Loop ForgeForest creek, sun through mist
Works, from LTX 2.5 Creative Lab LoRAs, tested locally
- LoRA
- SDR to HDR at 1.0
- Output
- 1280×704, 121 frames at 24fps
- Sampling
- 8 steps, euler
- Seed
- 42
- Generated in
- 12 min
- Peak VRAM
- 10.2 GiB
- Ran on
- RTX 3060, 12GB (local)
What was wired in
- Scene embeddingltx-2.5-22b-ic-lora-sdr-to-hdr-scene-emb.safetensors, in place of a prompt
Both versions are pulled down 2.5 stops so that an SDR screen can show the highlights. The SDR source has nothing above white, so the sunlit water turns flat grey. The HDR version keeps the glints and the light shafts. That headroom is the model's estimate of what was there, not recovered data.
SDR to HDR takes no prompt. A scene embedding goes in its place.
Notes
The output is ACEScg EXR frames and a 10-bit HLG master, and the exposure was pulled down on both versions after generation.
Run it yourself
Download everything for this test (.zip, 20.8 MB). It holds the workflow, every input it loads and a README. Copy the inputs into ComfyUI/input, put the models below in place and drag the workflow onto ComfyUI.
| File | Put it in | Size |
|---|---|---|
| ltx-2.5-22b-distilled-transformer-comfy-int8-convrot.safetensors gated | models/diffusion_models | 21.5 GB |
| ltx-2.5-audio-vae-bf16.safetensors gated | models/vae | 364.9 MB |
| ltx-2.5-video-vae-bf16.safetensors gated | models/vae | 1.5 GB |
| ltx-2.5-22b-ic-lora-sdr-to-hdr-1.0.safetensors gated | models/loras | 1.3 GB |
| ltx-2.5-22b-ic-lora-sdr-to-hdr-scene-emb.safetensors gated | models/embeddings | 12.6 MB |
The Lightricks repositories (the LTX 2.5 base model and the LoRAs) are gated. Log in to Hugging Face and accept the terms on each repository page before downloading.
Custom nodes: ComfyUI-LTXVideo at commit 3bf3ca6. Everything else is part of ComfyUI 0.37.0 (commit 0f74f7fb, frontend 1.53.6).