Add H3 prompt curator

README.md

@@ -56,6 +56,13 @@
   - Output: `prompt`
   - Builds one H3 prompt block per beat, with quick controls for per-shot timing, continuity, ref behavior, anchor additions, soundscape, and music while staying compatible with direct text editing.
 
+- `Dumas H3 Prompt Curator`
+  - Inputs: `action_prompt`, `anatomy_guard`, optional `anchor`, optional `soundscape`, optional `ref_1` through `ref_9`
+  - Outputs: `prompt`, `ref_image_1` through `ref_image_9`, `reference_count`, `debug`
+  - Builds one standalone MiniMax H3 prompt from your final action text plus structured character/location references.
+  - The action text can mention references by character/location name, alias, `<Picture N>`, or `<refN>`. Only mentioned references are emitted, and the output images are compacted/renumbered so skipped inputs do not leave gaps.
+  - Adds curated reference context, optional anatomy guard text, anchor/style text, and `overall_soundscape:` text while respecting MiniMax H3's reference-generation shape: one prompt plus up to nine reference images.
+
 - `Dumas H3 Shot Length`
   - Inputs: `shot_seconds`, `fps`, optional `cap_to_h3_max`
   - Outputs: `seconds`, `frames`, `info`
@@ -76,6 +83,16 @@
   - Output: `reference`
   - Builds one structured `REFERENCE` object for a location/environment so H3 can use the same socket type for both character and scenic refs.
 
+- `Dumas Character Helper`
+  - Inputs: `image1`, `image2`, picture IDs, character identity fields, `general`, `wardrobe`
+  - Outputs: `image1`, `image2`, `reference_prompt`, `wardrobe`
+  - Restores the original general-purpose helper shape: pass two images through unchanged and emit prompt text/wardrobe text for manual wiring.
+
+- `Dumas Location Helper`
+  - Inputs: `image1`, `image2`, picture IDs, `location_id`, `name`, `alias`, `description`, `general`
+  - Outputs: `image1`, `image2`, `reference_prompt`
+  - Matching general-purpose helper for environments/locations: pass two images through unchanged and emit location reference prompt text.
+
 - `Dumas Anchor Style`
   - Inputs: `anchor_style`, `style_description`
   - Output: `anchor`
@@ -83,6 +100,11 @@
   - The preset wording is tuned for H3-safe persistent anchors: camera language, lighting, texture, production treatment, and tone, without naming characters or describing one-off actions.
   - Selecting a preset fills the editable description field, and the edited multiline description is the `STRING` value passed downstream into H3 anchor sockets such as `anchor_override`.
 
+- `Dumas Soundscape Helper`
+  - Inputs: `soundscape`, `soundscape_description`
+  - Output: `soundscape`
+  - Matching soundscape helper for standalone H3 prompts. Pick a preset such as quiet interior, rainy street, cafe, city night, forest, industrial, or silent, then edit the text that flows into `Dumas H3 Prompt Curator`.
+
 - `Dumas JSON String to Object`
   - Input: `json_string`
   - Output: parsed `JSON`
@@ -239,7 +261,7 @@ decr  -> use index - 1
 
 `Dumas H3 Plan Attach Scene Images` and `Dumas H3 Plan Extract Scene Images` are a companion pair for `ComfyUI-MiniMaxH3-Contex-Loop` and the local `ref2v` lane. The upstream H3 plan node cannot dynamically grow nine new image sockets for every JSON-defined scene, so Dumas stores scene image bindings beside the plan using a lightweight token and an in-memory registry. That keeps `plan.json` archiving intact while still letting you wire up nine IMAGE sockets per scene through chained helper nodes.
 
-`Dumas Character Reference` and `Dumas Location Reference` live in `Dumas/MiniMax`. Both output a structured `REFERENCE` object that carries the image plus its semantic payload. `Dumas H3 Long Videos` accepts those `REFERENCE` sockets directly on `ref_1`..`ref_9`, resolves `<Picture N>` against the wired slot positions, and can also pull character wardrobe context from the structured ref data when `character_memory` is left blank.
+`Dumas Character Helper` is the restored two-image/text helper for general H3 workflows, and `Dumas Location Helper` mirrors it for scene/environment references. The structured `Dumas Character Reference` and `Dumas Location Reference` nodes remain available separately for workflows that want a single `REFERENCE` socket. `Dumas H3 Prompt Curator` consumes those structured references, assigns the final `<Picture N>` numbering, and outputs only the compacted images the prompt actually mentions.
 
 `Dumas Strip Iteration Suffix` keeps the part before the first underscore and drops the rest. Names like `char123_pose_final.png` become `char123.png`, while names with no underscore such as `char123.png` are left untouched.
 

dumas_h3_latent_upscale.py

@@ -1,6 +1,8 @@
+from contextlib import contextmanager
 from functools import lru_cache
 import gc
 import glob
+import logging
 import math
 import os
 import re
@@ -40,9 +42,12 @@ LATENTS_STD = [
 ]
 
 _LATENT_UPSCALE_FOLDER = "latent_upscale_models"
+LOGGER = logging.getLogger(__name__)
 MP_UNIT = 1024 * 1024
 RES_MULTIPLE = 32
 CUDA_MODEL_CHUNK_LENGTH = 17
+CUDA_MODEL_MIN_TOTAL_VRAM_BYTES = 10 * 1024 * 1024 * 1024
+_MODEL_HOLD_DEPTH = 0
 
 
 def _uses_cuda_model_upscale(param):
@@ -53,15 +58,83 @@ def _uses_cuda_model_upscale(param):
     return device == "cuda" and (mode == "model" or has_model_name)
 
 
-def _effective_temporal_params(param):
+def _effective_temporal_params(param, frame_count=None):
     chunk_length = int(param.get("chunk_length", 0) or 0)
     temporal_overlap = int(param.get("temporal_overlap", 0) or 0)
     if _uses_cuda_model_upscale(param):
-        chunk_length = CUDA_MODEL_CHUNK_LENGTH if chunk_length <= 0 else min(chunk_length, CUDA_MODEL_CHUNK_LENGTH)
+        if chunk_length <= 0:
-        temporal_overlap = min(max(0, temporal_overlap), max(0, chunk_length - 17))
+            chunk_length = 85
+            temporal_overlap = 17
     return chunk_length, temporal_overlap
 
