Prediction
fofr/sd3-explorer:ba3320806125ae93991c899010c998e4ee6a9dc6bdd89aeb6ecbd992815650a9Input
- seed
- 123
- model
- sd3_medium_incl_clips_t5xxlfp16.safetensors
- shift
- 3
- steps
- 28
- width
- 1024
- height
- 1024
- prompt
- a closeup photo of a man
- sampler
- dpmpp_2m
- scheduler
- sgm_uniform
- output_format
- webp
- guidance_scale
- 1.5
- output_quality
- 80
- negative_prompt
- number_of_images
- 1
- triple_prompt_t5
- use_triple_prompt
- triple_prompt_clip_g
- triple_prompt_clip_l
- negative_conditioning_end
- 0
- triple_prompt_empty_padding
{
"seed": 123,
"model": "sd3_medium_incl_clips_t5xxlfp16.safetensors",
"shift": 3,
"steps": 28,
"width": 1024,
"height": 1024,
"prompt": "a closeup photo of a man",
"sampler": "dpmpp_2m",
"scheduler": "sgm_uniform",
"output_format": "webp",
"guidance_scale": 1.5,
"output_quality": 80,
"negative_prompt": "",
"number_of_images": 1,
"triple_prompt_t5": "",
"use_triple_prompt": false,
"triple_prompt_clip_g": "",
"triple_prompt_clip_l": "",
"negative_conditioning_end": 0,
"triple_prompt_empty_padding": true
}
npm install replicate
REPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
import Replicate from "replicate";
import fs from "node:fs";
const replicate = new Replicate({
auth: process.env.REPLICATE_API_TOKEN,
});
Run fofr/sd3-explorer using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"fofr/sd3-explorer:ba3320806125ae93991c899010c998e4ee6a9dc6bdd89aeb6ecbd992815650a9",
{
input: {
seed: 123,
model: "sd3_medium_incl_clips_t5xxlfp16.safetensors",
shift: 3,
steps: 28,
width: 1024,
height: 1024,
prompt: "a closeup photo of a man",
sampler: "dpmpp_2m",
scheduler: "sgm_uniform",
output_format: "webp",
guidance_scale: 1.5,
output_quality: 80,
negative_prompt: "",
number_of_images: 1,
triple_prompt_t5: "",
use_triple_prompt: false,
triple_prompt_clip_g: "",
triple_prompt_clip_l: "",
negative_conditioning_end: 0,
triple_prompt_empty_padding: true
}
}
);
// 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.
pip install replicate
REPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
import replicate
Run fofr/sd3-explorer using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"fofr/sd3-explorer:ba3320806125ae93991c899010c998e4ee6a9dc6bdd89aeb6ecbd992815650a9",
input={
"seed": 123,
"model": "sd3_medium_incl_clips_t5xxlfp16.safetensors",
"shift": 3,
"steps": 28,
"width": 1024,
"height": 1024,
"prompt": "a closeup photo of a man",
"sampler": "dpmpp_2m",
"scheduler": "sgm_uniform",
"output_format": "webp",
"guidance_scale": 1.5,
"output_quality": 80,
"negative_prompt": "",
"number_of_images": 1,
"triple_prompt_t5": "",
"use_triple_prompt": False,
"triple_prompt_clip_g": "",
"triple_prompt_clip_l": "",
"negative_conditioning_end": 0,
"triple_prompt_empty_padding": True
}
)
print(output)
To learn more, take a look at the guide on getting started with Python.
REPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run fofr/sd3-explorer 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": "fofr/sd3-explorer:ba3320806125ae93991c899010c998e4ee6a9dc6bdd89aeb6ecbd992815650a9",
"input": {
"seed": 123,
"model": "sd3_medium_incl_clips_t5xxlfp16.safetensors",
"shift": 3,
"steps": 28,
"width": 1024,
"height": 1024,
"prompt": "a closeup photo of a man",
"sampler": "dpmpp_2m",
"scheduler": "sgm_uniform",
"output_format": "webp",
"guidance_scale": 1.5,
"output_quality": 80,
"negative_prompt": "",
"number_of_images": 1,
"triple_prompt_t5": "",
"use_triple_prompt": false,
"triple_prompt_clip_g": "",
"triple_prompt_clip_l": "",
"negative_conditioning_end": 0,
"triple_prompt_empty_padding": true
}
}' \
https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
brew install cog
If 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/fofr/sd3-explorer@sha256:ba3320806125ae93991c899010c998e4ee6a9dc6bdd89aeb6ecbd992815650a9 \
