pandas9/flux-dev-stoiqo | Run with an API on Replicate

pandas9

flux-dev-stoiqo

Cold

FLUX.1 Dev with STOIQO NewReality

Public

1.9K runs

A100 (80GB)

Run with an API

Pricing

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

boring low quality snapchat photo circa 2015, Selfie photo of cute woman with soft light brown hair in a car, The light from the setting sun gives a soft orange glow across her face and upper body, casting long shadowsboring low quality snapchat photo circa 2015, Selfie photo of cute woman with soft light brown hair in a car, The light from the setting sun gives a soft orange glow across her face and upper body, casting long shadows

Default: ""

aspect_ratio

string

Aspect ratio for the generated image

Default: "1:1"

guidance_scale

number

(minimum: 0.1, maximum: 10)

Guidance for the generated image

Default: 2.5

num_inference_steps

number

(minimum: 1, maximum: 50)

Number of inference steps

Default: 28

lora_scale

number

(minimum: -1, maximum: 1)

Initial LoRA scale

Default: 0.5

model

string

Model to use

Default: "STOIQONewrealityFLUXSD_F1DAlpha"

add_lora

boolean

Add LoRA to the model

Default: false

output_format

string

Format of the output images

Default: "webp"

output_quality

integer

(minimum: 0, maximum: 100)

Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.

Default: 95

seed

integer

Set a seed for reproducibility. Random by default.

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

npx create-replicate --model=pandas9/flux-dev-stoiqo

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 pandas9/flux-dev-stoiqo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "pandas9/flux-dev-stoiqo:3257403bcf96c3eabf64626d54fab3d81f8aeace2ea0c28849e46a77eaac87e6",
  {
    input: {
      model: "STOIQONewrealityFLUXSD_F1DAlpha",
      prompt: "boring low quality snapchat photo circa 2015, Selfie photo of cute woman with soft light brown hair in a car, The light from the setting sun gives a soft orange glow across her face and upper body, casting long shadows",
      add_lora: false,
      lora_scale: 0.5,
      aspect_ratio: "1:1",
      output_format: "webp",
      guidance_scale: 2.5,
      output_quality: 95,
      num_inference_steps: 28
    }
  }
);

// 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 pandas9/flux-dev-stoiqo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "pandas9/flux-dev-stoiqo:3257403bcf96c3eabf64626d54fab3d81f8aeace2ea0c28849e46a77eaac87e6",
    input={
        "model": "STOIQONewrealityFLUXSD_F1DAlpha",
        "prompt": "boring low quality snapchat photo circa 2015, Selfie photo of cute woman with soft light brown hair in a car, The light from the setting sun gives a soft orange glow across her face and upper body, casting long shadows",
        "add_lora": False,
        "lora_scale": 0.5,
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "guidance_scale": 2.5,
        "output_quality": 95,
        "num_inference_steps": 28
    }
)

