Half the steps · ~1.6× faster · 45% of the gap to the 8-step teacher closed · texture at 1.03× the teacher's, verified clean · teacher preferred on only 6 of 45 judged renders · 12 trained resolutions · 78,000 training samples · 21 days on one RTX 3090.
A LoRA for Krea 2 Turbo that reduces the minimum usable step count from 8 to 4 — Turbo's own model and sigmas, half the denoising passes, and the fine texture that 4-step Turbo loses put back.
⚡ Half the steps — 8 → 4, on Turbo's own deployment sigmas
⏱️ ~1.6× faster end to end — 54.5 s vs 88.7 s at 1024×1024 (1.8× on denoise alone)
🎯 Texture as good as the teacher or better — 1.03× the teacher's fine-texture energy at 1280² and 1440², every frequency band within 10%; verified clean: saturation 0.96–0.97×, fewer clipped highlights/shadows, skin texture 0.97–0.99×
📏 45% of the 4-step gap closed — held-out velocity error fell from 4.70e-02 (stock Turbo at 4 steps) to 2.59e-02 with the LoRA; VLM judge preferred teacher on only 6 of 45 renders (37 ties, 2 LoRA wins)
🗣️ Prompt-aware training — critic scores images against their prompts during training
📐 12 trained resolutions — multi-aspect from 512×512 up to 1440×1440
🔌 Drop-in — plain LoRA weights for diffusers and ComfyUI. No custom nodes, no patched sampler, no code
📷 43,044 real-photo crops — 25,560 from LSDIR + 17,484 from Flickr2K, captioned, in critic's real set
🔢 78,000 training samples in shipped weights
📅 21 days on a single RTX 3090
🔁 16 recipe adjustments — each made on measurement of the one before
💡 Too strong on a prompt? Turn it down. The LoRA restores fine texture, and on some subjects — stylised art, high-contrast splash pieces, very large renders — that can read as too much at strength 1.0. Effect scales smoothly: 0.75 is a good second setting, 0.6–0.9 is fair game.
The 15 test prompts, rendered by Krea 2 Turbo with this LoRA at 4 steps
1import torch
2from diffusers import Krea2Pipeline
3from huggingface_hub import hf_hub_download
4from safetensors.torch import load_file
56pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")78lora = hf_hub_download("lvladikov/Krea2-Turbo-Distill-4step-LoRA","krea2_turbo_4step_rank_64_lora.safetensors")9state = load_file(lora)10state ={f"transformer.{k}": v for k, v in state.items()ifnot k.endswith(".alpha")}11pipe.load_lora_weights(state, adapter_name="4step")1213image = pipe("a fox in the snow", num_inference_steps=4, guidance_scale=0.0).images[0]14image.save("krea2_4step.png")
num_inference_steps=4 is the whole config. Pipeline applies Turbo's fixed timestep shift (μ = 1.15) and evaluates at σ = 1.0, 0.905, 0.760, 0.513 — exactly the four points the LoRA was trained on. Keep guidance_scale=0.0.
Strength: pipe.set_adapters(["4step"], adapter_weights=[0.75]). Stock Turbo for comparison: pipe.unload_lora_weights() + num_inference_steps=8.
⚙️ cfg 1.0, not 0.0. ComfyUI expresses "no CFG" as 1.0 (one forward pass); diffusers uses 0.0. Setting 0.0 in ComfyUI is not the same thing.
Performance (1024×1024, Apple Silicon MLX bf16)
load
denoise
total
Turbo 8 steps (quality bar)
8.2 s
77.5 s
88.7 s
Turbo 4 steps, no LoRA
7.8 s
38.8 s
49.7 s
Turbo 4 steps + this LoRA
7.3 s
44.0 s
54.5 s
4 steps with LoRA is ~1.6× faster than the 8-step bar (54.5 s vs 88.7 s). Denoise alone: 1.8× (44.0 s vs 77.5 s).
Per-step cost: 9.7 s → 11.0 s (~13% slower), plus ~1.3 GB peak memory. Loading the LoRA costs nothing measurable. Halving steps wins comfortably.
LoRA Strength
strength
what happens
below 1.0
Correction partly applied — output between unassisted 4-step and full LoRA. 0.75 for when 1.0 is too textured/hard
1.0
Trained point, recommended
1.0–1.5
Extrapolation — surface detail denser, micro-contrast harder, coherent but stylised
above 1.5
Not recommended — breaks into uniform speckle/noise over whole image
Reach for steps before strength: 1.0 at more steps is the dependable way to get more. Strength and step count trade against each other.
LoRA strength comparison
Method
Progressive distillation with Krea 2 Turbo as its own teacher. Teacher ran 8 steps at μ = 1.15, guidance 0.0; full trajectory recorded. Student trained to cover two teacher steps in one:
v_target = (x_{i+2} − x_i) / (σ_{i+2} − σ_i)
The even indices of the 8-step schedule are precisely the four sigmas the 4-step student deploys on — no interpolation, no schedule mismatch.