 
+def _is_oom_error(exc):
+    text = str(exc).lower()
+    return "out of memory" in text or "exhausted its gpu spatial fallbacks" in text
+
+
+def _should_retry_temporal_before_spatial(param):
+    return _uses_cuda_model_upscale(param) and int(param.get("chunk_length", 0) or 0) > CUDA_MODEL_CHUNK_LENGTH
+
+
+def _cuda_total_memory_bytes():
+    try:
+        if not torch.cuda.is_available():
+            return 0
+        if hasattr(torch.cuda, "mem_get_info"):
+            _free, total = torch.cuda.mem_get_info()
+            return int(total)
+        current_device = torch.cuda.current_device() if hasattr(torch.cuda, "current_device") else 0
+        props = torch.cuda.get_device_properties(current_device)
+        return int(getattr(props, "total_memory", 0) or 0)
+    except Exception:
+        return 0
+
+
+def _should_skip_cuda_model_upscale(param):
+    total = _cuda_total_memory_bytes()
+    return _uses_cuda_model_upscale(param) and 0 < total < CUDA_MODEL_MIN_TOTAL_VRAM_BYTES
+
+
+def _fallback_to_interp(video, param, reason):
+    method = param.get("method", "bilinear")
+    LOGGER.warning("H3 latent upscale model %s; using %s interpolation instead", reason, method)
+    try:
+        gc.collect()
+    except Exception:
+        pass
+    if torch.cuda.is_available():
+        try:
+            torch.cuda.empty_cache()
+        except Exception:
+            pass
+    interp_param = dict(param)
+    interp_param["mode"] = "interp"
+    return upscale_video_interp(video, interp_param)
+
+
+def _retry_with_smaller_temporal(video, param, upscaler, exc):
+    if not _is_oom_error(exc):
+        raise exc
+    smaller = _shrink_temporal_param(param)
+    if smaller is None:
+        raise exc
+    LOGGER.info(
+        "H3 latent upscale temporal OOM: retrying with chunk_length=%s overlap=%s",
+        smaller.get("chunk_length"), smaller.get("temporal_overlap"),
+    )
+    try:
+        gc.collect()
+    except Exception:
+        pass
+    if torch.cuda.is_available():
+        try:
+            torch.cuda.empty_cache()
+        except Exception:
+            pass
+    return _upscale_video_temporal_chunks(video, smaller, upscaler)
+
+
 def _models_dir():
     try:
         if _LATENT_UPSCALE_FOLDER not in folder_paths.folder_names_and_paths:
@@ -349,7 +422,7 @@ def load_upscale_model(name, device, precision):
     return model
 
 
-def unload_upscale_model(name, device, precision):
+def _unload_upscale_model_now(name, device, precision):
     cache_key = f"{name}::{device}::{precision}"
     model = _MODEL_CACHE.get(cache_key)
     if model is not None and str(next(model.parameters()).device) != "cpu":
@@ -361,6 +434,22 @@ def unload_upscale_model(name, device, precision):
             pass
 
 
+def unload_upscale_model(name, device, precision):
+    if _MODEL_HOLD_DEPTH > 0:
+        return
+    _unload_upscale_model_now(name, device, precision)
+
+
+@contextmanager
+def _hold_upscale_model_loaded():
+    global _MODEL_HOLD_DEPTH
+    _MODEL_HOLD_DEPTH += 1
+    try:
+        yield
+    finally:
+        _MODEL_HOLD_DEPTH -= 1
+
+
 def _compute_upscale_target(width, height, h_in, w_in):
     ds = 16
     w_px = float(width)
@@ -617,12 +706,25 @@ def upscale_video_model(video, param):
     except RuntimeError as exc:
         if "out of memory" not in str(exc).lower():
             raise
+        if _should_retry_temporal_before_spatial(param):
+            raise RuntimeError(
+                "out of memory: retry H3 latent upscale with a smaller temporal chunk "
+                "before spatial fallback"
+            ) from exc
         smaller = _shrink_model_tile_param(param)
         if smaller is None:
             raise RuntimeError(
                 "H3 latent upscale exhausted its GPU spatial fallbacks. "
                 "Reduce the target size, tile size, or split the shot earlier."
             ) from exc
+        LOGGER.info(
+            "H3 latent upscale model OOM: retrying with tile_size_mode=%s rows=%s cols=%s tile=%sx%s",
+            smaller.get("tile_size_mode"),
+            smaller.get("grid_rows"),
+            smaller.get("grid_cols"),
+            smaller.get("tile_width"),
+            smaller.get("tile_height"),
+        )
         try:
             gc.collect()
         except Exception:
@@ -683,12 +785,22 @@ def _upscale_video_model_tiled(video, param):
     # If the requested tile is not smaller than the target on either axis,
     # the tiled path would just duplicate work.
     if len(rows) == 1 and len(cols) == 1:
+        LOGGER.info(
+            "H3 latent upscale model: single core pass, tokens=%s target=%sx%s",
+            int(video.shape[2]), w_out, h_out,
+        )
         return _upscale_video_model_core(video, param)
 
     scale_h = h_out / float(h_in)
     scale_w = w_out / float(w_in)
     orig_dtype = video.dtype
     out = torch.zeros((video.shape[0], video.shape[1], video.shape[2], h_out, w_out), device="cpu", dtype=orig_dtype)
+    LOGGER.info(
+        "H3 latent upscale model: %s spatial tiles, tokens=%s target=%sx%s tile_mode=%s tile=%sx%s overlap=%sx%s",
+        len(rows) * len(cols), int(video.shape[2]), w_out, h_out, mode, tile_w, tile_h,
+        spatial_w_overlap if mode == "rows_cols" else overlap,
+        spatial_h_overlap if mode == "rows_cols" else overlap,
+    )
 
     for i, r0 in enumerate(rows):
         tr = trows[i]
@@ -753,43 +865,51 @@ def upscale_video_interp(video, param):
 def _upscale_video_temporal_chunks(video, param, upscaler):
     if video.device.type != "cpu":
         video = video.to(device="cpu", copy=True)
-    chunk_length, temporal_overlap = _effective_temporal_params(param)
+    t = int(video.shape[2])
+    frame_count = _frames_for_tokens(t)
+    chunk_length, temporal_overlap = _effective_temporal_params(param, frame_count)
     chunk_param = dict(param)
     chunk_param["chunk_length"] = chunk_length
     chunk_param["temporal_overlap"] = temporal_overlap
     anchor_strength = float(param.get("anchor_strength", 0.999) or 0.999)
-    t = int(video.shape[2])
-    frame_count = _frames_for_tokens(t)
     if chunk_length <= 0 or frame_count <= chunk_length:
-        return upscaler(video, chunk_param)
+        LOGGER.info(
+            "H3 latent upscale: single temporal chunk, tokens=%s frames=%s chunk_length=%s overlap=%s",
+            t, frame_count, chunk_length, temporal_overlap,
+        )
+        try:
+            return upscaler(video, chunk_param)
+        except RuntimeError as exc:
+            return _retry_with_smaller_temporal(video, chunk_param, upscaler, exc)
 
     bounds = _temporal_segments(t, chunk_length, temporal_overlap)
     if len(bounds) <= 1:
-        return upscaler(video, chunk_param)
+        LOGGER.info(
+            "H3 latent upscale: single temporal segment, tokens=%s frames=%s chunk_length=%s overlap=%s",
+            t, frame_count, chunk_length, temporal_overlap,
+        )
+        try:
+            return upscaler(video, chunk_param)
+        except RuntimeError as exc:
+            return _retry_with_smaller_temporal(video, chunk_param, upscaler, exc)
 
