musubi-tuner vs SimpleTuner for Krea 2 LoRA training

Both musubi-tuner and SimpleTuner can train Krea 2 LoRAs. Here is how they compare, using each project's docs and GitHub activity.

	musubi-tuner	SimpleTuner
Krea 2 support	supported (fp8 / ConvRot int8 base)	supported
GitHub stars	2107	2942
Last commit	2026-10-12	2026-10-20
Latest release	v0.3.6	v4.10.1
VRAM (Krea 2)	ai-toolkit: ~20 GB at batch 1 with qfloat8; also trains on 12 GB with Krea Raw, low VRAM on, 50% transformer offload, 100% text-encoder offload, convrot 8, compile off, LoKr factor 8, 512 resolution only, and cached latents plus text embeddings. musubi: 12GB+ recommended for image training (general guidance); fp8 or --convrot_int8 halves weight VRAM
Overview	kohya's CLI scripts for newer models; supports fp8 base weights and recommends 12 GB+ VRAM for image training.	bghira's trainer; more powerful (e.g. teacher-student regularization), but the data loader is harder to set up.

Which should you pick?

If you want the quickest start with a web UI, pick ai-toolkit. If you already use a script-based trainer's ecosystem, stick with it.

Shared Krea 2 settings

Natural-language captions, ~70-500 words; shorter captions lock features harder
Diverse dataset (varied expressions/angles)
Train at 1024px or higher
Batch size >= 2 if VRAM allows
Training at 512px can work for output up to ~2MP; add higher-res buckets gradually
ai-toolkit downscales images larger than 1536px
Automagic3 can give weaker LoRAs than v1/v2; pair it with LoKr factor 8 or 4 and sigmoid timesteps (that's my recipe). ai-toolkit's experimental automagic4 (Oct 23) keeps the LR from drifting to the floor
EMA in ai-toolkit makes no noticeable difference; Automagic v3 already behaves a lot like EMA
OneTrainer preview-2 branch (not master yet): LoRA on 8-bit quantized Krea 2 trains ~1.2x faster (16 GB preset); FLUX.2 16 GB preset ~1.3x; faster 8-bit math on RTX 50-series; DoRA not sped up
Character captions: name, expression, pose, clothing, then scene
Kaloscope style adapters (heathcliff01) for Krea 2 Raw and Turbo: style by artist name, weighted blends or a reference image; needs its own ComfyUI nodes
ai-toolkit: point to local or alternative Qwen3-VL text encoder and Qwen-Image VAE files with text_encoder_path and vae_path under model_kwargs in the YAML
Very slow steps (hundreds of seconds per step) mean the GPU is out of VRAM and swapping; lower the batch size or turn on low VRAM / offloading
Pose control for Krea 2 Turbo: the Krea-2-PoseControl LoRA (MIT, 17-keypoint skeleton) with the ComfyUI-Krea2-Pose node pack; use release/krea2-pose-control-mix025.safetensors
12 GB ai-toolkit recipe (Krea Raw): low VRAM on, 50% transformer offload, 100% text-encoder offload, convrot 8 quantization, compile off, LoKr factor 8, 512 resolution only, cache latents and text embeddings. First steps can take many minutes; if the run hangs after the first step, try dropping the training adapter, a lower quant (Q6/Q4), or skipping text-encoder offload once embeddings are cached

Setup guides

Where to rent a 16 GB+ GPU

Cheapest 16 GB+ cards (2026-10-20 08:06 UTC) from RunPod and Vast.ai. Prices move constantly; see the live price table.

GPU	VRAM	RunPod community $/hr	Vast.ai cheapest $/hr
Tesla V100	16 GB	$0.19	$0.08
RTX 3090	24 GB	$0.22	$0.12
RTX 5060 Ti	16 GB	—	$0.14
Tesla V100S	32 GB	—	$0.14
RTX A5000	24 GB	$0.16	—
RTX A4000	16 GB	$0.17	—

Sources

FAQ

Is musubi-tuner or SimpleTuner better for Krea 2?

Both support it. Pick based on workflow (UI vs scripts) and the notes above.

Can I train Krea 2 LoRAs with musubi-tuner?

supported (fp8 / ConvRot int8 base)

Can I train Krea 2 LoRAs with SimpleTuner?

supported

Weekly newsletter: new models, trainer releases, cheapest GPUs. Subscribe

Data updated 2026-10-20. Disclosure: RunPod and Vast.ai links are referral links; ImageLoRA may earn a commission at no cost to you. unknown = no data yet. · Raw data (JSON) · llms.txt