Downloads · 30 days
230
41% of all-time downloads
LAXMAYDAY/krea2-scene-linear-hdr-lora
krea2-scene-linear-hdr-lora is a text-to-image model from LAXMAYDAY. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as cc-by-nc-4.0.
A small LoRA that makes Krea 2 generate true scene-linear HDR — float radiance with values well above 1.0, exportable to .exr for render / VFX / IBL. The model generates in a LogC4-encoded space (values stay in [0,1],…
Downloads · 30 days
230
41% of all-time downloads
All-time downloads
561
Public
Repo size
939 MB
Likes
9
Public
Click a slice to open those files.
.safetensors939 MB · 100%
From the Hugging Face model README
A small LoRA that makes Krea 2 generate true scene-linear HDR — float radiance with
values well above 1.0, exportable to .exr for render / VFX / IBL. The model generates in a
LogC4-encoded space (values stay in [0,1], fed to the frozen Qwen Image VAE); you recover
the HDR by applying inverse-LogC4 after decode.
Trained on RAW with musubi-tuner (networks.lora_krea2, dim/alpha 32, 264 modules).
| file | use |
|---|---|
krea2-hdr-logc4-v1.safetensors | LoRA for musubi-tuner / diffusers (native key names) |
krea2-hdr-logc4-v1-COMFYUI.safetensors | LoRA for ComfyUI (keys remapped — the musubi one does not load in ComfyUI as-is) |
The LoRA output is a LogC4 code in [0,1], not linear. Pipeline:
prompt → Krea2 + this LoRA → LogC4 code [0,1] → inverse-LogC4 → scene-linear (>>1) → EXR / HDR AVIF
scene-linear HDR, high dynamic range, physically based lighting.[0,1] clamp is harmless — values >1 appear only after inverse-LogC4.ComfyUI (use the -COMFYUI file): install the comfyui_krea_hdr node pack (LogC4ToLinear +
SaveEXRSceneLinear). Graph: UNETLoader(Krea2 RAW) → CLIPLoader(type=krea2) → VAELoader(Qwen Image VAE) → LoraLoader → KSampler(cfg 5.5, euler, simple, 28 steps) → VAEDecode → LogC4ToLinear → SaveEXRSceneLinear.
Do NOT add ModelSamplingSD3/shift — Krea2 already applies its shift; adding one double-shifts and
washes the image out.
musubi-tuner (use the native file): krea2_generate_image.py ... --lora_weight krea2-hdr-logc4-v1.safetensors,
then inverse-LogC4 → EXR.
Same prompt+seed, base vs LoRA: the base clips highlights flat at the decode ceiling (fake HDR); this LoRA spreads highlights into graduated values (real HDR) — pinned-at-ceiling 6.20% → 0.66%. Generalizes to out-of-distribution prompts (7/8 fire/neon/portrait/cathedral/candle produce real HDR, brightest region on the actual light source).