Critic (LADD-style) on frozen Turbo features at block 14:
Real: teacher finals (unpaired) or real photographs (half the draws), re-noised to σ ∈ [0.02, 0.5]
Fake: student's predicted clean latent
Prompt-aware head reads pooled text vector; mismatch term forces real images under wrong prompts to read fake
Real photos captioned so they participate in prompt-aware term
Three key weight choices:
Final chord (σ = 0.512, decides fine texture) weighted 3× in PD loss
Low-frequency anchor on large buckets (weight 0.2) — structure held to teacher, fine band free
Shipped adapter is Polyak (EMA) average (decay 0.999), not last live state
4 global linears — time_embed.linear_1, time_embed.linear_2, time_mod_proj, final_layer.linear
The global linears are included deliberately. Measuring Krea's own Raw→Turbo delta:
layer
relative ‖ΔW‖/‖W‖
time_embed.linear_2
0.0777 ← largest change in network
time_embed.linear_1
0.0429
final_layer.linear
0.0265
typical block linear
~0.014
time_embed.linear_2 moves ~5.5× more than any block linear. Changing step count is largely a change to how the model reads the timestep — a LoRA freezing the timestep path withholds the weights the task most needs.
Training Data
13,750 prompts from Lakonik/t2i-prompts-3m (sampled without replacement, deduplicated, filtered), one recorded teacher trajectory each
203 held-out validation + 641 OOD evaluation — never received a gradient step
43,044 real-photo crops — 25,560 LSDIR + 17,484 Flickr2K, cut at native resolution to 12 buckets, quality-gated, VAE-encoded, captioned per crop
Photos only reached the critic — never regression targets — so adapter learned detail density from reality, not content.
Resolutions (12 buckets)
512×512
512×768
768×512
768×768
768×1024
1024×768
1024×1024
960×1280
1280×960
1280×1280
1440×1280
1440×1440
1440×1440 had a deliberately small share — enough to learn the size without spending budget there. Buckets interleaved by remaining samples, not curriculum.
Hardware
Trained on single RTX 3090 (24 GB). Frozen base quantized weight-only to int8 (blockwise-64) — ~0.007 relative error, ~3% step time cost. Teacher trajectories rolled at same precision (targets permanent, error baked in).
Every bucket trained under full int8 up to 1440×1440. Large buckets fit via:
Checkpointed block inputs staged to pinned host memory (numerically exact)
Discriminator pass after generator backward (peaks don't overlap)
Trunk stopped at feature tap it actually reads
Released LoRA is bf16 applied to unquantized base.
Usage Notes
🎯 Krea 2 Turbo only — trained against Turbo's weights and schedule
🚫 Keep guidance at 0.0 (ComfyUI: cfg 1.0, not 0.0)
📐 Keep μ = 1.15 — training targets anchored to that grid
🔬 Training used int8 base; released LoRA is bf16 on unquantized base
Examples
Every sheet below: base model (8 steps), base at 4 steps without LoRA, base at 4 steps with LoRA — same seed throughout. Compare panels 2 vs 3 to isolate LoRA effect. NFE = steps (Turbo is CFG-free).
Portrait of a young woman with freckles and windswept auburn hair...
portrait comparison
Turbo 8 steps
Turbo 4 steps, no LoRA
Turbo 4 steps + LoRA
8 steps
4 steps
4 steps + LoRA
Kingfisher bursting out of water...
kingfisher comparison
Turbo 8 steps
Turbo 4 steps, no LoRA
Turbo 4 steps + LoRA
8 steps
4 steps
4 steps + LoRA
Rainy night city street with glowing neon signs...
neonstreet comparison
Turbo 8 steps
Turbo 4 steps, no LoRA
Turbo 4 steps + LoRA
8 steps
4 steps
4 steps + LoRA
(12 more examples in full version — see assets/ for all 15 prompts)
Resolution Sweeps
assets/resolution_sweeps/ — this LoRA at every trained resolution for all 15 test prompts (same prompts, seed, 4 steps, strength 1.0). Nothing cherry-picked.
_teacher-8step/ — official Krea 2 Turbo 8-step reference renders for same prompts/seeds/resolutions.
Two ways to read: down the sweep (does it hold across resolutions?) or against teacher (open same file in both folders).
Bonus: 2-Step Extreme Test
Out-of-spec experiment — not for production. Useful as fast preview: at 2 steps, LoRA at strength 1.0 gives reliable read on composition/look at quarter of 8 steps.
Stock Turbo ghosts/smears at 2 steps; with LoRA image stays coherent and sharp. All 15 prompts checked: extra detail is real subject detail (hair, skin, fabric) + sharper atmospheric elements where prompt calls for it. Nothing unprompted appears, nothing intrudes on faces.
Full strips: assets/resolution_sweeps/2step-LoRA-extreme/
🔭 Dedicated 2-step LoRA now published:lvladikov/Krea2-Turbo-Distill-2step-LoRA. Renders at 2 steps for fast previews/drafts. Not this adapter's quality — for quality renders, stay here.
Archive
Earlier checkpoints and sweeps under _archive/ — superseded, not maintained.
What's next
A 2-step LoRA was the natural follow-on, and it is now published as its own project: lvladikov/Krea2-Turbo-Distill-2step-LoRA.
It is a separate release rather than a competitor to this one: at two steps a distilled model gives up more than at four, so the aim is a usable 2-step Turbo — fast previews and drafts at half this adapter's cost, a quarter of the teacher's — not the quality bar this adapter holds. It is still in training, and its page carries the measurements and the faults as they stand.
Detailed Model Card
For more details, if interested, have a look at the Detailed Model Card.
License
This adapter is a Derivative of Krea 2 Turbo under the Krea 2 Community License Agreement. Everything the agreement says about Krea 2 Turbo applies to this LoRA: Acceptable Use Policy, revenue threshold for commercial use, content-filtering duty for deployments.
