nodes/Lightricks-ComfyUI-LTXVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Automated PR - 2026-10-20

Browse Source
This commit is contained in:
github-actions[bot]
2026-10-20 06:55:07 +00:00
parent 44c8a36b7c
commit 339ecc1380
12 changed files with 6492 additions and 8194 deletions
Download Patch File Download Diff File Expand all files Collapse all files
example_workflows/2.5/HDR_workflows/LTX-2.5_I2V_HDR_Two_Stage_Distilled.json
+562 -703
View File
File diff suppressed because it is too large Load Diff
example_workflows/2.5/HDR_workflows/LTX-2.5_ICLoRA_Inpaint_HDR_Two_Stage_Distilled.json
+728 -910
View File
File diff suppressed because it is too large Load Diff
example_workflows/2.5/HDR_workflows/LTX-2.5_ICLoRA_SDR_to_HDR_Distilled.json
+968 -1066
View File
File diff suppressed because it is too large Load Diff
example_workflows/2.5/HDR_workflows/LTX-2.5_V2V_TiledFusion_HDR_to_HDR.json
+3216 -3856
View File
File diff suppressed because it is too large Load Diff
example_workflows/2.5/HDR_workflows/LTX-2.5_V2V_TiledFusion_SDR_to_HDR.json
+968 -1169
View File
File diff suppressed because it is too large Load Diff
example_workflows/2.5/README.md
+6 -6
View File
@@ -60,7 +60,7 @@ Upscale prompts should describe **look and style** (lighting, palette, film stoc
| -------- | ------------ |
| [LTX-2.5_V2V_TiledFusion_Upscale.json](./LTX-2.5_V2V_TiledFusion_Upscale.json) | **V2V upscale.** Preprocess resizes the guide to `output_size` (FullHD / 4K / 8K), then 8 fused steps with the detail refiner. Tiles come from `tile_size` (HD). |
| [LTX-2.5_V2V_TiledFusion_Native_4K_8K.json](./LTX-2.5_V2V_TiledFusion_Native_4K_8K.json) | **V2V native / dynamic 4K/8K.** Stage 1 at `initial_canvas_size` FullHD (8 steps, Day-To-Night IC-LoRA). Latent ×2 (×4 when `output_size` is 8K), then 3 fused steps with a fresh prompt and the original clip resized to output. Optional second IC-LoRA on stage 2. |
| [LTX-2.5_V2V_TiledFusion_SDR_to_HDR.json](./LTX-2.5_V2V_TiledFusion_SDR_to_HDR.json) | Same recipe as Native, with the HDR IC-LoRA. SDR MP4 → ACEScct, then `LTXVHDRDecodePostprocess` (EXR + HLG). |
| [LTX-2.5_V2V_TiledFusion_SDR_to_HDR.json](./LTX-2.5_V2V_TiledFusion_SDR_to_HDR.json) | Same recipe as Native, with the HDR IC-LoRA. SDR MP4 → ACEScct; EXR via `LTXVHDRDecodePostprocess`, HLG via core Create Video / Save Video. |
| [LTX-2.5_V2V_TiledFusion_HDR_to_HDR.json](./LTX-2.5_V2V_TiledFusion_HDR_to_HDR.json) | **Native HDR→HDR refine.** EXR still (ACEScct, float32 VAE, `img_compression` 0) with the detail refiner instead of the HDR IC-LoRA. Same 4K/8K tiled ladder; EXR + HLG out. |
## Which workflow should I use?
@@ -137,17 +137,17 @@ Two-stage is the better default when you care about spatial detail. Single-stage
| Tiled Fusion SDR→HDR | 2 | 2× or 4× latent | Same as native, HDR IC-LoRA | SDR→ACEScct 4K/8K; EXR + HLG |
| Tiled Fusion HDR→HDR | 2 | 2× or 4× latent | HDR EXR still + refine IC-LoRA | Native ACEScct refine; EXR + HLG |
Native HDR I/O: [LTX-2.5_V2V_TiledFusion_HDR_to_HDR.json](./LTX-2.5_V2V_TiledFusion_HDR_to_HDR.json) — `LTXVLoadEXRSequence` → ACEScct → `LTXVVAEForceFloat32` → refine IC-LoRA tiled fusion → `LTXVHDRDecodePostprocess` (`transfer=acescct`, optional EXR) → `LTXVSaveHLG` from `hdr_linear`. `img_compression = 0`. Same idea as pipelines `--hdr` on Distilled / IC-LoRA.
Native HDR I/O: [LTX-2.5_V2V_TiledFusion_HDR_to_HDR.json](./LTX-2.5_V2V_TiledFusion_HDR_to_HDR.json) — `LTXVLoadEXRSequence` → ACEScct → `LTXVVAEForceFloat32` → refine IC-LoRA tiled fusion → EXR via `LTXVHDRDecodePostprocess` (`transfer=acescct`, EXR=`acescg`); HLG via Convert Image Color Space (`HDR ACEScct` → `HDR`) → Create Video (`HDR`) → Save Video. `img_compression = 0`. Same idea as pipelines `--hdr` on Distilled / IC-LoRA.
