impetusdesign/rqi-txc-itp | Run with an API on Replicate

Cold

Public

364 runs

A100 (80GB)

Playground API Examples README Versions

Input

Run this model in Node.js with one line of code:

npx create-replicate --model=impetusdesign/rqi-txc-itp

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set 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 impetusdesign/rqi-txc-itp using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "impetusdesign/rqi-txc-itp:7a90584fb703549dc2c78392f4ab8007846f6bd9ffe0e5e593d0dac31396009f",
  {
    input: {
      seed: 42,
      image: "https://replicate.delivery/pbxt/M65x6u7RptL8vxU5KSYZpkckkkkknvJT45BhJ5tN6ZgLzWWk/replicatetest.png",
      prompt: "A seamless pattern having Lotus and Daffodils",
      ip_scale: 0.5,
      num_outputs: 1,
      aspect_ratio: "1:1"
    }
  }
);

// 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 replicate

Set 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 replicate

Run impetusdesign/rqi-txc-itp using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "impetusdesign/rqi-txc-itp:7a90584fb703549dc2c78392f4ab8007846f6bd9ffe0e5e593d0dac31396009f",
    input={
        "seed": 42,
        "image": "https://replicate.delivery/pbxt/M65x6u7RptL8vxU5KSYZpkckkkkknvJT45BhJ5tN6ZgLzWWk/replicatetest.png",
        "prompt": "A seamless pattern having Lotus and Daffodils",
        "ip_scale": 0.5,
        "num_outputs": 1,
        "aspect_ratio": "1:1"
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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 impetusdesign/rqi-txc-itp 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": "impetusdesign/rqi-txc-itp:7a90584fb703549dc2c78392f4ab8007846f6bd9ffe0e5e593d0dac31396009f",
    "input": {
      "seed": 42,
      "image": "https://replicate.delivery/pbxt/M65x6u7RptL8vxU5KSYZpkckkkkknvJT45BhJ5tN6ZgLzWWk/replicatetest.png",
      "prompt": "A seamless pattern having Lotus and Daffodils",
      "ip_scale": 0.5,
      "num_outputs": 1,
      "aspect_ratio": "1:1"
    }
  }' \
  https://api.replicate.com/v1/predictions

To 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 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/impetusdesign/rqi-txc-itp@sha256:7a90584fb703549dc2c78392f4ab8007846f6bd9ffe0e5e593d0dac31396009f \
  -i 'seed=42' \
  -i 'image="https://replicate.delivery/pbxt/M65x6u7RptL8vxU5KSYZpkckkkkknvJT45BhJ5tN6ZgLzWWk/replicatetest.png"' \
  -i 'prompt="A seamless pattern having Lotus and Daffodils"' \
  -i 'ip_scale=0.5' \
  -i 'num_outputs=1' \
  -i 'aspect_ratio="1:1"'

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/impetusdesign/rqi-txc-itp@sha256:7a90584fb703549dc2c78392f4ab8007846f6bd9ffe0e5e593d0dac31396009f
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": 42,
      "image": "https://replicate.delivery/pbxt/M65x6u7RptL8vxU5KSYZpkckkkkknvJT45BhJ5tN6ZgLzWWk/replicatetest.png",
      "prompt": "A seamless pattern having Lotus and Daffodils",
      "ip_scale": 0.5,
      "num_outputs": 1,
      "aspect_ratio": "1:1"
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2024-12-06T14:54:45.968366Z",
  "created_at": "2024-12-06T14:29:51.742000Z",
  "data_removed": false,
  "error": null,
  "id": "5mssvvm5zsrj60ckkhg88a549c",
  "input": {
    "image": "https://replicate.delivery/pbxt/M65x6u7RptL8vxU5KSYZpkckkkkknvJT45BhJ5tN6ZgLzWWk/replicatetest.png",
    "scale": 0.5,
    "prompt": "A seamless pattern having Lotus and Daffodils"
  },
  "logs": "INFO:predict:Processing input image: /tmp/tmpf8jubcaqreplicatetest.png\nINFO:predict:Using prompt: A seamless pattern having Lotus and Daffodils\nINFO:predict:Scale value: 0.5\nINFO:predict:Generating output image...\n  0%|          | 0/24 [00:00<?, ?it/s]\n  4%|▍         | 1/24 [00:00<00:13,  1.66it/s]\n  8%|▊         | 2/24 [00:01<00:11,  2.00it/s]\n 12%|█▎        | 3/24 [00:01<00:11,  1.86it/s]\n 17%|█▋        | 4/24 [00:02<00:11,  1.79it/s]\n 21%|██        | 5/24 [00:02<00:10,  1.76it/s]\n 25%|██▌       | 6/24 [00:03<00:10,  1.74it/s]\n 29%|██▉       | 7/24 [00:03<00:09,  1.73it/s]\n 33%|███▎      | 8/24 [00:04<00:09,  1.73it/s]\n 38%|███▊      | 9/24 [00:05<00:08,  1.72it/s]\n 42%|████▏     | 10/24 [00:05<00:08,  1.72it/s]\n 46%|████▌     | 11/24 [00:06<00:07,  1.71it/s]\n 50%|█████     | 12/24 [00:06<00:07,  1.71it/s]\n 54%|█████▍    | 13/24 [00:07<00:06,  1.71it/s]\n 58%|█████▊    | 14/24 [00:08<00:05,  1.71it/s]\n 62%|██████▎   | 15/24 [00:08<00:05,  1.71it/s]\n 67%|██████▋   | 16/24 [00:09<00:04,  1.71it/s]\n 71%|███████   | 17/24 [00:09<00:04,  1.71it/s]\n 75%|███████▌  | 18/24 [00:10<00:03,  1.71it/s]\n 79%|███████▉  | 19/24 [00:10<00:02,  1.71it/s]\n 83%|████████▎ | 20/24 [00:11<00:02,  1.71it/s]\n 88%|████████▊ | 21/24 [00:12<00:01,  1.70it/s]\n 92%|█████████▏| 22/24 [00:12<00:01,  1.70it/s]\n 96%|█████████▌| 23/24 [00:13<00:00,  1.70it/s]\n100%|██████████| 24/24 [00:13<00:00,  1.70it/s]\n100%|██████████| 24/24 [00:13<00:00,  1.72it/s]\nINFO:predict:Saving generated image to /tmp/output.png",
  "metrics": {
    "predict_time": 16.079534358,
    "total_time": 1494.226366
  },
  "output": "https://replicate.delivery/yhqm/D6dN7XE6rKqHLNxn5Azc7GO9LBfapEQ1F8tBr90Mmce1IM4TA/output.png",
  "started_at": "2024-12-06T14:54:29.888832Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/qoxq-xtthgnfv6s56o2lqrplkrcyeegzoxxnh6wrlxcdizqgb6dwaotwa",
    "get": "https://api.replicate.com/v1/predictions/5mssvvm5zsrj60ckkhg88a549c",
    "cancel": "https://api.replicate.com/v1/predictions/5mssvvm5zsrj60ckkhg88a549c/cancel"
  },
  "version": "d350d0ac395a41a62c4942e28e1ca1e7fbf6c23543bec06599795097b49ae812"
}

