe. Surrounding the word, a miniature winter wonderland unfolds in exquisite detail. Tiny evergreen trees, their branches laden with snow, create a dense forest. A frozen lake reflects the scene like a mirror, with microscopic ice skaters etching patterns on its surface. A miniature log cabin nestles in the trees, warm light spilling from its windows and smoke curling from the chimney. Tiny deer and rabbits leave intricate tracks in the snow. Countless snowflakes of varying sizes and intricate designs swirl around the scene, some caught in mid-fall, others settled on surfaces. The globe's glass is visible at the edges, slightly distorting the view and adding to the magical atmosphere. The lighting suggests a setting sun, casting long shadows and bathing the scene in a warm, golden glow that contrasts with the cool blues and whites of the snow. Every element is rendered in minute detail, inviting the viewer to explore the miniature world within the snow globe.",
"sampler": "uni_pc",
"scheduler": "normal",
"output_format": "webp",
"output_quality": 80,
"negative_prompt": "",
"number_of_images": 1
},
"logs": "Random seed set to: 1592606031\nRunning workflow\ngot prompt\nExecuting node 4, title: Load Checkpoint, class type: CheckpointLoaderSimple\nmodel_type FLOW\nunet unexpected: ['early_dits.0.attn.w1k.weight', 'early_dits.0.attn.w1o.weight', 'early_dits.0.attn.w1q.weight', 'early_dits.0.attn.w1v.weight', 'early_dits.0.mlp.c_fc1.weight', 'early_dits.0.mlp.c_fc2.weight', 'early_dits.0.mlp.c_proj.weight', 'early_dits.0.modCX.1.weight', 'early_dits.1.attn.w1k.weight', 'early_dits.1.attn.w1o.weight', 'early_dits.1.attn.w1q.weight', 'early_dits.1.attn.w1v.weight', 'early_dits.1.mlp.c_fc1.weight', 'early_dits.1.mlp.c_fc2.weight', 'early_dits.1.mlp.c_proj.weight', 'early_dits.1.modCX.1.weight', 'early_dits.2.attn.w1k.weight', 'early_dits.2.attn.w1o.weight', 'early_dits.2.attn.w1q.weight', 'early_dits.2.attn.w1v.weight', 'early_dits.2.mlp.c_fc1.weight', 'early_dits.2.mlp.c_fc2.weight', 'early_dits.2.mlp.c_proj.weight', 'early_dits.2.modCX.1.weight', 'early_linear.weight']\nUsing pytorch attention in VAE\nUsing pytorch attention in VAE\nloaded straight to GPU\nRequested to load AuraFlow\nLoading 1 new model\nExecuting node 10, title: ModelSamplingAuraFlow, class type: ModelSamplingAuraFlow\nRequested to load AuraT5Model\nLoading 1 new model\nExecuting node 6, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode\nExecuting node 7, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode\nExecuting node 5, title: Empty Latent Image, class type: EmptyLatentImage\nExecuting node 3, title: KSampler, class type: KSampler\nRequested to load AuraFlow\nLoading 1 new model\n 0%| | 0/25 [00:00<?, ?it/s]\n 4%|▍ | 1/25 [00:00<00:12, 1.91it/s]\n 8%|▊ | 2/25 [00:00<00:09, 2.56it/s]\n 12%|█▏ | 3/25 [00:01<00:09, 2.25it/s]\n 16%|█▌ | 4/25 [00:01<00:09, 2.15it/s]\n 20%|██ | 5/25 [00:02<00:09, 2.10it/s]\n 24%|██▍ | 6/25 [00:02<00:09, 2.08it/s]\n 28%|██▊ | 7/25 [00:03<00:08, 2.06it/s]\n 32%|███▏ | 8/25 [00:03<00:08, 2.04it/s]\n 36%|███▌ | 9/25 [00:04<00:11, 1.44it/s]\n 40%|████ | 10/25 [00:05<00:09, 1.58it/s]\n 44%|████▍ | 11/25 [00:05<00:08, 1.69it/s]\n 48%|████▊ | 12/25 [00:07<00:12, 1.04it/s]\n 52%|█████▏ | 13/25 [00:08<00:12, 1.04s/it]\n 56%|█████▌ | 14/25 [00:10<00:12, 1.15s/it]\n 60%|██████ | 15/25 [00:12<00:13, 1.31s/it]\n 64%|██████▍ | 16/25 [00:13<00:11, 1.33s/it]\n 68%|██████▊ | 17/25 [00:15<00:11, 1.45s/it]\n 72%|███████▏ | 18/25 [00:15<00:08, 1.26s/it]\n 76%|███████▌ | 19/25 [00:17<00:07, 1.23s/it]\n 80%|████████ | 20/25 [00:18<00:06, 1.23s/it]\n 84%|████████▍ | 21/25 [00:19<00:04, 1.14s/it]\n 88%|████████▊ | 22/25 [00:20<00:03, 1.05s/it]\n 92%|█████████▏| 23/25 [00:21<00:02, 1.10s/it]\n 96%|█████████▌| 24/25 [00:22<00:01, 1.07s/it]\n100%|██████████| 25/25 [00:23<00:00, 1.05it/s]\n100%|██████████| 25/25 [00:23<00:00, 1.09it/s]\nRequested to load AutoencoderKL\nLoading 1 new model\nExecuting node 8, title: VAE Decode, class type: VAEDecode\nExecuting node 9, title: Save Image, class type: SaveImage\nPrompt executed in 28.20 seconds\noutputs: {'9': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nComfyUI_00001_.png",