     orig_dtype = video.dtype
     out = None
     out_h = out_w = None
+    LOGGER.info(
+        "H3 latent upscale: %s temporal chunks, tokens=%s frames=%s chunk_length=%s overlap=%s",
+        len(bounds), t, frame_count, chunk_length, temporal_overlap,
+    )
     for i, (k0, f0, k1, f1) in enumerate(bounds):
         chunk = video[:, :, k0:k1].contiguous()
+        LOGGER.info(
+            "H3 latent upscale: temporal chunk %s/%s tokens %s:%s frames %s:%s",
+            i + 1, len(bounds), k0, k1, f0, f1,
+        )
         try:
             chunk_out, chunk_h, chunk_w = upscaler(chunk, chunk_param)
         except RuntimeError as exc:
-            if "out of memory" not in str(exc).lower():
+            return _retry_with_smaller_temporal(video, chunk_param, upscaler, exc)
-                raise
-            smaller = _shrink_temporal_param(chunk_param)
-            if smaller is None:
-                raise
-            try:
-                gc.collect()
-            except Exception:
-                pass
-            if torch.cuda.is_available():
-                try:
-                    torch.cuda.empty_cache()
-                except Exception:
-                    pass
-            return _upscale_video_temporal_chunks(video, smaller, upscaler)
         chunk_out = chunk_out.to(device="cpu", dtype=orig_dtype)
         if out is None:
             out_h, out_w = chunk_h, chunk_w
@@ -819,7 +939,22 @@ def upscale_latent_video(video, param):
     if mode == "off":
         return video, video.shape[-2], video.shape[-1]
     if mode == "model":
-        return _upscale_video_temporal_chunks(video, param, upscale_video_model)
+        if _should_skip_cuda_model_upscale(param):
+            return _fallback_to_interp(video, param, "requires more than this card's VRAM")
+        model_name = param.get("model_name")
+        device = param.get("device", "cuda")
+        precision = param.get("precision", "fp16")
+        dev = torch.device(device if (device == "cpu" or torch.cuda.is_available()) else "cpu")
+        try:
+            with _hold_upscale_model_loaded():
+                try:
+                    return _upscale_video_temporal_chunks(video, param, upscale_video_model)
+                finally:
+                    _unload_upscale_model_now(model_name, dev, precision)
+        except RuntimeError as exc:
+            if not _is_oom_error(exc):
+                raise
+            return _fallback_to_interp(video, param, "exhausted GPU memory")
     return _upscale_video_temporal_chunks(video, param, upscale_video_interp)
 
 
@@ -892,10 +1027,10 @@ class H3LatentUpscaleParams:
                     "tooltip": "Temporal fade schedule over each tile's sampling. Off keeps the fade fixed; narrowing shrinks it over steps; widening grows it over steps."}),
                 "dynamic_fade_min": ("INT", {"default": 32, "min": 0, "max": 4096, "step": 32,
                     "tooltip": "Minimum fade width used by dynamic_fade when it is enabled."}),
-                "chunk_length": ("INT", {"default": 17, "min": 17, "max": 100000, "step": 17,
+                "chunk_length": ("INT", {"default": 85, "min": 17, "max": 100000, "step": 17,
-                    "tooltip": "Temporal chunk length for latent upscale. CUDA model upscale is capped to 17 internally so short long-video shots do not bypass splitting and OOM."}),
+                    "tooltip": "Temporal chunk length for latent upscale. CUDA model upscale keeps this when it splits the shot, but uses 17/0 if this would otherwise process the whole shot as one OOM-prone batch."}),
-                "temporal_overlap": ("INT", {"default": 0, "min": 0, "max": 100000, "step": 17,
+                "temporal_overlap": ("INT", {"default": 17, "min": 0, "max": 100000, "step": 17,
-                    "tooltip": "Temporal overlap between latent chunks. CUDA model upscale uses 0 when capped to one H3 block to minimize peak VRAM."}),
+                    "tooltip": "Temporal overlap between latent chunks. 17 matches the upstream split example; CUDA model upscale drops overlap only for the emergency 17-frame guard path."}),
                 "resize_conditioning": ("BOOLEAN", {"default": False,
                     "tooltip": "Reserved for upstream split compatibility. Leave OFF unless you need the original fallback behavior."}),
                 "anchor_strength": ("FLOAT", {"default": 0.999, "min": 0.0, "max": 1.0, "step": 0.01,

