The model to use
Default: "CoolName-IL-v2"
The VAE to use
Default: "default"
The prompt, uses Compel weighting syntax
Default: "street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V"
The negative prompt (for things you don't want), uses Compel weighting syntax
Default: "nsfw, naked"
CFG scale defines how much attention the model pays to the prompt when generating, set to 1 to disable
Default: 7
Amount to rescale CFG generated noise to avoid overexposed images, set to 0 or 1 to disable
Default: 1
PAG scale is similar to CFG but improves the result; set to 0 to disable
Default: 0
How many CLIP layers to skip; 1 means no skip (comportamento alinhado ao A1111)
Default: 2
The width of the image
Default: 1280
The height of the image
Upscale factor
Default: "Original"
Prepend preprompt (Prompt: "masterpiece, best quality, absurdres, newest," | Negative prompt: "low quality, bad quality, watermark,")
Default: true
The scheduler to use
Default: "Euler a"
Number of steps when generating
Default: 30
Number of images to generate (1-4). Note: higher batch sizes in high resolution may exceed VRAM limits.
The seed for generation; set to -1 for random seed
Default: -1
Use ADetailer face_yolov9c.pt
Default: false
ADetailer face prompt (if blank, will use the image prompt)
ADetailer face negative prompt (if blank, will use: blurry, deformed face, extra features, unrealistic skin texture, oversmoothed, low resolution, artifacts)
Use ADetailer hand_yolov9c.pt
ADetailer hand prompt (if blank, will use: detailed hands, realistic anatomy, well-defined fingers, natural pose, soft shadows, high resolution, intricate details)
ADetailer hand negative prompt (if blank, will use: extra fingers, fused or missing fingers, blurry, distorted, low detail, poorly drawn, unnatural proportions)
Use ADetailer person_yolov8m-seg.pt
ADetailer person prompt (if blank, will use: best quality, detailed, realistic shadows)
ADetailer person negative prompt (if blank, will use: deformed, unrealistic proportions, extra limbs, blurred, low quality, distorted pose, exaggerated features)
Run this model in Node.js with one line of code:
npm install replicate
REPLICATE_API_TOKEN
export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run aisha-ai-official/coolname-il-v2 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "aisha-ai-official/coolname-il-v2:6c3f448205e5892578a551f711e56e6ed1998f5fea263306aaf52d3b09f707fd", { input: { vae: "default", seed: -1, model: "CoolName-IL-v2", steps: 30, width: 1280, height: 1280, prompt: "street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V", upscale: "Original", cfg_scale: 7, clip_skip: 2, pag_scale: 0, scheduler: "Euler a", batch_size: 1, adetailer_face: false, adetailer_hand: false, negative_prompt: "nsfw, naked", adetailer_person: false, guidance_rescale: 1, prepend_preprompt: 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
import replicate
output = replicate.run( "aisha-ai-official/coolname-il-v2:6c3f448205e5892578a551f711e56e6ed1998f5fea263306aaf52d3b09f707fd", input={ "vae": "default", "seed": -1, "model": "CoolName-IL-v2", "steps": 30, "width": 1280, "height": 1280, "prompt": "street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V", "upscale": "Original", "cfg_scale": 7, "clip_skip": 2, "pag_scale": 0, "scheduler": "Euler a", "batch_size": 1, "adetailer_face": False, "adetailer_hand": False, "negative_prompt": "nsfw, naked", "adetailer_person": False, "guidance_rescale": 1, "prepend_preprompt": True } ) print(output)
To learn more, take a look at the guide on getting started with Python.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "aisha-ai-official/coolname-il-v2:6c3f448205e5892578a551f711e56e6ed1998f5fea263306aaf52d3b09f707fd", "input": { "vae": "default", "seed": -1, "model": "CoolName-IL-v2", "steps": 30, "width": 1280, "height": 1280, "prompt": "street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V", "upscale": "Original", "cfg_scale": 7, "clip_skip": 2, "pag_scale": 0, "scheduler": "Euler a", "batch_size": 1, "adetailer_face": false, "adetailer_hand": false, "negative_prompt": "nsfw, naked", "adetailer_person": false, "guidance_rescale": 1, "prepend_preprompt": true } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