SDR→HDR IC-LoRA (separate from native EXR HDR): [LTX-2.3_ICLoRA_HDR_Distilled.json](../2.3/LTX-2.3_ICLoRA_HDR_Distilled.json) for a single-stage pass, or [LTX-2.5_V2V_TiledFusion_SDR_to_HDR.json](./LTX-2.5_V2V_TiledFusion_SDR_to_HDR.json) for the tiled 4K/8K ladder. `LoadVideo` → `LTXVSDRToHDRWorkingSpace` (`srgb_gamma`) → HDR IC-LoRA guide → float32 VAE decode → `LTXVHDRDecodePostprocess` (`transfer=acescct`, EXR=`acescct`) → HLG. Sampler **euler**; original audio frozen/muxed. Same idea as pipelines `hdr_ic_lora --text-embeddings`.
SDR→HDR IC-LoRA (separate from native EXR HDR): [LTX-2.5_V2V_TiledFusion_SDR_to_HDR.json](./LTX-2.5_V2V_TiledFusion_SDR_to_HDR.json) (tiled 4K/8K ladder): `LoadVideo` → Convert Image Color Space (`sRGB` → `HDR ACEScct`) → HDR IC-LoRA guide → float32 VAE decode → EXR via `LTXVHDRDecodePostprocess` (`transfer=acescct`, EXR=`acescg`); HLG via Convert Image Color Space (`HDR ACEScct` → `HDR`) → Create Video (`HDR`) → Save Video. Sampler **euler**; original audio frozen/muxed. Same idea as pipelines `hdr_ic_lora --text-embeddings`. For a single-stage pass, [LTX-2.3_ICLoRA_HDR_Distilled.json](../2.3/LTX-2.3_ICLoRA_HDR_Distilled.json) is the older LogC3 graph: `LTXVHDRDecodePostprocess` (`transfer=logc3`) writes a linear EXR, without the core HDR nodes.
For native HDR, set **`img_compression = 0`** (Python `--hdr` EXR conditioning skips JPEG/CRF; CRF on ACEScct darkens highlights). Turn **prompt enhancer off** when matching goldens. I2V stage-2 distilled sigmas should be `0.909375, 0.725, 0.421875, 0.0` (not `0.85, …`). Inpaint keeps its own 2-step stage-2 schedule.
HDR graphs live under [`HDR_workflows/`](./HDR_workflows/).
HDR graphs live under [`HDR_workflows/`](./HDR_workflows/). They use core Convert Image Color Space and HDR Create Video / Save Video, so they need ComfyUI v0.38.0 or newer.
Native HDR I/O: `LTXVLoadEXRSequence` → float32 VAE → `LTXVHDRDecodePostprocess` (`transfer=acescct`, optional EXR) → `LTXVSaveHLG` from `hdr_linear`. Same idea as pipelines `--hdr` on Distilled / IC-LoRA.
Native HDR I/O: `LTXVLoadEXRSequence` → float32 VAE → EXR via `LTXVHDRDecodePostprocess` (`transfer=acescct`, EXR=`acescg`); HLG via Convert Image Color Space (`HDR ACEScct` → `HDR`) → Create Video (`HDR`) → Save Video. Same idea as pipelines `--hdr` on Distilled / IC-LoRA.
SDR→HDR IC-LoRA (separate from native EXR HDR): [LTX-2.5_ICLoRA_SDR_to_HDR_Distilled.json](./HDR_workflows/LTX-2.5_ICLoRA_SDR_to_HDR_Distilled.json) — `LoadVideo` → `LTXVSDRToHDRWorkingSpace` (`srgb_gamma`) → `Resize Image/Mask` (scale to multiple 32) → **fixed scene embeddings** (`LTXVLoadConditioning`, not a free-text prompt) → HDR IC-LoRA guide → float32 VAE decode → `LTXVHDRDecodePostprocess` (`transfer=acescct`, EXR=`acescg`) → HLG. Sampler **euler**; original audio frozen/muxed. Same idea as pipelines `hdr_ic_lora --text-embeddings`. Conditioning fps snaps to 60 when source fps is above 30 (playback fps unchanged for decode/export).
SDR→HDR IC-LoRA (separate from native EXR HDR): [LTX-2.5_ICLoRA_SDR_to_HDR_Distilled.json](./HDR_workflows/LTX-2.5_ICLoRA_SDR_to_HDR_Distilled.json) — `LoadVideo` → Convert Image Color Space (`sRGB` → `HDR ACEScct`) → `Resize Image/Mask` (scale to multiple 32) → **fixed scene embeddings** (`LTXVLoadConditioning`, not a free-text prompt) → HDR IC-LoRA guide → float32 VAE decode → EXR via `LTXVHDRDecodePostprocess` (`transfer=acescct`, EXR=`acescg`); HLG via Convert Image Color Space (`HDR ACEScct` → `HDR`) → Create Video (`HDR`) → Save Video. Sampler **euler**; original audio frozen/muxed. Same idea as pipelines `hdr_ic_lora --text-embeddings`. Conditioning fps snaps to 60 when source fps is above 30 (playback fps unchanged for decode/export).
For native HDR, set **`img_compression = 0`** (Python `--hdr` EXR conditioning skips JPEG/CRF; CRF on ACEScct darkens highlights). Turn **prompt enhancer off** when matching goldens. I2V stage-2 distilled sigmas should be `0.909375, 0.725, 0.421875, 0.0` (not `0.85, …`). Inpaint keeps its own 2-step stage-2 schedule.