Krea-2

Krea-2 is a ~12B single-stream diffusion-transformer text-to-image family. InvokeAI supports both published checkpoints:

• Krea-2-Turbo — distilled for fast, low-step generation. Runs at 8 steps with CFG disabled (CFG Scale 1.0). This is the recommended checkpoint for everyday use.
• Krea-2-Raw — the undistilled base checkpoint. Runs at more steps (~28) with CFG enabled (CFG Scale ~5.5, equivalent to the reference pipeline’s guidance 4.5) and supports negative prompts. It is primarily intended as a base for finetuning / LoRA training, but full inference is supported.

The variant is detected automatically on install, and selecting a Krea-2 model sets sensible defaults (steps, CFG, 1024×1024) for that variant.

Hardware

Krea-2 is a large model. See the System Requirements table for details. In short, on a 24 GB card enable FP8 in the model’s Default Settings to fit 1024² (with a LoRA). For lower VRAM, use a GGUF transformer (Q4_K ≈ 12 GB total).

Installing

The easiest path is the Krea-2 launchpad bundle in the Model Manager, which installs the models and their dependencies together.

Krea-2 needs three components:

Component	Diffusers install	GGUF / single-file install
Transformer	bundled in the pipeline	the .gguf / single-file checkpoint
VAE (Qwen-Image)	bundled	installed separately
Text encoder (Qwen3-VL)	bundled	installed separately

• Diffusers (e.g. krea/Krea-2-Turbo, krea/Krea-2-Raw): a single ~26 GB install that bundles the VAE and text encoder. Nothing else is required.
• GGUF / single-file: the checkpoint ships only the transformer. You must also install a standalone Qwen-Image VAE and a Qwen3-VL encoder (both included in the launchpad bundle).

When you select a GGUF/single-file Krea-2 model, InvokeAI auto-selects an installed VAE and Qwen3-VL encoder if you have them. If none are installed, you’ll be prompted to pick them (in the model dropdowns) before you can generate. Selecting a Diffusers Krea-2 model clears those standalone selections and uses the bundled components.

Qwen3-VL encoder download

Single-file Qwen3-VL encoders bundle only the weights. The tokenizer/config are fetched once from HuggingFace (Qwen/Qwen3-VL-4B-Instruct) on first use, then cached for offline use. A single-file fp8 encoder is kept resident in fp8 (roughly half the VRAM of the bf16 encoder).

Conditioning enhancers

Two optional, off-by-default toggles are available under Advanced Options (below CFG Scale). They transform the text conditioning and are especially useful for the distilled Turbo checkpoint:

• Conditioning Rebalance — per-layer weighting of the text embedding to improve prompt adherence.
• Seed Variance Enhancer — injects controlled noise into the conditioning to restore per-seed diversity (the distilled model otherwise produces near-identical images across seeds), trading some prompt adherence for variety.

Both are recorded in image metadata and can be recalled. When enabled on the canvas, the same enhancer chain is applied independently to the global prompt and each positive regional prompt before their conditionings are collected.

Multiple conditionings

In the workflow editor, the Denoise - Krea-2 node accepts one conditioning or a collection for both its positive and negative conditioning inputs. Multiple independently encoded conditionings are concatenated after padding tokens are removed.

The Text Encoder - Krea-2 node also accepts an optional mask. A masked conditioning applies to that image region; an unmasked conditioning applies to the background not covered by any regional mask. If regional masks cover the full image, an unmasked conditioning falls back to the full image instead of being ignored. Krea-2 uses restricted attention on alternating main transformer blocks, leaving the other blocks unrestricted to preserve image-wide coherence. Positive regional prompts are available on the canvas. In workflows, masked conditioning collections can also be supplied to the negative input when CFG is enabled. Canvas regional negative prompts, auto-negative, and regional reference images are not supported.

Regional prompting memory

Regional prompting builds a dense boolean attention mask whose memory grows quadratically with the combined text and image token count. Invoke reserves memory for retained masks, construction scratch space, and the dtype-sized additive attention bias created by SDPA. Fused memory-efficient attention support for dense masks still depends on the GPU, PyTorch build, dtype, and sequence shape. When no fused kernel is available, PyTorch falls back to math attention, which may use substantially more VRAM and can cause an out-of-memory error. Reducing image resolution or disabling regional prompting is the practical fallback. Automated CUDA coverage is skipped on unsupported hardware and cannot exercise every GPU/backend combination.

LoRA

Krea-2 LoRAs (diffusers PEFT format) are supported and apply to both the transformer and — where the LoRA includes text-encoder layers — the Qwen3-VL encoder.