-i 'seed=123' \
-i 'model="sd3_medium_incl_clips_t5xxlfp16.safetensors"' \
-i 'shift=3' \
-i 'steps=28' \
-i 'width=1024' \
-i 'height=1024' \
-i 'prompt="a closeup photo of a man"' \
-i 'sampler="dpmpp_2m"' \
-i 'scheduler="sgm_uniform"' \
-i 'output_format="webp"' \
-i 'guidance_scale=1.5' \
-i 'output_quality=80' \
-i 'negative_prompt=""' \
-i 'number_of_images=1' \
-i 'triple_prompt_t5=""' \
-i 'use_triple_prompt=false' \
-i 'triple_prompt_clip_g=""' \
-i 'triple_prompt_clip_l=""' \
-i 'negative_conditioning_end=0' \
-i 'triple_prompt_empty_padding=true'
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/fofr/sd3-explorer@sha256:ba3320806125ae93991c899010c998e4ee6a9dc6bdd89aeb6ecbd992815650a9
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 123, "model": "sd3_medium_incl_clips_t5xxlfp16.safetensors", "shift": 3, "steps": 28, "width": 1024, "height": 1024, "prompt": "a closeup photo of a man", "sampler": "dpmpp_2m", "scheduler": "sgm_uniform", "output_format": "webp", "guidance_scale": 1.5, "output_quality": 80, "negative_prompt": "", "number_of_images": 1, "triple_prompt_t5": "", "use_triple_prompt": false, "triple_prompt_clip_g": "", "triple_prompt_clip_l": "", "negative_conditioning_end": 0, "triple_prompt_empty_padding": true } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{
"completed_at": "2024-06-18T12:48:14.359400Z",
"created_at": "2024-06-18T12:47:57.333000Z",
"data_removed": false,
"error": null,
"id": "kb3404y5jnrgg0cg5dhrrwnatc",
"input": {
"seed": 123,
"model": "sd3_medium_incl_clips_t5xxlfp16.safetensors",
"shift": 3,
"steps": 28,
"width": 1024,
"height": 1024,
"prompt": "a closeup photo of a man",
"sampler": "dpmpp_2m",
"scheduler": "sgm_uniform",
"output_format": "webp",
"guidance_scale": 1.5,
"output_quality": 80,
"negative_prompt": "",
"number_of_images": 1,
"triple_prompt_t5": "",
"use_triple_prompt": false,
"triple_prompt_clip_g": "",
"triple_prompt_clip_l": "",
"negative_conditioning_end": 0,
"triple_prompt_empty_padding": true
},
"logs": "Seed set to: 123\nChecking weights\n✅ sd3_medium_incl_clips_t5xxlfp16.safetensors exists in ComfyUI/models/checkpoints\n====================================\nRunning workflow\ngot prompt\nExecuting node 252, title: Load Checkpoint, class type: CheckpointLoaderSimple\nmodel_type FLOW\nUsing pytorch attention in VAE\nUsing pytorch attention in VAE\nloaded straight to GPU\nRequested to load SD3\nLoading 1 new model\nExecuting node 13, title: ModelSamplingSD3, class type: ModelSamplingSD3\nExecuting node 6, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode\nRequested to load SD3ClipModel_\nLoading 1 new model\nExecuting node 289, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode\nExecuting node 274, title: 🔧 SD3 Negative Conditioning, class type: SD3NegativeConditioning+\nExecuting node 271, title: KSampler, class type: KSampler\nRequested to load SD3\nLoading 1 new model\n 0%| | 0/28 [00:00<?, ?it/s]\n 7%|▋ | 2/28 [00:00<00:06, 4.29it/s]\n 11%|█ | 3/28 [00:00<00:05, 4.27it/s]\n 14%|█▍ | 4/28 [00:00<00:05, 4.25it/s]\n 18%|█▊ | 5/28 [00:01<00:05, 4.25it/s]\n 21%|██▏ | 6/28 [00:01<00:05, 4.25it/s]\n 25%|██▌ | 7/28 [00:01<00:04, 4.24it/s]\n 29%|██▊ | 8/28 [00:01<00:04, 4.24it/s]\n 32%|███▏ | 9/28 [00:02<00:04, 4.23it/s]\n 36%|███▌ | 10/28 [00:02<00:04, 4.24it/s]\n 39%|███▉ | 11/28 [00:02<00:04, 4.24it/s]\n 43%|████▎ | 12/28 [00:02<00:03, 4.24it/s]\n 46%|████▋ | 13/28 [00:03<00:03, 4.24it/s]\n 50%|█████ | 14/28 [00:03<00:03, 4.23it/s]\n 54%|█████▎ | 15/28 [00:03<00:03, 4.23it/s]\n 57%|█████▋ | 16/28 [00:03<00:02, 4.23it/s]\n 61%|██████ | 17/28 [00:04<00:02, 4.23it/s]\n 64%|██████▍ | 18/28 [00:04<00:02, 4.23it/s]\n 68%|██████▊ | 19/28 [00:04<00:02, 4.23it/s]\n 