{ "completed_at": "2025-03-08T07:44:53.169528Z", "created_at": "2025-03-08T07:44:45.132000Z", "data_removed": false, "error": null, "id": "ccx3kanj9hrme0cnejvaryz7h8", "input": { "vae": "default", "seed": -1, "model": "CoolName-IL-v2", "steps": 30, "width": 1280, "height": 1280, "prompt": "street, 1girl, dark-purple short hair, purple eyes, medium breasts, cleavage, casual clothes, smile, V", "upscale": "Original", "cfg_scale": 7, "clip_skip": 2, "pag_scale": 0, "scheduler": "Euler a", "batch_size": 1, "adetailer_face": false, "adetailer_hand": false, "negative_prompt": "nsfw, naked", "adetailer_person": false, "guidance_rescale": 1, "prepend_preprompt": true }, "logs": "Using text to image mode.\nUsing seed: 1482574017\n 0%| | 0/30 [00:00<?, ?it/s]\n 7%|▋ | 2/30 [00:00<00:03, 7.93it/s]\n 10%|█ | 3/30 [00:00<00:03, 6.84it/s]\n 13%|█▎ | 4/30 [00:00<00:04, 6.39it/s]\n 17%|█▋ | 5/30 [00:00<00:04, 6.15it/s]\n 20%|██ | 6/30 [00:00<00:03, 6.02it/s]\n 23%|██▎ | 7/30 [00:01<00:03, 5.93it/s]\n 27%|██▋ | 8/30 [00:01<00:03, 5.87it/s]\n 30%|███ | 9/30 [00:01<00:03, 5.83it/s]\n 33%|███▎ | 10/30 [00:01<00:03, 5.79it/s]\n 37%|███▋ | 11/30 [00:01<00:03, 5.77it/s]\n 40%|████ | 12/30 [00:01<00:03, 5.75it/s]\n 43%|████▎ | 13/30 [00:02<00:02, 5.71it/s]\n 47%|████▋ | 14/30 [00:02<00:02, 5.72it/s]\n 50%|█████ | 15/30 [00:02<00:02, 5.72it/s]\n 53%|█████▎ | 16/30 [00:02<00:02, 5.72it/s]\n 57%|█████▋ | 17/30 [00:02<00:02, 5.71it/s]\n 60%|██████ | 18/30 [00:03<00:02, 5.72it/s]\n 63%|██████▎ | 19/30 [00:03<00:01, 5.71it/s]\n 67%|██████▋ | 20/30 [00:03<00:01, 5.69it/s]\n 70%|███████ | 21/30 [00:03<00:01, 5.69it/s]\n 73%|███████▎ | 22/30 [00:03<00:01, 5.68it/s]\n 77%|███████▋ | 23/30 [00:03<00:01, 5.68it/s]\n 80%|████████ | 24/30 [00:04<00:01, 5.68it/s]\n 83%|████████▎ | 25/30 [00:04<00:00, 5.68it/s]\n 87%|████████▋ | 26/30 [00:04<00:00, 5.67it/s]\n 90%|█████████ | 27/30 [00:04<00:00, 5.66it/s]\n 93%|█████████▎| 28/30 [00:04<00:00, 5.67it/s]\n 97%|█████████▋| 29/30 [00:04<00:00, 5.65it/s]\n100%|██████████| 30/30 [00:05<00:00, 5.63it/s]\n100%|██████████| 30/30 [00:05<00:00, 5.80it/s]", "metrics": { "predict_time": 8.031910731, "total_time": 8.037528 }, "output": [ "https://replicate.delivery/xezq/1dJdTkp6nNKaAxYsnXFFuO11XZFTeHAMejmPBils8SB1daWUA/0.png" ], "started_at": "2025-03-08T07:44:45.137617Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/bcwr-6lurb4mwwtxeg6ucubyh65ktnl7flis34pu2ze4bc4x5cu7j7rsq", "get": "https://api.replicate.com/v1/predictions/ccx3kanj9hrme0cnejvaryz7h8", "cancel": "https://api.replicate.com/v1/predictions/ccx3kanj9hrme0cnejvaryz7h8/cancel" }, "version": "6c3f448205e5892578a551f711e56e6ed1998f5fea263306aaf52d3b09f707fd" }
Using text to image mode. Using seed: 1482574017 0%| | 0/30 [00:00<?, ?it/s] 7%|▋ | 2/30 [00:00<00:03, 7.93it/s] 10%|█ | 3/30 [00:00<00:03, 6.84it/s] 13%|█▎ | 4/30 [00:00<00:04, 6.39it/s] 17%|█▋ | 5/30 [00:00<00:04, 6.15it/s] 20%|██ | 6/30 [00:00<00:03, 6.02it/s] 23%|██▎ | 7/30 [00:01<00:03, 5.93it/s] 27%|██▋ | 8/30 [00:01<00:03, 5.87it/s] 30%|███ | 9/30 [00:01<00:03, 5.83it/s] 33%|███▎ | 10/30 [00:01<00:03, 5.79it/s] 37%|███▋ | 11/30 [00:01<00:03, 5.77it/s] 40%|████ | 12/30 [00:01<00:03, 5.75it/s] 43%|████▎ | 13/30 [00:02<00:02, 5.71it/s] 47%|████▋ | 14/30 [00:02<00:02, 5.72it/s] 50%|█████ | 15/30 [00:02<00:02, 5.72it/s] 53%|█████▎ | 16/30 [00:02<00:02, 5.72it/s] 57%|█████▋ | 17/30 [00:02<00:02, 5.71it/s] 60%|██████ | 18/30 [00:03<00:02, 5.72it/s] 63%|██████▎ | 19/30 [00:03<00:01, 5.71it/s] 67%|██████▋ | 20/30 [00:03<00:01, 5.69it/s] 70%|███████ | 21/30 [00:03<00:01, 5.69it/s] 73%|███████▎ | 22/30 [00:03<00:01, 5.68it/s] 77%|███████▋ | 23/30 [00:03<00:01, 5.68it/s] 80%|████████ | 24/30 [00:04<00:01, 5.68it/s] 83%|████████▎ | 25/30 [00:04<00:00, 5.68it/s] 87%|████████▋ | 26/30 [00:04<00:00, 5.67it/s] 90%|█████████ | 27/30 [00:04<00:00, 5.66it/s] 93%|█████████▎| 28/30 [00:04<00:00, 5.67it/s] 97%|█████████▋| 29/30 [00:04<00:00, 5.65it/s] 100%|██████████| 30/30 [00:05<00:00, 5.63it/s] 100%|██████████| 30/30 [00:05<00:00, 5.80it/s]
View more examples
This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.
This model doesn't have a readme.
A good anime merge from 12 other models
Great text-to-image model by Cagliostro Lab
Realistic text-to-image by TiwazM
This model is cold. 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.