Krea2 Turbo Distill 2 step LoRA - new checkpoint released (chk41320)
Krea 2 Turbo — 2-Step Distillation LoRA (work in progress)
Previous posts/releases - here, here and here.
🧪 A fast-preview adapter, from a project still in training. When the subject is close and fills a good part of the frame — a portrait, a single figure, an object seen up close — two steps already hold up well, and you can rely on this adapter for those images. Small subjects are where it still falls short, people and objects alike: faces in a crowd, figures in a wide scene, the machines at the back of a gym — anything that takes up little of the frame can come out ghosted or smeared. For those, and whenever quality matters more than speed, use the 4-step LoRA. Every figure on the model card measures the adapter honestly against 4-step and 8-step renders. Training continues one recipe change at a time, and a later checkpoint replaces this one only when the sweeps and I visually agree it is better. Known issues.
📐 The saved steps can also go into resolution. A small subject is simply one that covers few pixels, so a larger render makes the same subject bigger — and at a quarter of the teacher's steps, renders up to 2048×2048, Krea's published maximum recommended resolution and beyond the largest size this adapter was trained at (1440×1440), come within easy reach. That makes the adapter a stepping stone to high-resolution renders as well as a fast preview. Past 2048×2048, stock Krea 2 itself begins to duplicate subjects — a property of the base model, with or without this adapter.
chk00041320 (2 Oct 2026) is 9,720 training samples later than chk00031600 (25 Sep 2026), and those samples went to what matters first in a picture — subjects drawn twice, or two poses blended into one, at the large sizes — and to faces in busy scenes. It is also the first checkpoint measured on the full 22-prompt sweep: the original 15, plus seven scenes of people, animals and action added on 29 Sep 2026 because structure is what they test — five friends on a beach, a family at a table seen from above, three kittens in a basket, two dogs in a tug of war, a show jumper, a pianist's hands, a flock of flamingos. Details on the changes since previously released last checkpoint here.
LoRA highlights:
- ⚡ A quarter of the steps — 8 → 2, on Turbo's own deployment sigmas
[1.0, 0.7595] - ⏱️ 4× faster denoising — 76.4 s → 19.3 s at 1024×1024; the adapter's own cost per call is within measurement noise
- 🎯 Fine detail at the teacher's level — 0.97–1.09× the teacher's fine-texture energy at every trained resolution (stock Turbo at 2 steps: 0.40–0.65×); from 1 megapixel up, closer to the teacher than the 4-step adapter
- 📊 Distribution matching, not imitation — matches what the teacher would plausibly produce rather than its exact trajectory, so the student commits instead of averaging into blur and doubled edges
- 🗣️ Prompt-conditioned throughout — teacher and fake scores both read each prompt's conditioning; a blind rubric finds 2 points missing of 352 (objects, counts, attributes, relations), and a judge prefers the 8-step teacher on 12 of 66 (4-step adapter: 6 of 45, on the original 15 prompts), mostly on style
- 📐 12 trained resolutions — multi-aspect from 512×512 up to 1440×1440
- 🔌 Drop-in, no exceptions — plain LoRA, stock Euler, diffusers / ComfyUI / MLX. No custom nodes, no custom sampler
- 🧬 Same shape as the 4-step adapter — rank 64 on the same 228 modules
- 🎲 13,750 recorded teacher trajectories from the 4-step project, reused — not one new teacher run
- 🔢 41,320 training samples in the 2-step stages, on top of the 4-step LoRA's 78,000
- 📅 25 days from the first 2-step launch to this checkpoint, on a single RTX 3090 — training continues
- 🔁 More than forty recipe adjustments across two methods — each kept only when the renders did not get worse
If you have already used my previous version, please redownload/replace krea2_turbo_2step_rank_64_lora.safetensors / krea2_turbo_2step_rank_64_lora_comfyui.safetensors from the latest in the project repo.
Full details on model card - https://huggingface.co/lvladikov/Krea2-Turbo-Distill-2step-LoRA
Not my video, but found someone on YouTube has covered the 2 & 4 step LoRAs including identify preserving edits, have a look: https://www.youtube.com/watch?v=V_qgoV0iPDM (copyright goes to author)
Also if you are using ComfyUI Cloud and have subscription, I have released a new ComfyUI Cloud Workflow / App for Krea 2 Turbo using my 2 & 4 step LoRAs, includes User Prompt, two Random Prompt modes, Prompt Enhancement, Steps, Resolution choices, as well as Upscaling - you can find details here.