Readme
An experiment in accurate captioning for memes with text. Original training art by fallenchungus, now posting at https://x.com/datssmojo
A FLUX model fine-tuned on fallenchungus comics (Updated 5 months, 2 weeks ago)
Run this model in Node.js with one line of code:
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 deepfates/flux-fallenchungus using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"deepfates/flux-fallenchungus:810f7563cf2dcb3edf1988f319b5c2d7205253c186417664a67c87707ef777f7",
{
input: {
seed: 40402,
model: "dev",
prompt: " CHNGS line drawing drawing of a gold mannequin head with a large wig made of colorful flowers and green leafy vines. the caption reads WELCOME TO THE DEEP FATES PROGRAM",
go_fast: true,
lora_scale: 1,
megapixels: "1",
num_outputs: 1,
aspect_ratio: "1:1",
output_format: "webp",
guidance_scale: 4,
output_quality: 80,
prompt_strength: 0.8,
extra_lora_scale: 1,
num_inference_steps: 50
}
}
);
// 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 deepfates/flux-fallenchungus using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"deepfates/flux-fallenchungus:810f7563cf2dcb3edf1988f319b5c2d7205253c186417664a67c87707ef777f7",
input={
"seed": 40402,
"model": "dev",
"prompt": " CHNGS line drawing drawing of a gold mannequin head with a large wig made of colorful flowers and green leafy vines. the caption reads WELCOME TO THE DEEP FATES PROGRAM",
"go_fast": True,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 1,
"aspect_ratio": "1:1",
"output_format": "webp",
"guidance_scale": 4,
"output_quality": 80,
"prompt_strength": 0.8,
"extra_lora_scale": 1,
"num_inference_steps": 50
}
)
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 deepfates/flux-fallenchungus 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": "deepfates/flux-fallenchungus:810f7563cf2dcb3edf1988f319b5c2d7205253c186417664a67c87707ef777f7",
"input": {
"seed": 40402,
"model": "dev",
"prompt": " CHNGS line drawing drawing of a gold mannequin head with a large wig made of colorful flowers and green leafy vines. the caption reads WELCOME TO THE DEEP FATES PROGRAM",
"go_fast": true,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 1,
"aspect_ratio": "1:1",
"output_format": "webp",
"guidance_scale": 4,
"output_quality": 80,
"prompt_strength": 0.8,
"extra_lora_scale": 1,
"num_inference_steps": 50
}
}' \
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/deepfates/flux-fallenchungus@sha256:810f7563cf2dcb3edf1988f319b5c2d7205253c186417664a67c87707ef777f7 \
-i 'seed=40402' \
-i 'model="dev"' \
-i 'prompt=" CHNGS line drawing drawing of a gold mannequin head with a large wig made of colorful flowers and green leafy vines. the caption reads WELCOME TO THE DEEP FATES PROGRAM"' \
-i 'go_fast=true' \
-i 'lora_scale=1' \
-i 'megapixels="1"' \
-i 'num_outputs=1' \
-i 'aspect_ratio="1:1"' \
-i 'output_format="webp"' \
-i 'guidance_scale=4' \
-i 'output_quality=80' \
-i 'prompt_strength=0.8' \
-i 'extra_lora_scale=1' \
-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/deepfates/flux-fallenchungus@sha256:810f7563cf2dcb3edf1988f319b5c2d7205253c186417664a67c87707ef777f7
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 40402, "model": "dev", "prompt": " CHNGS line drawing drawing of a gold mannequin head with a large wig made of colorful flowers and green leafy vines. the caption reads WELCOME TO THE DEEP FATES PROGRAM", "go_fast": true, "lora_scale": 1, "megapixels": "1", "num_outputs": 1, "aspect_ratio": "1:1", "output_format": "webp", "guidance_scale": 4, "output_quality": 80, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 50 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Add a payment method to run this model.
