Kroma v0.3: Krea 2 Fine-Tune Adds Full Base Checkpoint

ComfyUI Wikinews

Lodestones ships Kroma v0.3 for Krea 2: a non-distilled full base checkpoint, a turbo variant, and a community LoRA pack that unlocks prompt following fixes.

Lodestones uploaded Kroma v0.3 to the Kroma repo on Hugging Face between August 19 and 30, the third iteration of the community fine-tune of Krea 2. v0.3 comes in two weights: a full base checkpoint (about 51.3 GB) that has no distilled turbo delta baked in, and the familiar turbo checkpoint (about 25.6 GB) for fast sampling. A separate kroma-v0.3-tdm-4steps-artifact file (about 234 MB) rounds out the release.

Kroma v0.3 cover

What is new in v0.3

The headline change is that Kroma now exists as a raw-base fine-tune, not just a turbo-merged checkpoint. Krea 2 ships in two flavors: the raw (non-distilled) model that produces the highest quality but needs more steps, and the Turbo distillation that samples in 8-12 steps. Kroma v0.1 and v0.2 could only be used at Turbo speed, because the fine-tune was trained on (or merged with) the Turbo delta. With v0.3-base, the fine-tune finally covers the non-distilled weights, so the "no distillation artifacts" route is open for Kroma too.

FileSizeWhat it is
kroma-v0.3-base.safetensors~51.3 GBFull fine-tune of Krea 2 raw (non-distilled) weights
kroma-v0.3-turbo.safetensors~25.6 GBTurbo-speed variant, sampled like Krea 2 Turbo
kroma-v0.3-tdm-4steps-artifact.safetensors~234 MBExperimental 4-step TDM artifact

Community extras already circulating

The Banodoco krea-2-image channel moved fast on the release:

  • INT8 ConvRot quants of the v0.3 turbo checkpoint appeared within hours from Hiccup1234 and thedarkthrust, with a cutecaption collection tracking the conversions.
  • Silveroxides maintains Kroma-LoRA with rank-384 LoRA extracts, including a custom-unlock build for v0.3 base.
  • Hippotes published a kroma-v0.3-txtfusion_diff extraction on Krea-2-Experiments that lets you take just the text-fusion layers of Kroma and stack them on the official Krea 2 Turbo checkpoint, which some users report as the best of both worlds.

How to use Kroma v0.3 in ComfyUI

The fine-tune uses the standard Krea 2 stack, so it works with ComfyUI's native Krea 2 support:

  1. Download the checkpoint into ComfyUI/models/diffusion_models/
  2. Load the Krea 2 text encoder (Qwen3-VL, 12 layers) with a CLIPLoader set to type krea2
  3. Load the Krea 2 VAE
  4. For kroma-v0.3-turbo: sample with Turbo settings (8-12 steps, CFG 1.0-1.5, shift/mu 1.15). For kroma-v0.3-base: use regular sampling settings as you would for the Krea 2 raw checkpoint.

One caveat from early users: Kroma is a fine-tune with its own "vibe", and prompts do not always translate 1:1 from Krea 2. If a subject stops following the prompt, a small amount of a subject LoRA nudges it back.

Availability

Comments

Sign in with GitHub to join the discussion.

Loading comments…
Kroma v0.3: Krea 2 Fine-Tune Adds Full Base Checkpoint | ComfyUI Wiki