--- title: LumiPic canonical_url: "https://www.modelscope.cn/models/oumoumad-ai/LumiPic" md_url: "https://www.modelscope.cn/models/oumoumad-ai/LumiPic.md" repository: oumoumad-ai/LumiPic last_updated: 2026-10-04 license: mit pipeline_tag: image-to-image tasks: - image-to-image base_model: - Qwen/Qwen-Image-Edit-2511 - black-forest-labs/FLUX.2-klein-base-4B - black-forest-labs/FLUX.2-klein-base-9B base_model_relation: adapter parameters: 2.6B tensor_type: - F16 library_name: - safetensors supports_inference: img2img downloads: 394 stars: 0 tags: - lora - hdr - exr - tone-mapping - logc3 - logc4 - acescct - aces - arri - diffusion-transformer - qwen-image-edit - flux2-klein --- # LumiPic > LumiPic - oumoumad-ai 在 ModelScope 开源的模型。LumiPic — Single-Image SDR to HDR LoRA Converts standard dynamic range (SDR) images to high dynamic range (HDR) EXR files — float-valued, with range well beyond what an 8-bit SDR output can carry. Based on LumiVid… oumoumad-ai/LumiPic 是 ModelScope 魔搭社区上的 2.6B 参数image-to-image模型，采用 mit 许可，基于 Qwen/Qwen-Image-Edit-2511、black-forest-labs/FLUX.2-klein-base-4B、black-forest-labs/FLUX.2-klein-base-9B 构建，并支持在线推理（img2img）。 - **Repository**: oumoumad-ai/LumiPic - **License**: mit - **Tasks**: image-to-image - **Parameters**: 2.6B - **Base model**: Qwen/Qwen-Image-Edit-2511, black-forest-labs/FLUX.2-klein-base-4B, black-forest-labs/FLUX.2-klein-base-9B - **Online inference**: img2img - **Tags**: lora, hdr, exr, tone-mapping, logc3, logc4, acescct, aces, arri, diffusion-transformer, qwen-image-edit, flux2-klein - **Downloads**: 394 - **Stars**: 0 - **Last updated**: 2026-10-04 Source: https://www.modelscope.cn/models/oumoumad-ai/LumiPic --- # LumiPic — Single-Image SDR to HDR LoRA Converts standard dynamic range (SDR) images to high dynamic range (HDR) EXR files — float-valued, with range well beyond what an 8-bit SDR output can carry. Based on [LumiVid](https://hdr-lumivid.github.io/) ([paper](https://arxiv.org/abs/2604.11788)) — the Lightricks research that introduced log-encoded diffusion for HDR generation. LumiPic is the same technique adapted to single-image diffusion transformers; *the technique is base-model agnostic*. Two trained LoRA families are published here, across three base models. > **2026-10-03 — V11 ACEScct added (Qwen-Image-Edit-2511).** A new LoRA trained to output **ACEScct** instead of ARRI log, on camera-style SDR inputs (hard-clipped sRGB, as real photos and generated images are) rather than display-rendered ones. It needs **two** Gear nodes — an ACEScct *encode* on the input as well as the decode on the output — and its own workflow. See [V11 ACEScct](#v11-acescct--what-changed) below. > > **2026-05-24 — V10 LogC4 added (alpha).** Six new checkpoints (two per model family) trained on **ARRI LogC4** instead of LogC3, giving ~3 extra stops of highlight headroom (linear ceiling ~470 vs LogC3's ~55). Testing so far is limited; see the [V10 caveats](#v10-logc4-status--caveats) section below. ## Examples Same 20 HDR outputs, viewed at two extreme exposure offsets — highlights still hold structure at EV+6, shadows still hold information at EV-6. **Exposure +6 (highlights pulled down):** ![EV+6](grid_ev+6.png) **Exposure -6 (shadows pushed up):** ![EV-6](grid_ev-6.png) ## Choosing a curve: LogC3 vs LogC4 vs ACEScct | Curve | Linear ceiling | Stops above 0.18 mid-gray | Decode node | |---|---|---|---| | **LogC3** (V1 / V5b / V9 / klein\_alpha\_\*) | ~55.2 | ≈ 8.3 | `Gear · LogC3 Decode + Save EXR` | | **LogC4** (V10 / `*_logc4_*`) | ~470 | ≈ 11.3 | `Gear · LogC4 Decode + Save EXR` | | **ACEScct** (V11 / `*_acescct_*`) | ~223 | ≈ 10.3 | `Gear · ACEScct Decode + Save EXR` **and** `Gear · ACEScct Encode` on the input | > ⚠️ **Picking the wrong decode curve silently produces wrong absolute linear values.