By signing in, you agree to our
terms of service and privacy policy
{
"completed_at": "2025-01-08T21:00:04.476377Z",
"created_at": "2025-01-08T20:59:56.803000Z",
"data_removed": false,
"error": null,
"id": "58bbmgc40drm80cm8yvvwwsv7w",
"input": {
"seed": 40402,
"model": "dev",
"prompt": " CHNGS line drawing drawing of a gold mannequin head with a large wig made of colorful flowers and green leafy vines. the caption reads WELCOME TO THE DEEP FATES PROGRAM",
"go_fast": true,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 1,
"aspect_ratio": "1:1",
"output_format": "webp",
"guidance_scale": 4,
"output_quality": 80,
"prompt_strength": 0.8,
"extra_lora_scale": 1,
"num_inference_steps": 50
},
"logs": "free=29090082111488\nDownloading weights\n2025-01-08T20:59:56Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpe_srp632/weights url=https://replicate.delivery/xezq/N4MICfLsnzyAKCROeM4SiQUWOCu0HxDrtWPVIejfDYEywlMQB/trained_model.tar\n2025-01-08T20:59:59Z | INFO | [ Complete ] dest=/tmp/tmpe_srp632/weights size=\"172 MB\" total_elapsed=2.520s url=https://replicate.delivery/xezq/N4MICfLsnzyAKCROeM4SiQUWOCu0HxDrtWPVIejfDYEywlMQB/trained_model.tar\nDownloaded weights in 2.54s\n2025-01-08 20:59:59.439 | INFO | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/245b1ac6b179a69f\n2025-01-08 20:59:59.509 | INFO | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded\n2025-01-08 20:59:59.510 | DEBUG | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys\n2025-01-08 20:59:59.510 | DEBUG | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted\nApplying LoRA: 0%| | 0/304 [00:00<?, ?it/s]\nApplying LoRA: 41%|████▏ | 126/304 [00:00<00:00, 1237.22it/s]\nApplying LoRA: 82%|████████▏ | 250/304 [00:00<00:00, 948.25it/s] \nApplying LoRA: 100%|██████████| 304/304 [00:00<00:00, 982.00it/s]\n2025-01-08 20:59:59.820 | SUCCESS | fp8.lora_loading:load_lora:539 - LoRA applied in 0.38s\nrunning quantized prediction\nUsing seed: 40402\n 0%| | 0/50 [00:00<?, ?it/s]\n 4%|▍ | 2/50 [00:00<00:02, 18.20it/s]\n 8%|▊ | 4/50 [00:00<00:03, 13.57it/s]\n 12%|█▏ | 6/50 [00:00<00:03, 12.53it/s]\n 16%|█▌ | 8/50 [00:00<00:03, 12.11it/s]\n 20%|██ | 10/50 [00:00<00:03, 11.85it/s]\n 24%|██▍ | 12/50 [00:00<00:03, 11.50it/s]\n 28%|██▊ | 14/50 [00:01<00:03, 11.45it/s]\n 32%|███▏ | 16/50 [00:01<00:02, 11.46it/s]\n 36%|███▌ | 18/50 [00:01<00:02, 11.47it/s]\n 40%|████ | 20/50 [00:01<00:02, 11.46it/s]\n 44%|████▍ | 22/50 [00:01<00:02, 11.39it/s]\n 48%|████▊ | 24/50 [00:02<00:02, 11.30it/s]\n 52%|█████▏ | 26/50 [00:02<00:02, 11.32it/s]\n 56%|█████▌ | 28/50 [00:02<00:01, 11.37it/s]\n 60%|██████ | 30/50 [00:02<00:01, 11.41it/s]\n 64%|██████▍ | 32/50 [00:02<00:01, 11.41it/s]\n 68%|██████▊ | 34/50 [00:02<00:01, 11.35it/s]\n 72%|███████▏ | 36/50 [00:03<00:01, 11.33it/s]\n 76%|███████▌ | 38/50 [00:03<00:01, 11.35it/s]\n 80%|████████ | 40/50 [00:03<00:00, 11.39it/s]\n 84%|████████▍ | 42/50 [00:03<00:00, 11.40it/s]\n 88%|████████▊ | 44/50 [00:03<00:00, 11.38it/s]\n 92%|█████████▏| 46/50 [00:03<00:00, 11.35it/s]\n 96%|█████████▌| 48/50 [00:04<00:00, 11.35it/s]\n100%|██████████| 50/50 [00:04<00:00, 11.35it/s]\n100%|██████████| 50/50 [00:04<00:00, 11.54it/s]\nTotal safe images: 1 out of 1",