dumas_h3_longvideos.py

@@ -4040,6 +4040,88 @@ def _copy_sample_latent(out_latent):
         return None
 
 
+def _retarget_conditioning_spatial(cond, latent_h, latent_w):
+    """Resize H3 keyframe latents in existing conditioning to a new latent grid."""
+    latent_h = int(latent_h)
+    latent_w = int(latent_w)
+    if latent_h <= 0 or latent_w <= 0:
+        raise RuntimeError("conditioning target latent size must be positive")
+    out = []
+    for item in cond:
+        try:
+            tensor, data = item
+        except Exception:
+            out.append(item)
+            continue
+        nd = dict(data)
+        keyframes = nd.get("minimax_keyframes")
+        if keyframes:
+            resized_keyframes = []
+            for keyframe in keyframes:
+                nkf = dict(keyframe)
+                latent_value = nkf.get("latent")
+                if latent_value is not None and len(getattr(latent_value, "shape", ())) >= 5:
+                    if latent_value.shape[3] != latent_h or latent_value.shape[4] != latent_w:
+                        b, c, t, h, w = latent_value.shape
+                        resized = torch.nn.functional.interpolate(
+                            latent_value.to(torch.float32).reshape(b * t, c, h, w),
+                            size=(latent_h, latent_w),
+                            mode="bilinear",
+                            align_corners=False,
+                        ).reshape(b, c, t, latent_h, latent_w)
+                        nkf["latent"] = resized.to(device=latent_value.device, dtype=latent_value.dtype)
+                resized_keyframes.append(nkf)
+            nd["minimax_keyframes"] = resized_keyframes
+        out.append([tensor, nd])
+    return out
+
+
+def _pad_to_h3_patch_size(tensor):
+    try:
+        import comfy.ldm.common_dit as common_dit
+        return common_dit.pad_to_patch_size(tensor, (1, 2, 2))
+    except Exception:
+        return tensor
+
+
+def _crop_conditioning_to_tile(cond, source_h, source_w, row, col, tile_h, tile_w):
+    """Crop H3 keyframe latents in existing conditioning for a spatial tile."""
+    out = []
+    for item in cond:
+        try:
+            tensor, data = item
+        except Exception:
+            out.append(item)
+            continue
+        nd = dict(data)
+        keyframes = nd.get("minimax_keyframes")
+        if keyframes:
+            cropped_keyframes = []
+            for keyframe in keyframes:
+                nkf = dict(keyframe)
+                latent_value = nkf.get("latent")
+                if latent_value is not None and len(getattr(latent_value, "shape", ())) >= 5:
+                    kh, kw = latent_value.shape[3], latent_value.shape[4]
+                    if kh != source_h or kw != source_w:
+                        b, c, t, h, w = latent_value.shape
+                        latent_value = torch.nn.functional.interpolate(
+                            latent_value.to(torch.float32).reshape(b * t, c, h, w),
+                            size=(source_h, source_w),
+                            mode="bilinear",
+                            align_corners=False,
+                        ).reshape(b, c, t, source_h, source_w).to(
+                            device=latent_value.device,
+                            dtype=latent_value.dtype,
+                        )
+                    nkf["latent"] = _pad_to_h3_patch_size(
+                        latent_value[:, :, :, row:row + tile_h, col:col + tile_w].contiguous()
+                    )
+                cropped_keyframes.append(nkf)
+            nd["minimax_keyframes"] = cropped_keyframes
+        out.append([tensor, nd])
+    return out
+
+
 def _latent_with_replaced_samples(template_latent, sampled_latent):
     """Reuse the original latent payload, but swap in freshly sampled tensors."""
     if not isinstance(template_latent, dict):
@@ -6693,18 +6775,22 @@ class H3LongVideos:
                 # pass; otherwise the 12-step base latent and the upscale latent sit
                 # in memory together and can trigger a retry loop.
                 out["samples"] = comfy.nested_tensor.NestedTensor((upscaled_video, full_audio))
-                del out_samples, positive, latent, parts
+                del out_samples, parts
                 mm.soft_empty_cache()
                 target_w = int(up_w) * 16
                 target_h = int(up_h) * 16
                 if target_w <= 0 or target_h <= 0:
                     raise RuntimeError("latent upscale target size must be positive")
-                upscale_cond, upscale_latent = _build_shot_conditioning(
+                try:
-                    clip, vae, prompt, target_w, target_h, ln, fps, handoff,
+                    upscale_cond = _retarget_conditioning_spatial(positive, int(up_h), int(up_w))
-                    ref_images=refs, ref_image_size=ref_image_size,
+                    upscale_latent = dict(latent) if isinstance(latent, dict) else {}
-                    ref_noise_aug=ref_noise_aug, audio_vae=audio_vae, silent=silent)
+                except Exception:
-                upscale_latent["samples"] = comfy.nested_tensor.NestedTensor(
+                    upscale_cond, upscale_latent = _build_shot_conditioning(
-                    (upscaled_video, full_audio))
+                        clip, vae, prompt, target_w, target_h, ln, fps, handoff,
+                        ref_images=refs, ref_image_size=ref_image_size,
+                        ref_noise_aug=ref_noise_aug, audio_vae=audio_vae, silent=silent)
+                upscale_latent["samples"] = comfy.nested_tensor.NestedTensor((upscaled_video, full_audio))
+                del positive, latent
                 refine_steps = int(latent_upscale_param.get("steps", 2) or 2)
                 refine_sampler = latent_upscale_param.get("sampler_name", sn)
                 refine_scheduler = latent_upscale_param.get("scheduler", sch)
@@ -6771,6 +6857,11 @@ class H3LongVideos:
                 rows, cols, trows, tcols, row_ovl, col_ovl = compute_spatial_grid(
                     int(up_h), int(up_w), tile_th, tile_tw, ol_th, ol_tw, min_tile_tw, min_tile_tw
                 )
+                logging.info(
+                    "H3 latent refine: %s spatial sampler tiles, target=%sx%s tile_mode=%s tile=%sx%s overlap=%sx%s",
+                    len(rows) * len(cols), target_w, target_h, tile_size_mode, tile_w_px, tile_h_px,
+                    spatial_w_overlap_px, spatial_h_overlap_px,
+                )
                 if len(rows) == 1 and len(cols) == 1:
                     (refined_out,) = nodes.common_ksampler(
                         model, seed, refine_steps, cfg, refine_sampler, refine_scheduler, upscale_cond, negative, upscale_latent,
@@ -6783,12 +6874,10 @@ class H3LongVideos:
                         for col_index, c0 in enumerate(cols):
                             tc = tcols[col_index]
                             ovw = col_ovl[col_index]
-                            tile_target_w = int(tc) * 16
+                            tile_cond = _crop_conditioning_to_tile(
-                            tile_target_h = int(tr) * 16
+                                upscale_cond, int(up_h), int(up_w), r0, c0, tr, tc
-                            tile_cond, tile_latent = _build_shot_conditioning(
+                            )
-                                clip, vae, prompt, tile_target_w, tile_target_h, ln, fps, handoff,
+                            tile_latent = dict(upscale_latent) if isinstance(upscale_latent, dict) else {}
-                                ref_images=refs, ref_image_size=ref_image_size,
-                                ref_noise_aug=ref_noise_aug, audio_vae=audio_vae, silent=silent)
                             tile_video = upscaled_video[:, :, :, r0:r0 + tr, c0:c0 + tc].contiguous()
                             tr_s = tr + (tr % 2)
                             tc_s = tc + (tc % 2)

dumas_image_nodes.py

@@ -27,6 +27,15 @@ _H3_PLAN_IMAGE_BINDINGS_CAP = 128
 _H3_PLAN_IMAGE_SLOTS = 9
 _FOLDER_IMAGE_EXTS = (".png", ".jpg", ".jpeg", ".webp", ".bmp", ".gif", ".tiff", ".tif")
 _ANCHOR_STYLE_H3_NOTE = ""
+_H3_PROMPT_REF_SLOTS = 9
+_H3_PROMPT_MAX_CHARS = 7000
+_PICTURE_TAG_RE = re.compile(r"<\s*picture[\s_\-]*(\d+)\s*>", re.I)
+_REF_TAG_RE = re.compile(r"<\s*ref[\s_\-]*(\d+)\s*>", re.I)
+_ANATOMY_GUARD_TEXT = (
+    "Each person has one head, two arms, two hands with five fingers on each hand, "
+    "and two legs with two feet. Limbs stay attached to the correct body and move "
+    "only with the person they belong to."
+)
 _ANCHOR_STYLE_PRESETS = OrderedDict(
     [
         (
@@ -346,6 +355,47 @@ _ANCHOR_STYLE_PRESETS = OrderedDict(
         ),
     ]
 )
+_SOUNDSCAPE_PRESETS = OrderedDict(
+    [
+        (
+            "quiet interior",
+            "quiet indoor room tone, faint ventilation and distant household ambience",
+        ),
+        (
+            "rainy street",
+            "steady rain, wet pavement, distant traffic hum",
+        ),
+        (
+            "cafe",
+            "low room tone, faint glassware, cutlery, and muted conversation",
+        ),
+        (
+            "city night",
+            "distant traffic hum, occasional horn, night air",
+        ),
+        (
+            "forest",
+            "wind in leaves, distant birds, soft natural ambience",
+        ),
+        (
+            "industrial",
+            "large interior reverb, distant metal ticks, low machine hum",
+        ),
+        (
+            "silent",
+            "no dialogue, no vocals, only the natural ambient bed of the scene",
+        ),
+        ("custom", ""),
+    ]
+)
+
+
+def _soundscape_options():
+    return list(_SOUNDSCAPE_PRESETS.keys())
+
+
+def _soundscape_description(soundscape_name):
+    return _SOUNDSCAPE_PRESETS.get(soundscape_name, "")
 _LOAD_IMAGES_FOLDER_DEFAULT_STATE = {
     "version": 1,
     "folder": "",
@@ -920,6 +970,206 @@ def normalize_reference(value, picture_id=None, allow_image_fallback=True):
     )
 
