--- license: creativeml-openrail-m tags: - imagepipeline - imagepipeline.io - text-to-image - ultra-realistic pinned: false pipeline_tag: text-to-image --- ## 19936-BUKAKAKE-LORA Generated on Image Pipeline **This lora model is uploaded on [imagepipeline.io](https://imagepipeline.io/)** Model details - - "It is rather prone to getting cum on hair, and has a slight bias against facials/cum on faces, so make sure to tune for that in your prompt so it gets proper coverage. It is able to generate excessive cum from a minimal 'bukkake, cum' tag alongside it. A strength of 0.75 is good. -If your model still has a problem with handjobs, penises, etc. and the like, it'll only really make it work marginally better. Given that most models fuck up hands, penises, and other particulates regardless, expect only a marginal improvement. -All v1.0 pics were made with my custom blends. All of these blends have an AOM3 base, so this LoRA should work for you as well if you use AOM3 or a similar model." [![Try this model](https://img.shields.io/badge/try_this_model-image_pipeline-BD9319)](https://imagepipeline.io/models/19936-BUKAKAKE-LORA?id=ed1fa2f8-ec2d-4794-9182-d2242fb538d8/) ## How to try this model ? You can try using it locally or send an API call to test the output quality. Get your `API_KEY` from [imagepipeline.io](https://imagepipeline.io/). No payment required. Coding in `php` `javascript` `node` etc ? Checkout our documentation [![documentation](https://img.shields.io/badge/documentation-image_pipeline-blue)](https://docs.imagepipeline.io/docs/introduction) ```python import requests import json url = "https://imagepipeline.io/sd/text2image/v1/run" payload = json.dumps({ "model_id": "sd1.5", "prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K", "negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime", "width": "512", "height": "512", "samples": "1", "num_inference_steps": "30", "safety_checker": false, "guidance_scale": 7.5, "multi_lingual": "no", "embeddings": "", "lora_models": "ed1fa2f8-ec2d-4794-9182-d2242fb538d8", "lora_weights": "0.5" }) headers = { 'Content-Type': 'application/json', 'API-Key': 'your_api_key' } response = requests.request("POST", url, headers=headers, data=payload) print(response.text) } ``` Get more ready to use `MODELS` like this for `SD 1.5` and `SDXL` : [![All models](https://img.shields.io/badge/Get%20All%20Models-image_pipeline-BD9319)](https://imagepipeline.io/models) ### API Reference #### Generate Image ```http https://api.imagepipeline.io/sd/text2image/v1 ``` | Headers | Type | Description | |:----------------------| :------- |:-------------------------------------------------------------------------------------------------------------------| | `API-Key` | `str` | Get your `API_KEY` from [imagepipeline.io](https://imagepipeline.io/) | | `Content-Type` | `str` | application/json - content type of the request body | | Parameter | Type | Description | | :-------- | :------- | :------------------------- | | `model_id` | `str` | Your base model, find available lists in [models page](https://imagepipeline.io/models) or upload your own| | `prompt` | `str` | Text Prompt. Check our [Prompt Guide](https://docs.imagepipeline.io/docs/SD-1.5/docs/extras/prompt-guide) for tips | | `num_inference_steps` | `int [1-50]` | Noise is removed with each step, resulting in a higher-quality image over time. Ideal value 30-50 (without LCM) | | `guidance_scale` | `float [1-20]` | Higher guidance scale prioritizes text prompt relevance but sacrifices image quality. Ideal value 7.5-12.5 | | `lora_models` | `str, array` | Pass the model_id(s) of LoRA models that can be found in models page | | `lora_weights` | `str, array` | Strength of the LoRA effect | --- license: creativeml-openrail-m tags: - imagepipeline - imagepipeline.io - text-to-image - ultra-realistic pinned: false pipeline_tag: text-to-image --- ### Feedback If you have any feedback, please reach out to us at hello@imagepipeline.io #### 🔗 Visit Website [![portfolio](https://img.shields.io/badge/image_pipeline-BD9319?style=for-the-badge&logo=gocd&logoColor=white)](https://imagepipeline.io/) If you are the original author of this model, please [click here](https://airtable.com/apprTaRnJbDJ8ufOx/shr4g7o9B6fWfOlUR) to add credits