"metrics": {
"predict_time": 7.582019316,
"total_time": 7.673377
},
"output": [
"https://replicate.delivery/xezq/PWArKmjTMZIBC9W29nzz87ZnIOTyXRHHVqG2qwOBrdMVZyAF/out-0.webp"
],
"started_at": "2025-01-08T20:59:56.894357Z",
"status": "succeeded",
"urls": {
"stream": "https://stream.replicate.com/v1/files/bcwr-tflmfsccv46utl4d33w26abar4x3qf25mmn5n7hngdsr5wkuinua",
"get": "https://api.replicate.com/v1/predictions/58bbmgc40drm80cm8yvvwwsv7w",
"cancel": "https://api.replicate.com/v1/predictions/58bbmgc40drm80cm8yvvwwsv7w/cancel"
},
"version": "810f7563cf2dcb3edf1988f319b5c2d7205253c186417664a67c87707ef777f7"
}
free=29090082111488
Downloading weights
2025-01-08T20:59:56Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpe_srp632/weights url=https://replicate.delivery/xezq/N4MICfLsnzyAKCROeM4SiQUWOCu0HxDrtWPVIejfDYEywlMQB/trained_model.tar
2025-01-08T20:59:59Z | INFO | [ Complete ] dest=/tmp/tmpe_srp632/weights size="172 MB" total_elapsed=2.520s url=https://replicate.delivery/xezq/N4MICfLsnzyAKCROeM4SiQUWOCu0HxDrtWPVIejfDYEywlMQB/trained_model.tar
Downloaded weights in 2.54s
2025-01-08 20:59:59.439 | INFO | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/245b1ac6b179a69f
2025-01-08 20:59:59.509 | INFO | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded
2025-01-08 20:59:59.510 | DEBUG | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-08 20:59:59.510 | DEBUG | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA: 0%| | 0/304 [00:00<?, ?it/s]
Applying LoRA: 41%|████▏ | 126/304 [00:00<00:00, 1237.22it/s]
Applying LoRA: 82%|████████▏ | 250/304 [00:00<00:00, 948.25it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 982.00it/s]
2025-01-08 20:59:59.820 | SUCCESS | fp8.lora_loading:load_lora:539 - LoRA applied in 0.38s
running quantized prediction
Using seed: 40402
0%| | 0/50 [00:00<?, ?it/s]
4%|▍ | 2/50 [00:00<00:02, 18.20it/s]
8%|▊ | 4/50 [00:00<00:03, 13.57it/s]
12%|█▏ | 6/50 [00:00<00:03, 12.53it/s]
16%|█▌ | 8/50 [00:00<00:03, 12.11it/s]
20%|██ | 10/50 [00:00<00:03, 11.85it/s]
24%|██▍ | 12/50 [00:00<00:03, 11.50it/s]
28%|██▊ | 14/50 [00:01<00:03, 11.45it/s]
32%|███▏ | 16/50 [00:01<00:02, 11.46it/s]
36%|███▌ | 18/50 [00:01<00:02, 11.47it/s]
40%|████ | 20/50 [00:01<00:02, 11.46it/s]
44%|████▍ | 22/50 [00:01<00:02, 11.39it/s]
48%|████▊ | 24/50 [00:02<00:02, 11.30it/s]
52%|█████▏ | 26/50 [00:02<00:02, 11.32it/s]
56%|█████▌ | 28/50 [00:02<00:01, 11.37it/s]
60%|██████ | 30/50 [00:02<00:01, 11.41it/s]
64%|██████▍ | 32/50 [00:02<00:01, 11.41it/s]
68%|██████▊ | 34/50 [00:02<00:01, 11.35it/s]
72%|███████▏ | 36/50 [00:03<00:01, 11.33it/s]
76%|███████▌ | 38/50 [00:03<00:01, 11.35it/s]
80%|████████ | 40/50 [00:03<00:00, 11.39it/s]
84%|████████▍ | 42/50 [00:03<00:00, 11.40it/s]
88%|████████▊ | 44/50 [00:03<00:00, 11.38it/s]
92%|█████████▏| 46/50 [00:03<00:00, 11.35it/s]
96%|█████████▌| 48/50 [00:04<00:00, 11.35it/s]
100%|██████████| 50/50 [00:04<00:00, 11.35it/s]
100%|██████████| 50/50 [00:04<00:00, 11.54it/s]
Total safe images: 1 out of 1
This model costs approximately $0.010 to run on Replicate, or 100 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.