"metrics": {
"predict_time": 28.776588944,
"total_time": 54.864422
},
"output": [
"https://replicate.delivery/yhqm/ZP1qr4rIfHxfFkcLO2ZOJOOfKppIX1BGK2BnNsD0oDvWxdZmA/ComfyUI_00001_.webp"
],
"started_at": "2024-07-27T18:27:26.567833Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/6ghkhk9k01rj60cgynsaddg43g",
"cancel": "https://api.replicate.com/v1/predictions/6ghkhk9k01rj60cgynsaddg43g/cancel"
},
"version": "e784141e567364018b6c24297273e910b80c468c60ccb2a2a6642c034c7d43ee"
}Generated in
Random seed set to: 1592606031
Running workflow
got prompt
Executing node 4, title: Load Checkpoint, class type: CheckpointLoaderSimple
model_type FLOW
unet unexpected: ['early_dits.0.attn.w1k.weight', 'early_dits.0.attn.w1o.weight', 'early_dits.0.attn.w1q.weight', 'early_dits.0.attn.w1v.weight', 'early_dits.0.mlp.c_fc1.weight', 'early_dits.0.mlp.c_fc2.weight', 'early_dits.0.mlp.c_proj.weight', 'early_dits.0.modCX.1.weight', 'early_dits.1.attn.w1k.weight', 'early_dits.1.attn.w1o.weight', 'early_dits.1.attn.w1q.weight', 'early_dits.1.attn.w1v.weight', 'early_dits.1.mlp.c_fc1.weight', 'early_dits.1.mlp.c_fc2.weight', 'early_dits.1.mlp.c_proj.weight', 'early_dits.1.modCX.1.weight', 'early_dits.2.attn.w1k.weight', 'early_dits.2.attn.w1o.weight', 'early_dits.2.attn.w1q.weight', 'early_dits.2.attn.w1v.weight', 'early_dits.2.mlp.c_fc1.weight', 'early_dits.2.mlp.c_fc2.weight', 'early_dits.2.mlp.c_proj.weight', 'early_dits.2.modCX.1.weight', 'early_linear.weight']
Using pytorch attention in VAE
Using pytorch attention in VAE
loaded straight to GPU
Requested to load AuraFlow
Loading 1 new model
Executing node 10, title: ModelSamplingAuraFlow, class type: ModelSamplingAuraFlow
Requested to load AuraT5Model
Loading 1 new model
Executing node 6, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode
Executing node 7, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode
Executing node 5, title: Empty Latent Image, class type: EmptyLatentImage
Executing node 3, title: KSampler, class type: KSampler
Requested to load AuraFlow
Loading 1 new model
0%| | 0/25 [00:00<?, ?it/s]
4%|▍ | 1/25 [00:00<00:12, 1.91it/s]
8%|▊ | 2/25 [00:00<00:09, 2.56it/s]
12%|█▏ | 3/25 [00:01<00:09, 2.25it/s]
16%|█▌ | 4/25 [00:01<00:09, 2.15it/s]
20%|██ | 5/25 [00:02<00:09, 2.10it/s]
24%|██▍ | 6/25 [00:02<00:09, 2.08it/s]
28%|██▊ | 7/25 [00:03<00:08, 2.06it/s]
32%|███▏ | 8/25 [00:03<00:08, 2.04it/s]
36%|███▌ | 9/25 [00:04<00:11, 1.44it/s]
40%|████ | 10/25 [00:05<00:09, 1.58it/s]
44%|████▍ | 11/25 [00:05<00:08, 1.69it/s]
48%|████▊ | 12/25 [00:07<00:12, 1.04it/s]
52%|█████▏ | 13/25 [00:08<00:12, 1.04s/it]
56%|█████▌ | 14/25 [00:10<00:12, 1.15s/it]
60%|██████ | 15/25 [00:12<00:13, 1.31s/it]
64%|██████▍ | 16/25 [00:13<00:11, 1.33s/it]
68%|██████▊ | 17/25 [00:15<00:11, 1.45s/it]
72%|███████▏ | 18/25 [00:15<00:08, 1.26s/it]
76%|███████▌ | 19/25 [00:17<00:07, 1.23s/it]
80%|████████ | 20/25 [00:18<00:06, 1.23s/it]
84%|████████▍ | 21/25 [00:19<00:04, 1.14s/it]
88%|████████▊ | 22/25 [00:20<00:03, 1.05s/it]
92%|█████████▏| 23/25 [00:21<00:02, 1.10s/it]
96%|█████████▌| 24/25 [00:22<00:01, 1.07s/it]
100%|██████████| 25/25 [00:23<00:00, 1.05it/s]
100%|██████████| 25/25 [00:23<00:00, 1.09it/s]
Requested to load AutoencoderKL
Loading 1 new model
Executing node 8, title: VAE Decode, class type: VAEDecode
Executing node 9, title: Save Image, class type: SaveImage
Prompt executed in 28.20 seconds
outputs: {'9': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
ComfyUI_00001_.png