BRIA 2.4: Text-to-Image Model for Commercial Licensing
Bria AI 2.4 is an alternative text-to-image model for specific commercial applications. It exclusively uses T5 for text embedding, enabling support for text prompts of unlimited length. This model matches 2.3's photorealism, with a 4% decrease in prompt alignment and 7% decrease in aesthetics. Like all Bria models, 2.4 upholds ethical standards, excludes copyrighted and harmful content, and comes with full legal liability coverage. While 2.4 is preferable when T5 embedding or support for longer prompts is specifically required, our recommended model for most use cases remains Bria 2.3, especially given its compatibility with Bria's ControlNets and Adapters.
For more information, please visit our website.
What's New
Bria AI 2.4 supports text prompts of unlimited length. Additionally, unlike BRIA 2.3, it exclusively uses T5 for text embedding, eliminating biases associated with CLIP.
Get Access
Interested in BRIA 2.4? Purchase is required to license and access BRIA 2.4, ensuring royalty management with our data partners and full liability coverage for commercial use.
Are you a startup or a student? We encourage you to apply for our Startup Program to request access. This program are designed to support emerging businesses and academic pursuits with our cutting-edge technology.
Contact us today to unlock the potential of BRIA 2.4! By submitting the form above, you agree to BRIA’s Privacy policy and Terms & conditions.
Key Features
Legally Compliant: Offers full legal liability coverage for copyright and privacy infringements. Thanks to training on 100% licensed data from leading data partners, we ensure the ethical use of content.
Patented Attribution Engine: Our attribution engine is our way to compensate our data partners, powered by our proprietary and patented algorithms.
Enterprise-Ready: Specifically designed for business applications, Bria AI 2.4 delivers high-quality, compliant imagery for a variety of commercial needs.
Customizable Technology: Provides access to source code and weights for extensive customization, catering to specific business requirements.
Model Description
Developed by: BRIA AI
Model type: Latent diffusion text-to-image model
Purchase is required to license and access the model.
Model Description: BRIA 2.4 is a text-to-image model trained exclusively on a professional-grade, licensed dataset. It is designed for commercial use and includes full legal liability coverage.
Resources for more information: BRIA AI
Code example using Diffusers
pip install diffusers, torch, huggingface_hub
from diffusers import DiffusionPipeline
from huggingface_hub import snapshot_download
import torch
import os, sys
pipeline_path = snapshot_download(repo_id='briaai/BRIA-2.4')
sys.path.append(pipeline_path)
from ella_xl_pipeline import EllaXLPipeline
pipe = DiffusionPipeline.from_pretrained("briaai/BRIA-2.3", torch_dtype=torch.float16, use_safetensors=True)
pipe.load_lora_weights(f'{pipeline_path}/pytorch_lora_weights.safetensors')
pipe.fuse_lora()
pipe.unload_lora_weights()
pipe.to("cuda")
pipe = EllaXLPipeline(pipe,f'{pipeline_path}/pytorch_model.bin')
prompt = "A portrait of a Beautiful and playful ethereal singer, golden designs, highly detailed, blurry background"
negative_prompt = "Logo,Watermark,Text,Ugly,Morbid,Extra fingers,Poorly drawn hands,Mutation,Blurry,Extra limbs,Gross proportions,Missing arms,Mutated hands,Long neck,Duplicate,Mutilated,Mutilated hands,Poorly drawn face,Deformed,Bad anatomy,Cloned face,Malformed limbs,Missing legs,Too many fingers"
images = pipe(prompt=prompt, negative_prompt=negative_prompt, height=1024, width=1024).images[0]
Some tips for using our text-to-image model at inference:
- You must set
pipe.force_zeros_for_empty_prompt = False - Using negative prompt is recommended.
- We support multiple aspect ratios, yet resolution should overall consists approximately
1024*1024=1Mpixels, for example:(1024,1024), (1280, 768), (1344, 768), (832, 1216), (1152, 832), (1216, 832), (960,1088) - If you need speed - try the BRIA 2.3 Fast which achieve 75% reduced inference time
- For 2.4, use 30-50 steps (higher is better)
- For 2.4, use
guidance_scaleof 5.0 or 7.5
- Downloads last month
- 72