Generated in

16.1 seconds

Tweak it Iterate in playground ShareReport View full prediction

This output was created using a different version of the model, impetusdesign/rqi-txc-itp:d350d0ac.

Examples

View more examples

Run time and cost

This model costs approximately $0.018 to run on Replicate, or 55 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 A100 (80GB) GPU hardware. Predictions typically complete within 13 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.

black-forest-labs/flux-1.1-pro

Generate images from text prompts, with optional composition guidance from a reference image via Flux Redux. Achieve faster generation with improved prompt adherence and diversity compared to prior releases. Accepts a text prompt (required) and an optional image prompt; outputs images. Control aspect ratio, resolution, output format, seed for reproducibility, safety tolerance, and enable prompt upsampling for more creative results.

63.5m runs

Official

black-forest-labs/flux-pro

Generate images from text prompts, with optional image conditioning to guide composition. Accepts a text prompt and an optional reference image (Flux Redux image conditioning that steers layout toward the reference) and outputs a single image. Control prompt adherence vs creativity via guidance, enable prompt upsampling for more varied results, set a seed for reproducibility, and adjust safety tolerance. Supports multiple aspect ratios and resolutions up to 1440px.

13.5m runs

Official

black-forest-labs/flux-1.1-pro-ultra

Generate images from text prompts, with optional reference image guidance to steer composition. Enable ultra mode for up to 4‑megapixel outputs with fast ~10‑second generation and strong prompt adherence, or use raw mode for a more natural, less processed aesthetic. Control blend strength between text and reference image, set aspect ratio and seed for reproducibility, and adjust safety tolerance. Outputs a single image per run.

18.7m runs

Official

luma/photon

Generate images from text prompts. Optionally guide outputs with image, style, and character reference images using adjustable weights, enabling style transfer and consistent character generation from a single reference. Choose aspect ratios (1:1, 3:4, 4:3, 9:16, 16:9, 9:21, 21:9) and set a seed for reproducible results. Leverage strong natural language understanding for high prompt adherence and multi-turn iterative workflows.

3.0m runs

Official

black-forest-labs/flux-1.1-pro-ultra-finetuned

Generate images from a text prompt using your own custom fine-tune. Provide a finetune_id for a previously trained model, optionally adjust finetune_strength to control style influence, and add a reference image (image_prompt) to steer composition alongside the text. Enable raw mode to produce less processed, more natural-looking results. Supports up to 4MP resolution, fast generation, multiple aspect ratios, and adjustable safety_tolerance.

102.2k runs

Official

stability-ai/sdxl

Generate images from text prompts. Transform existing images toward a prompt (image-to-image) and inpaint masked regions using a black–white mask. Accepts a text prompt with optional input image and mask; outputs one or more images up to 1024×1024. Use an optional refiner (expert ensemble or base image refiner) to add fine detail by handing off late denoising steps and controlling the handover point. Load LoRA weights and fine-tune via the built-in training workflow to create custom styles, characters, or products.

82.5m runs

black-forest-labs/flux-pro-finetuned

Generate images from text prompts using your custom FLUX.1 [pro] fine-tune. Provide a finetune_id from a previously trained Flux Pro fine-tune and adjust finetune_strength (0–2) to control how strongly the fine-tune influences the result. Optionally add an image_prompt (Flux Redux) to guide composition and layout from a reference image for image-to-image steering. Configure aspect ratio, seed, safety tolerance, and prompt upsampling; outputs an image.

10.5k runs

Official

openai/gpt-image-1-mini

Generate images from text prompts and optional reference images. Accept both text and image inputs and return images; use input fidelity to control how closely outputs match reference style and facial features. Configure aspect ratio (1:1, 3:2, 2:3), background transparency (transparent or opaque), quality presets, batch size, and compression. Provides a cost-efficient variant of GPT Image 1 for prompt-based and reference-guided image generation.

33.8k runs

Official

Input

Output

Examples

Run time and cost

Readme

Related models

black-forest-labs/flux-1.1-pro

black-forest-labs/flux-pro

black-forest-labs/flux-1.1-pro-ultra

luma/photon

black-forest-labs/flux-1.1-pro-ultra-finetuned

stability-ai/sdxl

black-forest-labs/flux-pro-finetuned

openai/gpt-image-1-mini