 
+def _reference_text(value):
+    return " ".join(str(value or "").split()).strip()
+
+
+def _reference_sentence(value):
+    text = _reference_text(value)
+    if text and text[-1] not in ".!?":
+        text += "."
+    return text
+
+
+def _reference_name_keys(ref):
+    names = []
+    for key in ("name", "id"):
+        value = _reference_text(ref.get(key))
+        if value:
+            names.append(value)
+    for alias in ref.get("aliases") or []:
+        value = _reference_text(alias)
+        if value:
+            names.append(value)
+    seen = set()
+    out = []
+    for name in names:
+        key = name.lower()
+        if key in seen:
+            continue
+        seen.add(key)
+        out.append(name)
+    return out
+
+
+def _reference_image(ref):
+    if not isinstance(ref, dict):
+        return None
+    return ref.get("image")
+
+
+def _normalize_prompt_refs(raw_refs):
+    refs = []
+    for slot_number, raw in enumerate(raw_refs or (), 1):
+        if raw is None:
+            refs.append(None)
+            continue
+        try:
+            ref = normalize_reference(raw, picture_id=slot_number, allow_image_fallback=False)
+        except Exception:
+            refs.append(None)
+            continue
+        if _reference_image(ref) is None:
+            refs.append(None)
+        else:
+            refs.append(ref)
+    return refs
+
+
+def _explicit_reference_tags(text):
+    return sorted(
+        {
+            int(match.group(1))
+            for pattern in (_PICTURE_TAG_RE, _REF_TAG_RE)
+            for match in pattern.finditer(text or "")
+        }
+    )
+
+
+def _name_matches_reference(text, ref):
+    haystack = str(text or "")
+    for name in _reference_name_keys(ref):
+        if re.search(r"\b" + re.escape(name) + r"\b", haystack, re.I):
+            return True
+    return False
+
+
+def _selected_prompt_refs(action_prompt, refs):
+    selected = []
+    seen_slots = set()
+    for slot_number in _explicit_reference_tags(action_prompt):
+        if not (1 <= slot_number <= len(refs)):
+            continue
+        ref = refs[slot_number - 1]
+        if ref is None:
+            continue
+        selected.append((slot_number, ref))
+        seen_slots.add(slot_number)
+    for slot_number, ref in enumerate(refs, 1):
+        if slot_number in seen_slots or ref is None:
+            continue
+        if _name_matches_reference(action_prompt, ref):
+            selected.append((slot_number, ref))
+            seen_slots.add(slot_number)
+    return selected
+
+
+def _replace_reference_tags(text, picture_map):
+    def repl(match):
+        original = int(match.group(1))
+        compacted = picture_map.get(original)
+        if compacted is None:
+            return ""
+        return f"<Picture {compacted}>"
+
+    rewritten = _PICTURE_TAG_RE.sub(repl, str(text or ""))
+    rewritten = _REF_TAG_RE.sub(repl, rewritten)
+    return re.sub(r"[ \t]{2,}", " ", rewritten).strip()
+
+
+def _reference_fact_sentence(ref, label):
+    if ref.get("kind") != "character":
+        return ""
+    facts = dict(ref.get("facts") or {})
+    bits = []
+    aliases = [_reference_text(alias) for alias in (ref.get("aliases") or []) if _reference_text(alias)]
+    if aliases:
+        bits.append(f"also known as {aliases[0]}")
+    for key in ("gender", "nationality", "occupation"):
+        value = _reference_text(facts.get(key))
+        if value:
+            bits.append(value if key != "occupation" else f"works as {value}")
+    age = _parse_positive_int(facts.get("age"))
+    if age is not None:
+        bits.append(f"{age} years old")
+    feet = _reference_text(facts.get("height_feet"))
+    inches = _reference_text(facts.get("height_inches"))
+    if feet and inches:
+        bits.append(f"{feet} foot {inches} tall")
+    elif feet:
+        bits.append(f"{feet} foot tall")
+    accent = _reference_text(facts.get("accent"))
+    if accent:
+        bits.append(f"speaks with a {accent} accent")
+    if not bits:
+        return ""
+    return f"Character facts for {label}: " + ", ".join(bits) + "."
+
+
+def _reference_context(ref, compact_picture_number):
+    label_name = _reference_text(ref.get("name")) or _reference_text(ref.get("id")) or "this reference"
+    label = f"<Picture {compact_picture_number}> {label_name}"
+    parts = [_reference_sentence(_reference_summary(ref.get("kind"), label_name, compact_picture_number))]
+    description = _reference_sentence(ref.get("description"))
+    wardrobe = _reference_sentence(ref.get("wardrobe"))
+    general = _reference_sentence(ref.get("general"))
+    facts = _reference_fact_sentence(ref, label)
+    if ref.get("kind") == "location":
+        if description:
+            parts.append(f"Location context for {label}: {description}")
+        if general:
+            parts.append(f"Location notes for {label}: {general}")
+    else:
+        if facts:
+            parts.append(facts)
+        if description:
+            parts.append(f"Persistent appearance for {label}: {description}")
+        if wardrobe:
+            parts.append(f"Persistent wardrobe/style for {label}: {wardrobe}")
+        if general:
+            parts.append(f"Character notes for {label}: {general}")
+    return " ".join(part for part in parts if part).strip()
+
+
+def _append_prompt_section(parts, label, text):
+    clean = _reference_text(text)
+    if clean:
+        parts.append(f"{label}: {clean}")
+
+
+def curate_h3_prompt(action_prompt, anchor="", soundscape="", refs=(), anatomy_guard="auto"):
+    normalized_refs = _normalize_prompt_refs(refs)
+    selected = _selected_prompt_refs(action_prompt, normalized_refs)
+    picture_map = {slot_number: index for index, (slot_number, _ref) in enumerate(selected, 1)}
+    action = _replace_reference_tags(action_prompt, picture_map)
+
+    prompt_parts = []
+    _append_prompt_section(prompt_parts, "Scene anchor", anchor)
+    if selected:
+        contexts = [_reference_context(ref, picture_number) for picture_number, (_slot, ref) in enumerate(selected, 1)]
+        _append_prompt_section(prompt_parts, "Reference context", " ".join(contexts))
+    _append_prompt_section(prompt_parts, "Action", action)
+    if anatomy_guard == "on" or (anatomy_guard == "auto" and any(ref.get("kind") == "character" for _slot, ref in selected)):
+        _append_prompt_section(prompt_parts, "Anatomy guard", _ANATOMY_GUARD_TEXT)
+    _append_prompt_section(prompt_parts, "overall_soundscape", soundscape)
+
+    prompt = "\n\n".join(prompt_parts).strip()
+    if len(prompt) > _H3_PROMPT_MAX_CHARS:
+        prompt = prompt[: _H3_PROMPT_MAX_CHARS - 3].rstrip() + "..."
+    images = [_reference_image(ref) for _slot, ref in selected]
+    images.extend([None] * (_H3_PROMPT_REF_SLOTS - len(images)))
+    debug = (
+        f"Selected {len(selected)} reference(s): "
+        + ", ".join(
+            f"input {slot}-><Picture {index}> {_reference_text(ref.get('name')) or ref.get('id')}"
+            for index, (slot, ref) in enumerate(selected, 1)
+        )
+        if selected
+        else "Selected 0 references."
+    )
+    return (prompt, *images[:_H3_PROMPT_REF_SLOTS], len(selected), debug)
+
+
 def _parse_positive_int(value):
     text = str(value or "").strip()
     if not text:
@@ -1042,6 +1292,65 @@ def _build_character_wardrobe_text(wardrobe, character_id, name, alias):
     return text
 