This model runs on Nvidia H100 GPU hardware. Predictions typically complete within 7 seconds.
An experiment in accurate captioning for memes with text. Original training art by fallenchungus, now posting at https://x.com/datssmojo
This model is warm. You'll get a fast response if the model is warm and already running, and a slower response if the model is cold and starting up.
This model costs approximately $0.010 to run on Replicate, but this varies depending on your inputs. View more.
Choose a file from your machine
Hint: you can also drag files onto the input
Choose a file from your machine
Hint: you can also drag files onto the input
free=29090082111488
Downloading weights
2025-01-08T20:59:56Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpe_srp632/weights url=https://replicate.delivery/xezq/N4MICfLsnzyAKCROeM4SiQUWOCu0HxDrtWPVIejfDYEywlMQB/trained_model.tar
2025-01-08T20:59:59Z | INFO | [ Complete ] dest=/tmp/tmpe_srp632/weights size="172 MB" total_elapsed=2.520s url=https://replicate.delivery/xezq/N4MICfLsnzyAKCROeM4SiQUWOCu0HxDrtWPVIejfDYEywlMQB/trained_model.tar
Downloaded weights in 2.54s
2025-01-08 20:59:59.439 | INFO | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/245b1ac6b179a69f
2025-01-08 20:59:59.509 | INFO | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded
2025-01-08 20:59:59.510 | DEBUG | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-08 20:59:59.510 | DEBUG | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA: 0%| | 0/304 [00:00<?, ?it/s]
Applying LoRA: 41%|████▏ | 126/304 [00:00<00:00, 1237.22it/s]
Applying LoRA: 82%|████████▏ | 250/304 [00:00<00:00, 948.25it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 982.00it/s]
2025-01-08 20:59:59.820 | SUCCESS | fp8.lora_loading:load_lora:539 - LoRA applied in 0.38s
running quantized prediction
Using seed: 40402
0%| | 0/50 [00:00<?, ?it/s]
4%|▍ | 2/50 [00:00<00:02, 18.20it/s]
8%|▊ | 4/50 [00:00<00:03, 13.57it/s]
12%|█▏ | 6/50 [00:00<00:03, 12.53it/s]
16%|█▌ | 8/50 [00:00<00:03, 12.11it/s]
20%|██ | 10/50 [00:00<00:03, 11.85it/s]
24%|██▍ | 12/50 [00:00<00:03, 11.50it/s]
28%|██▊ | 14/50 [00:01<00:03, 11.45it/s]
32%|███▏ | 16/50 [00:01<00:02, 11.46it/s]
36%|███▌ | 18/50 [00:01<00:02, 11.47it/s]
40%|████ | 20/50 [00:01<00:02, 11.46it/s]
44%|████▍ | 22/50 [00:01<00:02, 11.39it/s]
48%|████▊ | 24/50 [00:02<00:02, 11.30it/s]
52%|█████▏ | 26/50 [00:02<00:02, 11.32it/s]
56%|█████▌ | 28/50 [00:02<00:01, 11.37it/s]
60%|██████ | 30/50 [00:02<00:01, 11.41it/s]
64%|██████▍ | 32/50 [00:02<00:01, 11.41it/s]
68%|██████▊ | 34/50 [00:02<00:01, 11.35it/s]
72%|███████▏ | 36/50 [00:03<00:01, 11.33it/s]
76%|███████▌ | 38/50 [00:03<00:01, 11.35it/s]
80%|████████ | 40/50 [00:03<00:00, 11.39it/s]
84%|████████▍ | 42/50 [00:03<00:00, 11.40it/s]
88%|████████▊ | 44/50 [00:03<00:00, 11.38it/s]
92%|█████████▏| 46/50 [00:03<00:00, 11.35it/s]
96%|█████████▌| 48/50 [00:04<00:00, 11.35it/s]
100%|██████████| 50/50 [00:04<00:00, 11.35it/s]
100%|██████████| 50/50 [00:04<00:00, 11.54it/s]
Total safe images: 1 out of 1