** The EXR will look plausibly tonemapped but the absolute luminance will be off. Match the decode node to the LoRA's filename: `_logc4_*` → LogC4 node; `_acescct_*` → ACEScct nodes; everything else → LogC3 node. The ACEScct LoRA additionally expects its **input** image ACEScct-encoded (`Gear · ACEScct Encode`, `srgb_display`); feeding it a plain sRGB image is the same class of mistake as the wrong decode. The LogC4 family adds about 3 extra stops of highlight headroom — important for shots with direct sun, fire, specular reflections, or window-blown highlights that were hitting the LogC3 ceiling. For lower-DR content (interior, overcast, night), the two curves produce very similar outputs and LogC3 is fine. ## Weights ### Qwen-Image-Edit-2511 (mature) 5+ training iterations, 563 MB per LoRA. Best quality, larger base (~54 GB). **LogC3 (stable):** - `v5b_step2000.safetensors` — **Qwen default**. Most robust overall; best on stylized/AI-generated SDR inputs. - `v9_step1500.safetensors` — alternative. LumiVid-aligned augs (joint HDR+SDR EV shifts, luminance blur p=1.0). Slightly better on natural photos. - `hdrdit_v1_QE2511.safetensors` — original v1 release. **ACEScct (V11 — 2026-10-03):** - `v11_acescct_step3000.safetensors` — ACEScct in, ACEScct out; EXR is linear ACEScg (AP1). Trained on camera-style SDR with a cosine LR schedule and EMA. Use with [`SDR_To_HDR_acescct_QE11.json`](https://huggingface.co/oumoumad/LumiPic/resolve/main/SDR_To_HDR_acescct_QE11.json?download=true); LoRA strength **1.0**. **LogC4 (V10 alpha — 2026-05-24):** - `v10_logc4_step1500.safetensors` — recommended V10 candidate by stats (highest mean p99 = 17.96 across 10 golden scenes). - `v10_logc4_step3000.safetensors` — final (full training run completion). ### FLUX.2-klein-base-4B (alpha) Single training iteration, 88 MB per LoRA. Apache 2.0 base, 5× smaller than Qwen, fastest end-to-end. **LogC3:** - `klein4b_alpha_step1750.safetensors` — **klein-4B default**. Faithful HDR look; well-balanced. - `klein4b_alpha_step1000.safetensors` — alternative. Aggressive HDR (higher p99) but tends to blow out bright highlights. **LogC4 (V10 alpha):** - `klein4b_v10_logc4_step1500.safetensors` — strongest V10 performer in early ComfyUI testing (better than the Qwen V10 — see caveats). - `klein4b_v10_logc4_step2000.safetensors` — final. ### FLUX.2-klein-base-9B (alpha) Single training iteration, 158 MB per LoRA. Larger klein variant — more capacity, more nuanced HDR. Base model is **gated** on HF (request access at the [base model page](https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B) before first run). **LogC3:** - `klein9b_alpha_step2000.safetensors` — **klein-9B default**. Stable, well-behaved (mean p99 9.1, no scenes saturated in our 20-image benchmark). - `klein9b_alpha_step1250.safetensors` — most "good" scenes (13/20 in 5-50 p99 range, 0 saturated). Practically the best by per-scene quality count. - `klein9b_alpha_step1000.safetensors` — most aggressive (mean p99 20.6, but 4 scenes saturated). Pre-overfit peak HDR range. - `klein9b_alpha_step{250,500,750,1500,1750}.safetensors` — intermediate snapshots, available for experimentation. The training overfit curve was steep on klein-9B (mean p99: 1000=20.6 → 1250=11.1 → 1500=9.3 → 1750=9.6 → 2000=9.1). Step 2000 is the safest default; step 1250 is the practical sweet spot. **LogC4 (V10 alpha):** - `klein9b_v10_logc4_step1500.safetensors` — recommended V10 candidate. - `klein9b_v10_logc4_step2000.safetensors` — final. ## V11 ACEScct — what changed - **Encoding.** Input and output are both ACEScct (AMPAS S-2016-001): the SDR is linearised with the plain sRGB EOTF, converted Rec.709 → AP1 and ACEScct-encoded before the model sees it; the output is decoded back to linear ACEScg. Linear ceiling ≈ 223. - **Training inputs.