 
+def _label_for_location(name, location_id):
+    return _normalize_free_text(name) or _normalize_free_text(location_id) or "the location"
+
+
+def _build_location_helper_text(
+    primary_picture_id,
+    secondary_picture_id,
+    location_id,
+    name,
+    alias,
+    description,
+    general,
+):
+    primary_picture = int(primary_picture_id)
+    secondary_picture = int(secondary_picture_id)
+    location_name = _normalize_free_text(name)
+    location_id = _normalize_free_text(location_id)
+    alias = _normalize_free_text(alias)
+    description = _ensure_sentence(description)
+    general = _ensure_sentence(general)
+    location_label = _label_for_location(location_name, location_id)
+
+    if location_name:
+        first_line = (
+            f"<Picture {primary_picture}> and <Picture {secondary_picture}> reference "
+            f"the same location called {location_name}."
+        )
+    elif location_id:
+        first_line = (
+            f"<Picture {primary_picture}> and <Picture {secondary_picture}> reference "
+            f'the same location with ID "{location_id}".'
+        )
+    else:
+        first_line = (
+            f"<Picture {primary_picture}> and <Picture {secondary_picture}> reference "
+            "the same location."
+        )
+
+    lines = [
+        first_line,
+        f"<Picture {primary_picture}> is the primary wide/environment reference for {location_label}.",
+        f"<Picture {secondary_picture}> is the secondary detail/angle reference for {location_label}.",
+    ]
+
+    facts = []
+    if alias:
+        facts.append(f"is also known as {alias}")
+    if description:
+        facts.append(description)
+
+    if facts:
+        lines.append(f"{location_label} {', '.join(facts)}")
+
+    if general:
+        lines.append(general)
+
+    return "\n".join(lines)
+
+
 class DumasImageCompareNode:
     DESCRIPTION = (
         "Dumas Image Compare shows the difference between two images directly on "
@@ -1604,6 +1913,274 @@ class DumasH3PlanExtractSceneImagesNode:
         return (passthrough_plan, *images, _connected_image_count(images))
 
 
+class DumasCharacterHelperNode:
+    DESCRIPTION = (
+        "Build a general character reference prompt and wardrobe sheet from two "
+        "IMAGE sockets plus simple identity fields, while passing both images "
+        "through unchanged."
+    )
+    RETURN_TYPES = ("IMAGE", "IMAGE", "STRING", "STRING")
+    RETURN_NAMES = ("image1", "image2", "reference_prompt", "wardrobe")
+    FUNCTION = "build_character_text"
+    CATEGORY = "Dumas/MiniMax"
+
+    @classmethod
+    def INPUT_TYPES(cls):
+        return {
+            "required": {
+                "image1": ("IMAGE", {"tooltip": "Primary image to pass through and describe."}),
+                "image2": ("IMAGE", {"tooltip": "Secondary image to pass through and describe."}),
+                "image1_picture_id": (
+                    ["1", "2", "3", "4", "5", "6", "7", "8", "9"],
+                    {
+                        "default": "1",
+                        "tooltip": "Picture number to mention for image1 in the reference prompt.",
+                    },
+                ),
+                "image2_picture_id": (
+                    ["1", "2", "3", "4", "5", "6", "7", "8", "9"],
+                    {
+                        "default": "2",
+                        "tooltip": "Picture number to mention for image2 in the reference prompt.",
+                    },
+                ),
+                "character_id": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": False,
+                        "tooltip": "Optional character ID string to include in the output text.",
+                    },
+                ),
+                "name": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": False,
+                        "tooltip": "Character name used in the main reference sentences.",
+                    },
+                ),
+                "alias": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": False,
+                        "tooltip": "Optional alternate name, codename, or nickname.",
+                    },
+                ),
+                "gender": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": False,
+                        "tooltip": "Optional gender field for non-visual character facts.",
+                    },
+                ),
+                "age": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": False,
+                        "tooltip": "Optional numeric age. Invalid values are omitted.",
+                    },
+                ),
+                "nationality": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": False,
+                        "tooltip": "Optional nationality, origin, or cultural background.",
+                    },
+                ),
+                "occupation": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": False,
+                        "tooltip": "Optional job, role, or function that is not visually obvious.",
+                    },
+                ),
+                "height_feet": (
+                    ["", "3", "4", "5", "6", "7", "8"],
+                    {
+                        "default": "",
+                        "tooltip": "Optional feet component for the character's height.",
+                    },
+                ),
+                "height_inches": (
+                    ["", "0", "1", "2", "3", "4", "5", "6", "7", "8", "9", "10", "11"],
+                    {
+                        "default": "",
+                        "tooltip": "Optional inches component for the character's height.",
+                    },
+                ),
+                "accent": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": False,
+                        "tooltip": "Optional short accent description.",
+                    },
+                ),
+                "general": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": True,
+                        "tooltip": "Optional non-clothing details appended as the last sentence of the reference prompt.",
+                    },
+                ),
+                "wardrobe": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": True,
+                        "tooltip": "Optional wardrobe/channel text. Plain clothing lists are auto-wrapped as 'Name = ...' when a name, alias, or character ID is present.",
+                    },
+                ),
+            }
+        }
+
+    def build_character_text(
+        self,
+        image1,
+        image2,
+        image1_picture_id,
+        image2_picture_id,
+        character_id,
+        name,
+        alias,
+        gender,
+        age,
+        nationality,
+        occupation,
+        height_feet,
+        height_inches,
+        accent,
+        general,
+        wardrobe,
+    ):
+        text = _build_character_helper_text(
+            image1_picture_id,
+            image2_picture_id,
+            character_id,
+            name,
+            alias,
+            gender,
+            age,
+            nationality,
+            occupation,
+            height_feet,
+            height_inches,
+            accent,
+            general,
+        )
+        wardrobe_text = _build_character_wardrobe_text(
+            wardrobe,
+            character_id,
+            name,
+            alias,
+        )
+        return (image1, image2, text, wardrobe_text)
+
+
+class DumasLocationHelperNode:
+    DESCRIPTION = (
+        "Build a general location reference prompt from two IMAGE sockets plus "
+        "simple environment fields, while passing both images through unchanged."
+    )
+    RETURN_TYPES = ("IMAGE", "IMAGE", "STRING")
+    RETURN_NAMES = ("image1", "image2", "reference_prompt")
+    FUNCTION = "build_location_text"
+    CATEGORY = "Dumas/MiniMax"
+
+    @classmethod
+    def INPUT_TYPES(cls):
+        return {
+            "required": {
+                "image1": ("IMAGE", {"tooltip": "Primary location image to pass through and describe."}),
+                "image2": ("IMAGE", {"tooltip": "Secondary location image to pass through and describe."}),
+                "image1_picture_id": (
+                    ["1", "2", "3", "4", "5", "6", "7", "8", "9"],
+                    {
+                        "default": "1",
+                        "tooltip": "Picture number to mention for image1 in the reference prompt.",
+                    },
+                ),
+                "image2_picture_id": (
+                    ["1", "2", "3", "4", "5", "6", "7", "8", "9"],
+                    {
+                        "default": "2",
+                        "tooltip": "Picture number to mention for image2 in the reference prompt.",
+                    },
+                ),
+                "location_id": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": False,
+                        "tooltip": "Optional location ID string to include in the output text.",
+                    },
+                ),
+                "name": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": False,
+                        "tooltip": "Location name used in the main reference sentences.",
+                    },
+                ),
+                "alias": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": False,
+                        "tooltip": "Optional alternate name, label, or area name.",
+                    },
+                ),
+                "description": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": True,
+                        "tooltip": "Persistent environment, layout, and atmosphere description.",
+                    },
+                ),
+                "general": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": True,
+                        "tooltip": "Optional extra notes appended as the last sentence of the reference prompt.",
+                    },
+                ),
+            }
+        }
+
+    def build_location_text(
+        self,
+        image1,
+        image2,
+        image1_picture_id,
+        image2_picture_id,
+        location_id,
+        name,
+        alias,
+        description,
+        general,
+    ):
+        text = _build_location_helper_text(
+            image1_picture_id,
+            image2_picture_id,
+            location_id,
+            name,
+            alias,
+            description,
+            general,
+        )
+        return (image1, image2, text)
+
+
 class DumasCharacterReferenceNode:
     DESCRIPTION = (
         "Build one structured REFERENCE object for a character so H3 can carry "
@@ -1836,6 +2413,154 @@ class DumasLocationReferenceNode:
         )
 