71%|███████▏ | 20/28 [00:04<00:01, 4.23it/s]\n 75%|███████▌ | 21/28 [00:04<00:01, 4.23it/s]\n 79%|███████▊ | 22/28 [00:05<00:01, 4.23it/s]\n 82%|████████▏ | 23/28 [00:05<00:01, 4.23it/s]\n 86%|████████▌ | 24/28 [00:05<00:00, 4.22it/s]\n 89%|████████▉ | 25/28 [00:05<00:00, 4.22it/s]\n 93%|█████████▎| 26/28 [00:06<00:00, 4.22it/s]\n 96%|█████████▋| 27/28 [00:06<00:00, 4.22it/s]\n100%|██████████| 28/28 [00:06<00:00, 4.21it/s]\n100%|██████████| 28/28 [00:06<00:00, 4.23it/s]\nRequested to load AutoencodingEngine\nExecuting node 231, title: VAE Decode, class type: VAEDecode\nLoading 1 new model\nExecuting node 273, title: Save Image, class type: SaveImage\nPrompt executed in 15.44 seconds\noutputs: {'273': {'images': [{'filename': 'SD3_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nSD3_00001_.png",
"metrics": {
"predict_time": 16.990680244,
"total_time": 17.0264
},
"output": [
"https://replicate.delivery/pbxt/y2URI55il8qwKJ8w5gPS7ekO7dep2urdjUDVEEzfwRFagmfLB/SD3_00001_.webp"
],
"started_at": "2024-06-18T12:47:57.368720Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/kb3404y5jnrgg0cg5dhrrwnatc",
"cancel": "https://api.replicate.com/v1/predictions/kb3404y5jnrgg0cg5dhrrwnatc/cancel",
"web": "https://replicate.com/p/kb3404y5jnrgg0cg5dhrrwnatc"
},
"version": "ba3320806125ae93991c899010c998e4ee6a9dc6bdd89aeb6ecbd992815650a9"
}
Seed set to: 123
Checking weights
✅ sd3_medium_incl_clips_t5xxlfp16.safetensors exists in ComfyUI/models/checkpoints
====================================
Running workflow
got prompt
Executing node 252, title: Load Checkpoint, class type: CheckpointLoaderSimple
model_type FLOW
Using pytorch attention in VAE
Using pytorch attention in VAE
loaded straight to GPU
Requested to load SD3
Loading 1 new model
Executing node 13, title: ModelSamplingSD3, class type: ModelSamplingSD3
Executing node 6, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode
Requested to load SD3ClipModel_
Loading 1 new model
Executing node 289, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode
Executing node 274, title: 🔧 SD3 Negative Conditioning, class type: SD3NegativeConditioning+
Executing node 271, title: KSampler, class type: KSampler
Requested to load SD3
Loading 1 new model
0%| | 0/28 [00:00<?, ?it/s]
7%|▋ | 2/28 [00:00<00:06, 4.29it/s]
11%|█ | 3/28 [00:00<00:05, 4.27it/s]
14%|█▍ | 4/28 [00:00<00:05, 4.25it/s]
18%|█▊ | 5/28 [00:01<00:05, 4.25it/s]
21%|██▏ | 6/28 [00:01<00:05, 4.25it/s]
25%|██▌ | 7/28 [00:01<00:04, 4.24it/s]
29%|██▊ | 8/28 [00:01<00:04, 4.24it/s]
32%|███▏ | 9/28 [00:02<00:04, 4.23it/s]
36%|███▌ | 10/28 [00:02<00:04, 4.24it/s]
39%|███▉ | 11/28 [00:02<00:04, 4.24it/s]
43%|████▎ | 12/28 [00:02<00:03, 4.24it/s]
46%|████▋ | 13/28 [00:03<00:03, 4.24it/s]
50%|█████ | 14/28 [00:03<00:03, 4.23it/s]
54%|█████▎ | 15/28 [00:03<00:03, 4.23it/s]
57%|█████▋ | 16/28 [00:03<00:02, 4.23it/s]
61%|██████ | 17/28 [00:04<00:02, 4.23it/s]
64%|██████▍ | 18/28 [00:04<00:02, 4.23it/s]
68%|██████▊ | 19/28 [00:04<00:02, 4.23it/s]
71%|███████▏ | 20/28 [00:04<00:01, 4.23it/s]
75%|███████▌ | 21/28 [00:04<00:01, 4.23it/s]
79%|███████▊ | 22/28 [00:05<00:01, 4.23it/s]
82%|████████▏ | 23/28 [00:05<00:01, 4.23it/s]
86%|████████▌ | 24/28 [00:05<00:00, 4.22it/s]
89%|████████▉ | 25/28 [00:05<00:00, 4.22it/s]
93%|█████████▎| 26/28 [00:06<00:00, 4.22it/s]
96%|█████████▋| 27/28 [00:06<00:00, 4.22it/s]
100%|██████████| 28/28 [00:06<00:00, 4.21it/s]
100%|██████████| 28/28 [00:06<00:00, 4.23it/s]
Requested to load AutoencodingEngine
Executing node 231, title: VAE Decode, class type: VAEDecode
Loading 1 new model
Executing node 273, title: Save Image, class type: SaveImage
Prompt executed in 15.44 seconds
outputs: {'273': {'images': [{'filename': 'SD3_00001_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
SD3_00001_.png