** Earlier LoRAs were paired with SDRs made by a display transform that compresses highlights without clipping — a mapping a formula can invert. V11's SDRs are camera-style: hard clip at 1.0 and the sRGB curve, 8-bit, some JPEG. Below the clip the target equals the decoded SDR, so the model's job is the clipped highlights. - **Measured against real HDR ground truth** (38 held-out scenes, camera-style SDR, diffusers, 20 steps, no distillation LoRA): median midtone error **0.12 stops** (the VAE's own round-trip floor is 0.07), midtone bias +0.04 stops, colour ΔE 2.1. Highlights are reconstructed conservatively — about a third of a stop under ground truth in energy. - **ComfyUI specifics.** With a GGUF base, load this LoRA with **`LoraLoaderBypassModelOnly`** at strength 1.0: the regular loader merges the delta into rounded bf16 weights and loses most of it. Use **`TextEncodeQwenImageEdit`** (not the *Plus* node) with the ACEScct-encoded image on both the positive and the negative, prompt `Convert this image to HDR`. The released workflow keeps the 4-step Lightning setup of the LogC3 workflow; the ground-truth numbers above were measured at 20 steps without it — bypass the Lightning LoRA and set 20 steps to match. - **Inputs it is not for.** A display-rendered SDR (e.g. an ACES ODT render of an EXR) reads about a stop dark; those are better served by inverting the display transform. - **Seeds.** Midtone pinning varies with the noise seed; judge on three or more. ## V10 LogC4 — status & caveats **Testing has been limited.** Notable observations so far: - **Numerical evaluation via diffusers** (Qwen V10 across 10 golden scenes) shows clear improvements vs V9 LogC3 — mean p99 jumps from 7.76 to 17.96 (2.3×), mean peak from 41.6 to 263.3 linear, with no obvious regressions in shadow handling. The V10 Qwen LoRA genuinely uses the extra LogC4 headroom on bright content. - **ComfyUI testing of the same Qwen V10 LoRAs has *not* yet confirmed that improvement** — visual results look weaker than expected vs V9. We haven't fully diagnosed the discrepancy; candidates include diffusers-vs-ComfyUI pipeline differences (LoRA application, sampler, scheduler), VAE precision, or our test methodology. - **Klein V10 LoRAs (4B and 9B) perform well in ComfyUI testing** — `klein4b_v10_logc4_step1500.safetensors` has been the strongest LogC4 candidate in early ComfyUI runs. If you're picking one V10 to try first, start there. - The V10 dataset was rebuilt from raw scene-linear EXR sources (no LogC3 reuse) — 1143 pairs from 381 source scenes, joint EV-shifted, paper-aligned augmentations. - VAE roundtrip pre-flight (LogC3 vs LogC4 on the same VAE) showed LogC4 has slightly better shadow/midtone alignment and similar highlight alignment — so the architecture supports it. Treat all V10 ckpts as **alpha for community testing**, not as drop-in replacements for V9 in production. Share any useful feedback for improvement — open an issue on the GitHub repo with examples, observations, or pipeline differences you spot. Especially valuable: anything that helps explain the Qwen diffusers-vs-ComfyUI mismatch. ## Usage **Qwen-Image-Edit-2511:** ```python from diffusers import QwenImageEditPipeline import torch from PIL import Image pipe = QwenImageEditPipeline.from_pretrained("Qwen/Qwen-Image-Edit-2511", torch_dtype=torch.bfloat16) # LogC3 default: pipe.load_lora_weights("oumoumad/LumiPic", weight_name="v5b_step2000.safetensors") # LogC4 (V10 alpha): # pipe.load_lora_weights("oumoumad/LumiPic", weight_name="v10_logc4_step1500.safetensors") pipe = pipe.to("cuda") image = Image.open("photo.jpg").convert("RGB") output = pipe(prompt="Convert this image to HDR", image=image, num_inference_steps=40, guidance_scale=3.0, output_type="pt") # Decode LogC3 → linear HDR (see logc3.py in GitHub repo) # Decode LogC4 → linear HDR (see logc4.py — same interface, different curve constants) ``` **FLUX.2-klein-base-4B / 9B** (requires bleeding-edge diffusers: `pip install "git+https://github.com/huggingface/diffusers.git"`): ```python from diffusers import Flux2KleinPipeline import torch from PIL import Image # 4B (Apache 2.0, ungated) pipe = Flux2KleinPipeline.from_pretrained("black-forest-labs/FLUX.2-klein-base-4B", torch_dtype=torch.bfloat16) # LogC3: pipe.load_lora_weights("oumoumad/LumiPic", weight_name="klein4b_alpha_step1750.safetensors") # LogC4 (V10 alpha — recommended starting point for V10 testing): # pipe.load_lora_weights("oumoumad/LumiPic", weight_name="klein4b_v10_logc4_step1500.safetensors") # 9B (gated — accept license on HF first) # pipe = Flux2KleinPipeline.from_pretrained("black-forest-labs/FLUX.2-klein-base-9B", torch_dtype=torch.bfloat16) # pipe.load_lora_weights("oumoumad/LumiPic", weight_name="klein9b_alpha_step2000.safetensors") # or LogC4: weight_name="klein9b_v10_logc4_step1500.safetensors" pipe.enable_model_cpu_offload() # or pipe.to("cuda") if you have 32GB+ image = Image.open("photo.jpg").convert("RGB") output = pipe(prompt="Convert this image to HDR", image=image, num_inference_steps=25, guidance_scale=3.0, output_type="pt") ``` See the [GitHub repo](https://github.com/oumad/LumiPic) for complete inference code with EXR output (`inference.py` for Qwen, `inference_klein.py` for klein). ## Quick Inference ```bash git clone https://github.com/oumad/LumiPic.git && cd LumiPic pip install -r requirements.txt python inference.py --image photo.jpg # Qwen path (production) python inference_klein.py --image photo.jpg # klein path (alpha) ``` The base model and LoRA weights download automatically on first run. ## ComfyUI Ready-to-use workflows: **LogC3 (stable):** - [`SDR_To_HDR_QE11.json`](https://huggingface.co/oumoumad/LumiPic/resolve/main/SDR_To_HDR_QE11.json?download=true) — Qwen-Image-Edit-2511 - [`SDR_To_HDR_klein4b.json`](https://huggingface.co/oumoumad/LumiPic/resolve/main/SDR_To_HDR_klein4b.json?download=true) — FLUX.2-klein-base-4B - [`SDR_To_HDR_klein9b.json`](https://huggingface.co/oumoumad/LumiPic/resolve/main/SDR_To_HDR_klein9b.json?download=true) — FLUX.2-klein-base-9B **ACEScct (V11):** - [`SDR_To_HDR_acescct_QE11.json`](https://huggingface.co/oumoumad/LumiPic/resolve/main/SDR_To_HDR_acescct_QE11.json?download=true) — Qwen-Image-Edit-2511 + `v11_acescct_step3000.safetensors`. Same graph as the LogC3 Qwen workflow with `Gear · ACEScct Encode` added on the input and the decode swapped for `Gear · ACEScct Decode + Save EXR`. **LogC4 (V10 alpha):** - [`SDR_To_HDR_logc4_klein9b.json`](https://huggingface.co/oumoumad/LumiPic/resolve/main/SDR_To_HDR_logc4_klein9b.json?download=true) — FLUX.2-klein-base-9B + V10 LogC4 LoRA (the strongest V10 configuration in current testing) The LogC3 workflows use the **Gear · LogC3 Decode + Save EXR** node; the LogC4 workflow uses **Gear · LogC4 Decode + Save EXR** (added in ComfyUI_Gear v0.2.0). Same node API, different curve — never mix them. The ACEScct workflow uses **Gear · ACEScct Encode** and **Gear · ACEScct Decode + Save EXR**; update ComfyUI_Gear to a build that includes them. Drop the JSON onto your canvas, place the matching LoRA file in `ComfyUI/models/loras/{qwen,flux-2}/hdr/`, install [ComfyUI_Gear](https://github.com/oumad/ComfyUI_Gear) ≥ v0.2.0, queue with prompt `"Convert this image to HDR"`. ## Training - **Technique**: LoRA (rank 32) on the DiT transformer, trained to output ARRI log-encoded HDR (LogC3 for V1–V9, LogC4 for V10) - **Dataset**: ~260–1143 diverse HDR pairs (Poly Haven HDRIs, RED/ARRI footage, CG renders, Blender scenes), augmented with exposure shifts, luminance blur, contrast, JPEG, white-balance jitter. V10 rebuilt from raw scene-linear EXR sources only — no log-encoded reuse. - **Hyperparams**: rank 32, alpha 32, bf16, AdamW lr 1e-4, flowmatch scheduler - **Steps**: 2000–3000 (Qwen sweet spot ~1500; klein-4B sweet spot ~1500–1750; klein-9B sweet spot ~1250–2000 depending on V8 vs V10) - Trained with [Ostris AI-Toolkit](https://github.com/ostris/ai-toolkit). Qwen LoRAs use a fork with float32 `.npy` targets ([npy-float32-targets branch](https://github.com/oumad/ai-toolkit/tree/npy-float32-targets)); klein LoRAs use upstream + a 4-line VAE-on-GPU patch to `flux2_model.py`.