 
+class DumasSoundscapeHelperNode:
+    DESCRIPTION = (
+        "Choose a soundscape preset, auto-fill its editable description, and pass "
+        "the final soundscape text downstream for MiniMax H3 prompts."
+    )
+    RETURN_TYPES = ("STRING",)
+    RETURN_NAMES = ("soundscape",)
+    FUNCTION = "build_soundscape"
+    CATEGORY = "Dumas/MiniMax"
+
+    @classmethod
+    def INPUT_TYPES(cls):
+        default_soundscape = "quiet interior"
+        return {
+            "required": {
+                "soundscape": (
+                    _soundscape_options(),
+                    {
+                        "default": default_soundscape,
+                        "tooltip": "Preset title used to seed the editable soundscape description.",
+                    },
+                ),
+                "soundscape_description": (
+                    "STRING",
+                    {
+                        "default": _soundscape_description(default_soundscape),
+                        "multiline": True,
+                        "tooltip": (
+                            "Editable environmental audio description. Whatever text is here "
+                            "is what the node outputs to the soundscape socket."
+                        ),
+                    },
+                ),
+            }
+        }
+
+    def build_soundscape(self, soundscape, soundscape_description):
+        text = str(soundscape_description or "").strip()
+        if not text:
+            text = _soundscape_description(soundscape)
+        return (text,)
+
+
+class DumasH3PromptCuratorNode:
+    DESCRIPTION = (
+        "Curate one MiniMax H3 prompt from an action textbox, anchor text, "
+        "soundscape text, and up to nine structured references. References are "
+        "compacted so only mentioned names, aliases, or explicit <Picture N>/<refN> "
+        "tags are sent onward."
+    )
+    RETURN_TYPES = ("STRING",) + ("IMAGE",) * _H3_PROMPT_REF_SLOTS + ("INT", "STRING")
+    RETURN_NAMES = (
+        "prompt",
+        "ref_image_1",
+        "ref_image_2",
+        "ref_image_3",
+        "ref_image_4",
+        "ref_image_5",
+        "ref_image_6",
+        "ref_image_7",
+        "ref_image_8",
+        "ref_image_9",
+        "reference_count",
+        "debug",
+    )
+    FUNCTION = "curate_prompt"
+    CATEGORY = "Dumas/MiniMax"
+
+    @classmethod
+    def INPUT_TYPES(cls):
+        optional = {
+            "anchor": (
+                "STRING",
+                {
+                    "forceInput": True,
+                    "tooltip": "Optional anchor/style text, usually from Dumas Anchor Style.",
+                },
+            ),
+            "soundscape": (
+                "STRING",
+                {
+                    "forceInput": True,
+                    "tooltip": "Optional soundscape text, usually from Dumas Soundscape Helper.",
+                },
+            ),
+        }
+        for slot in range(1, _H3_PROMPT_REF_SLOTS + 1):
+            optional[f"ref_{slot}"] = (
+                _REFERENCE_TYPE,
+                {
+                    "tooltip": (
+                        f"Optional structured reference {slot}. The curator only outputs "
+                        "it if the action prompt mentions its name/alias or an explicit "
+                        f"<Picture {slot}>/<ref{slot}> tag."
+                    )
+                },
+            )
+        return {
+            "required": {
+                "action_prompt": (
+                    "STRING",
+                    {
+                        "default": "",
+                        "multiline": True,
+                        "tooltip": (
+                            "Write the final shot action here using character/location names. "
+                            "Mention a reference by name, alias, <Picture N>, or <refN> to use it."
+                        ),
+                    },
+                ),
+                "anatomy_guard": (
+                    ["auto", "on", "off"],
+                    {
+                        "default": "auto",
+                        "tooltip": (
+                            "Add the anatomy guard. Auto adds it when a character reference is used."
+                        ),
+                    },
+                ),
+            },
+            "optional": optional,
+        }
+
+    def curate_prompt(
+        self,
+        action_prompt,
+        anatomy_guard,
+        anchor="",
+        soundscape="",
+        ref_1=None,
+        ref_2=None,
+        ref_3=None,
+        ref_4=None,
+        ref_5=None,
+        ref_6=None,
+        ref_7=None,
+        ref_8=None,
+        ref_9=None,
+    ):
+        return curate_h3_prompt(
+            action_prompt,
+            anchor=anchor,
+            soundscape=soundscape,
+            refs=(ref_1, ref_2, ref_3, ref_4, ref_5, ref_6, ref_7, ref_8, ref_9),
+            anatomy_guard=anatomy_guard,
+        )
+
+
 class DumasAnchorStyleNode:
     DESCRIPTION = (
         "Choose an anchor-style preset, auto-fill its full description, and pass "
@@ -1887,9 +2612,12 @@ NODE_CLASS_MAPPINGS = {
     "DumasH3PlanExtractSceneImages": DumasH3PlanExtractSceneImagesNode,
     "DumasCharacterReference": DumasCharacterReferenceNode,
     "DumasLocationReference": DumasLocationReferenceNode,
+    "DumasSoundscapeHelper": DumasSoundscapeHelperNode,
+    "DumasH3PromptCurator": DumasH3PromptCuratorNode,
     "DumasAnchorStyle": DumasAnchorStyleNode,
-    "DumasCharacterHelper": DumasCharacterReferenceNode,
+    "DumasCharacterHelper": DumasCharacterHelperNode,
-    "DumasH3CharacterHelper": DumasCharacterReferenceNode,
+    "DumasLocationHelper": DumasLocationHelperNode,
+    "DumasH3CharacterHelper": DumasCharacterHelperNode,
 }
 