# 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 pandas9/flux-dev-stoiqo 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": "pandas9/flux-dev-stoiqo:3257403bcf96c3eabf64626d54fab3d81f8aeace2ea0c28849e46a77eaac87e6",
    "input": {
      "model": "STOIQONewrealityFLUXSD_F1DAlpha",
      "prompt": "boring low quality snapchat photo circa 2015, Selfie photo of cute woman with soft light brown hair in a car, The light from the setting sun gives a soft orange glow across her face and upper body, casting long shadows",
      "add_lora": false,
      "lora_scale": 0.5,
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "guidance_scale": 2.5,
      "output_quality": 95,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2024-10-15T08:03:24.828916Z",
  "created_at": "2024-10-15T08:03:06.422000Z",
  "data_removed": false,
  "error": null,
  "id": "10pcdzy06srj60cjhwssnfr22c",
  "input": {
    "model": "STOIQONewrealityFLUXSD_F1DAlpha",
    "prompt": "boring low quality snapchat photo circa 2015, Selfie photo of cute woman with soft light brown hair in a car, The light from the setting sun gives a soft orange glow across her face and upper body, casting long shadows",
    "add_lora": false,
    "lora_scale": 0.5,
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "guidance_scale": 2.5,
    "output_quality": 95,
    "num_inference_steps": 28
  },
  "logs": "Random seed set to: 2016542662\n====================================\nModel: STOIQONewrealityFLUXSD_F1DAlpha.safetensors\n====================================\nChecking inputs\n====================================\nChecking weights\n✅ ae.safetensors exists in ComfyUI/models/vae\n✅ clip_l.safetensors exists in ComfyUI/models/clip\n✅ t5xxl_fp16.safetensors exists in ComfyUI/models/clip\n====================================\nRunning workflow\n[ComfyUI] got prompt\nExecuting node 751, title: 💊 CR LoRA Stack, class type: CR LoRA Stack\nExecuting node 738, title: Load Diffusion Model, class type: UNETLoader\n[ComfyUI] model weight dtype torch.float8_e4m3fn, manual cast: torch.bfloat16\n[ComfyUI] model_type FLUX\nExecuting node 752, title: 💊 CR Apply LoRA Stack, class type: CR Apply LoRA Stack\nExecuting node 742, title: BasicScheduler, class type: BasicScheduler\nExecuting node 723, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode\n[ComfyUI] Requested to load FluxClipModel_\n[ComfyUI] Loading 1 new model\nExecuting node 731, title: FluxGuidance, class type: FluxGuidance\nExecuting node 743, title: BasicGuider, class type: BasicGuider\nExecuting node 744, title: RandomNoise, class type: RandomNoise\nExecuting node 740, title: SamplerCustomAdvanced, class type: SamplerCustomAdvanced\n[ComfyUI] Requested to load Flux\n[ComfyUI] Loading 1 new model\n[ComfyUI] loaded completely 0.0 11350.048889160156 True\n[ComfyUI]\n[ComfyUI] 0%|          | 0/28 [00:00<?, ?it/s]\n[ComfyUI] 4%|▎         | 1/28 [00:00<00:08,  3.31it/s]\n[ComfyUI] 7%|▋         | 2/28 [00:00<00:10,  2.46it/s]\n[ComfyUI] 11%|█         | 3/28 [00:01<00:10,  2.27it/s]\n[ComfyUI] 14%|█▍        | 4/28 [00:01<00:10,  2.20it/s]\n[ComfyUI] 18%|█▊        | 5/28 [00:02<00:10,  2.15it/s]\n[ComfyUI] 21%|██▏       | 6/28 [00:02<00:10,  2.13it/s]\n[ComfyUI] 25%|██▌       | 7/28 [00:03<00:09,  2.11it/s]\n[ComfyUI] 29%|██▊       | 8/28 [00:03<00:09,  2.10it/s]\n[ComfyUI] 32%|███▏      | 9/28 [00:04<00:09,  2.10it/s]\n[ComfyUI] 36%|███▌      | 10/28 [00:04<00:08,  2.09it/s]\n[ComfyUI] 39%|███▉      | 11/28 [00:05<00:08,  2.09it/s]\n[ComfyUI] 43%|████▎     | 12/28 [00:05<00:07,  2.08it/s]\n[ComfyUI] 46%|████▋     | 13/28 [00:06<00:07,  2.08it/s]\n[ComfyUI] 50%|█████     | 14/28 [00:06<00:06,  2.08it/s]\n[ComfyUI] 54%|█████▎    | 15/28 [00:07<00:06,  2.08it/s]\n[ComfyUI] 57%|█████▋    | 16/28 [00:07<00:05,  2.08it/s]\n[ComfyUI] 61%|██████    | 17/28 [00:07<00:05,  2.08it/s]\n[ComfyUI] 64%|██████▍   | 18/28 [00:08<00:04,  2.08it/s]\n[ComfyUI] 68%|██████▊   | 19/28 [00:08<00:04,  2.08it/s]\n[ComfyUI] 71%|███████▏  | 20/28 [00:09<00:03,  2.08it/s]\n[ComfyUI] 75%|███████▌  | 21/28 [00:09<00:03,  2.08it/s]\n[ComfyUI] 79%|███████▊  | 22/28 [00:10<00:02,  2.08it/s]\n[ComfyUI] 82%|████████▏ | 23/28 [00:10<00:02,  2.03it/s]\n[ComfyUI] 86%|████████▌ | 24/28 [00:11<00:01,  2.04it/s]\n[ComfyUI] 89%|████████▉ | 25/28 [00:11<00:01,  2.05it/s]\n[ComfyUI] 93%|█████████▎| 26/28 [00:12<00:00,  2.06it/s]\n[ComfyUI] 96%|█████████▋| 27/28 [00:12<00:00,  2.06it/s]\n[ComfyUI] 100%|██████████| 28/28 [00:13<00:00,  2.06it/s]\n[ComfyUI] 100%|██████████| 28/28 [00:13<00:00,  2.10it/s]\nExecuting node 702, title: VAE Decode, class type: VAEDecode\nExecuting node 719, title: Save Image, class type: SaveImage\n[ComfyUI] Prompt executed in 18.01 seconds\noutputs:  {'719': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nComfyUI_00001_.png",
  "metrics": {
    "predict_time": 18.397981601,
    "total_time": 18.406916
  },
  "output": [
    "https://replicate.delivery/yhqm/UeCCrXfrJdu93Eskw1CIa3K4gpDd9ks9CojOFLcLoR2MP9mTA/ComfyUI_00001_.webp"
  ],
  "started_at": "2024-10-15T08:03:06.430934Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/10pcdzy06srj60cjhwssnfr22c",
    "cancel": "https://api.replicate.com/v1/predictions/10pcdzy06srj60cjhwssnfr22c/cancel"
  },
  "version": "3257403bcf96c3eabf64626d54fab3d81f8aeace2ea0c28849e46a77eaac87e6"
}

