Krea 2 Raw: A Text-to-Image Model Checkpoint for Fine-Tuning on Hugging Face
Summary
This is a Hugging Face repository page for the Krea 2 Raw text-to-image model checkpoint. The model is not intended for direct inference but serves as a base for fine-tuning and post-training, such as training LoRAs that can then be used with the Krea 2 Turbo model. The page provides basic setup instructions for running inference using the official codebase and links to a collection of in-house trained LoRAs.
Source
Twitter / XKrea 2 Raw: A Text-to-Image Model Checkpoint for Fine-Tuning on Hugging Facehuggingface.coKey quotes
· 4 pulledThis is the Krea 2 Raw checkpoint, its not recommended for inference use.
Its a good base for finetuning or post-training for your own needs and domains.
For example, one use-case is to train LoRAs on midtrain and directly use them on Krea 2 Turbo.
We're on a journey to advance and democratize artificial intelligence through open source and open science.
You might also wanna read
Krea 2 (K2): Technical Report on Open-Weights Text-to-Image Foundation Models
This is a technical report introducing Krea 2 (K2), an open-weights text-to-image foundation model for creative exploration. The report disc
krea.ai·1d ago
Krea releases open-weight AI image models Krea 2 Raw and Turbo with custom license requiring content moderation
Krea, an AI creative tools startup, has released two versions of its new AI image generation model — Krea 2 Raw and Krea 2 Turbo — as open w
venturebeat.com·18h agoKrea releases open-weight AI image models Krea 2 Raw and Turbo with custom license requiring content moderation
Krea, an AI creative tools startup, has released two versions of its new AI image generation model — Krea 2 Raw and Krea 2 Turbo — as open w
venturebeat.com·18h ago
Research Study: Effectiveness of Adaptive Merging for Recycling LoRA Modules from Public Repositories
This research paper examines the effectiveness of adaptive merging methods for recycling LoRA (Low-Rank Adaptation) modules from public repo
arxiv.org·3mo ago
Converting FP8 Quantized CLIP Checkpoints to TensorRT Engines for Production Inference
This article provides a technical walkthrough for converting FP8-quantized checkpoints (specifically a CLIP model) into NVIDIA TensorRT engi
developer.nvidia.com·7d ago
Krea Releases Open Weights for FLUX.1 to Address AI Image Generation Challenges
Krea announces the open release of FLUX.1 Krea, addressing the unique 'AI look' in image generation, such as overly-blurry backgrounds and w
krea.ai·10mo ago
Krea: AI-powered image and video generation tool for designers
Krea is an AI-powered design tool for generating and editing images and videos, featuring fast generation, upscaling, realtime creation, and
Product Hunt·1mo agoComments
Sign in to join the conversation.
No comments yet. Be the first.