Generated in

18.4 seconds

Tweak it Iterate in playground Share Report View full prediction

Random seed set to: 2016542662
====================================
Model: STOIQONewrealityFLUXSD_F1DAlpha.safetensors
====================================
Checking inputs
====================================
Checking weights
✅ ae.safetensors exists in ComfyUI/models/vae
✅ clip_l.safetensors exists in ComfyUI/models/clip
✅ t5xxl_fp16.safetensors exists in ComfyUI/models/clip
====================================
Running workflow
[ComfyUI] got prompt
Executing node 751, title: 💊 CR LoRA Stack, class type: CR LoRA Stack
Executing node 738, title: Load Diffusion Model, class type: UNETLoader
[ComfyUI] model weight dtype torch.float8_e4m3fn, manual cast: torch.bfloat16
[ComfyUI] model_type FLUX
Executing node 752, title: 💊 CR Apply LoRA Stack, class type: CR Apply LoRA Stack
Executing node 742, title: BasicScheduler, class type: BasicScheduler
Executing node 723, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode
[ComfyUI] Requested to load FluxClipModel_
[ComfyUI] Loading 1 new model
Executing node 731, title: FluxGuidance, class type: FluxGuidance
Executing node 743, title: BasicGuider, class type: BasicGuider
Executing node 744, title: RandomNoise, class type: RandomNoise
Executing node 740, title: SamplerCustomAdvanced, class type: SamplerCustomAdvanced
[ComfyUI] Requested to load Flux
[ComfyUI] Loading 1 new model
[ComfyUI] loaded completely 0.0 11350.048889160156 True
[ComfyUI]
[ComfyUI] 0%|          | 0/28 [00:00<?, ?it/s]
[ComfyUI] 4%|▎         | 1/28 [00:00<00:08,  3.31it/s]
[ComfyUI] 7%|▋         | 2/28 [00:00<00:10,  2.46it/s]
[ComfyUI] 11%|█         | 3/28 [00:01<00:10,  2.27it/s]
[ComfyUI] 14%|█▍        | 4/28 [00:01<00:10,  2.20it/s]
[ComfyUI] 18%|█▊        | 5/28 [00:02<00:10,  2.15it/s]
[ComfyUI] 21%|██▏       | 6/28 [00:02<00:10,  2.13it/s]
[ComfyUI] 25%|██▌       | 7/28 [00:03<00:09,  2.11it/s]
[ComfyUI] 29%|██▊       | 8/28 [00:03<00:09,  2.10it/s]
[ComfyUI] 32%|███▏      | 9/28 [00:04<00:09,  2.10it/s]
[ComfyUI] 36%|███▌      | 10/28 [00:04<00:08,  2.09it/s]
[ComfyUI] 39%|███▉      | 11/28 [00:05<00:08,  2.09it/s]
[ComfyUI] 43%|████▎     | 12/28 [00:05<00:07,  2.08it/s]
[ComfyUI] 46%|████▋     | 13/28 [00:06<00:07,  2.08it/s]
[ComfyUI] 50%|█████     | 14/28 [00:06<00:06,  2.08it/s]
[ComfyUI] 54%|█████▎    | 15/28 [00:07<00:06,  2.08it/s]
[ComfyUI] 57%|█████▋    | 16/28 [00:07<00:05,  2.08it/s]
[ComfyUI] 61%|██████    | 17/28 [00:07<00:05,  2.08it/s]
[ComfyUI] 64%|██████▍   | 18/28 [00:08<00:04,  2.08it/s]
[ComfyUI] 68%|██████▊   | 19/28 [00:08<00:04,  2.08it/s]
[ComfyUI] 71%|███████▏  | 20/28 [00:09<00:03,  2.08it/s]
[ComfyUI] 75%|███████▌  | 21/28 [00:09<00:03,  2.08it/s]
[ComfyUI] 79%|███████▊  | 22/28 [00:10<00:02,  2.08it/s]
[ComfyUI] 82%|████████▏ | 23/28 [00:10<00:02,  2.03it/s]
[ComfyUI] 86%|████████▌ | 24/28 [00:11<00:01,  2.04it/s]
[ComfyUI] 89%|████████▉ | 25/28 [00:11<00:01,  2.05it/s]
[ComfyUI] 93%|█████████▎| 26/28 [00:12<00:00,  2.06it/s]
[ComfyUI] 96%|█████████▋| 27/28 [00:12<00:00,  2.06it/s]
[ComfyUI] 100%|██████████| 28/28 [00:13<00:00,  2.06it/s]
[ComfyUI] 100%|██████████| 28/28 [00:13<00:00,  2.10it/s]
Executing node 702, title: VAE Decode, class type: VAEDecode
Executing node 719, title: Save Image, class type: SaveImage
[ComfyUI] Prompt executed in 18.01 seconds
outputs:  {'719': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
ComfyUI_00001_.png

Examples

View more examples

Run time and cost

This model costs approximately $0.037 to run on Replicate, or 27 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 27 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.