 NODE_DISPLAY_NAME_MAPPINGS = {
@@ -1900,7 +2628,10 @@ NODE_DISPLAY_NAME_MAPPINGS = {
     "DumasH3PlanExtractSceneImages": "Dumas H3 Plan Extract Scene Images",
     "DumasCharacterReference": "Dumas Character Reference",
     "DumasLocationReference": "Dumas Location Reference",
+    "DumasSoundscapeHelper": "Dumas Soundscape Helper",
+    "DumasH3PromptCurator": "Dumas H3 Prompt Curator",
     "DumasAnchorStyle": "Dumas Anchor Style",
-    "DumasCharacterHelper": "Dumas Character Reference",
+    "DumasCharacterHelper": "Dumas Character Helper",
-    "DumasH3CharacterHelper": "Dumas Character Reference",
+    "DumasLocationHelper": "Dumas Location Helper",
+    "DumasH3CharacterHelper": "Dumas Character Helper",
 }

tests/test_dumas_h3_longvideos.py

@@ -362,6 +362,7 @@ class DumasH3LongVideosHelperTests(unittest.TestCase):
                 return self._parts
 
         order = []
+        build_calls = []
         first_out = {"samples": FakeNestedTensor((FakeTensor("v1"), FakeTensor("a1")))}
         second_out = {"samples": FakeNestedTensor((FakeTensor("v2"), FakeTensor("a2")))}
 
@@ -408,11 +409,15 @@ class DumasH3LongVideosHelperTests(unittest.TestCase):
                 order.append("upscale")
                 return FakeTensor("upv"), 8, 16
 
+            def build_conditioning(*_args, **_kwargs):
+                build_calls.append(True)
+                return (
+                    [["cond", {}]],
+                    {"samples": FakeNestedTensor((FakeTensor("basev"), FakeTensor("basea")))},
+                )
+
             self.module.nodes.common_ksampler = common_ksampler
-            self.module._build_shot_conditioning = lambda *_args, **_kwargs: (
+            self.module._build_shot_conditioning = build_conditioning
-                "cond",
-                {"samples": FakeNestedTensor((FakeTensor("basev"), FakeTensor("basea")))},
-            )
             self.module._evict_all_but = lambda *_args, **_kwargs: None
             self.module.mm.unload_model_and_clones = unload_model_and_clones
             self.module.mm.unload_all_models = unload_all_models
@@ -457,6 +462,7 @@ class DumasH3LongVideosHelperTests(unittest.TestCase):
             self.assertLess(order.index("upscale"), order.index("latent_upscale_sample"))
             self.assertLess(order.index("audio"), order.index("video"))
             self.assertEqual(order[-1], "cleanup")
+            self.assertEqual(len(build_calls), 1)
         finally:
             self.module.nodes.common_ksampler = original_common_ksampler
             self.module._build_shot_conditioning = original_build
@@ -476,6 +482,12 @@ class DumasH3LongVideosHelperTests(unittest.TestCase):
             else:
                 self.module.comfy.nested_tensor.NestedTensor = original_nested
 
+    def test_latent_refine_tiles_do_not_rebuild_conditioning(self):
+        source = inspect.getsource(self.module.H3LongVideos._render)
+        tile_branch = source[source.index("for col_index, c0 in enumerate(cols):"):]
+        self.assertIn("_crop_conditioning_to_tile", tile_branch)
+        self.assertNotIn("_build_shot_conditioning(", tile_branch)
+
     def test_latent_upscale_off_skips_second_pass(self):
         calls = []
         original_common_ksampler = self.module.nodes.common_ksampler
@@ -1165,8 +1177,8 @@ class DumasH3LongVideosHelperTests(unittest.TestCase):
         self.assertFalse(required["brightness_match"][1]["default"])
         self.assertEqual(required["dynamic_fade"][1]["default"], "off")
         self.assertEqual(required["dynamic_fade_min"][1]["default"], 32)
-        self.assertEqual(required["chunk_length"][1]["default"], 17)
+        self.assertEqual(required["chunk_length"][1]["default"], 85)
-        self.assertEqual(required["temporal_overlap"][1]["default"], 0)
+        self.assertEqual(required["temporal_overlap"][1]["default"], 17)
         self.assertFalse(required["resize_conditioning"][1]["default"])
         self.assertEqual(required["anchor_strength"][1]["default"], 0.999)
 
@@ -1256,16 +1268,61 @@ class DumasH3LongVideosHelperTests(unittest.TestCase):
         self.assertEqual(smaller["chunk_length"], 17)
         self.assertEqual(smaller["temporal_overlap"], 0)
 
-    def test_cuda_model_temporal_params_cap_saved_workflows(self):
+    def test_cuda_model_temporal_params_keep_splitting_saved_workflows(self):
         latent = importlib.import_module("dumas_h3_latent_upscale")
         chunk_length, temporal_overlap = latent._effective_temporal_params({
             "mode": "model",
             "device": "cuda",
             "chunk_length": 85,
             "temporal_overlap": 17,
-        })
+        }, frame_count=124)
-        self.assertEqual(chunk_length, 17)
+        self.assertEqual(chunk_length, 85)
-        self.assertEqual(temporal_overlap, 0)
+        self.assertEqual(temporal_overlap, 17)
+
+    def test_cuda_model_temporal_params_keep_short_saved_workflows_until_oom(self):
+        latent = importlib.import_module("dumas_h3_latent_upscale")
+        chunk_length, temporal_overlap = latent._effective_temporal_params({
+            "mode": "model",
+            "device": "cuda",
+            "chunk_length": 85,
+            "temporal_overlap": 17,
+        }, frame_count=85)
+        self.assertEqual(chunk_length, 85)
+        self.assertEqual(temporal_overlap, 17)
+
+    def test_cuda_model_oom_retries_temporal_before_spatial_fallback(self):
+        latent = importlib.import_module("dumas_h3_latent_upscale")
+
+        calls = []
+        original_tiled = latent._upscale_video_model_tiled
+        original_shrink_model = latent._shrink_model_tile_param
+        try:
+            def tiled(_video, param):
+                calls.append(("tiled", param.get("chunk_length"), param.get("tile_size_mode")))
+                raise RuntimeError("out of memory")
+
+            latent._upscale_video_model_tiled = tiled
+            latent._shrink_model_tile_param = (
+                lambda param: calls.append(("shrink_spatial", param.get("tile_size_mode"))) or None
+            )
+
+            with self.assertRaisesRegex(RuntimeError, "smaller temporal chunk"):
+                latent.upscale_video_model(
+                    "video",
+                    {
+                        "mode": "model",
+                        "device": "cuda",
+                        "model_name": "upscale.safetensors",
+                        "chunk_length": 85,
+                        "temporal_overlap": 17,
+                    },
+                )
+
+            self.assertEqual(calls[0], ("tiled", 85, None))
+            self.assertNotIn(("shrink_spatial", None), calls)
+        finally:
+            latent._upscale_video_model_tiled = original_tiled
+            latent._shrink_model_tile_param = original_shrink_model
 
     def test_interp_temporal_params_preserve_upstream_defaults(self):
         latent = importlib.import_module("dumas_h3_latent_upscale")
@@ -1278,6 +1335,182 @@ class DumasH3LongVideosHelperTests(unittest.TestCase):
         self.assertEqual(chunk_length, 85)
         self.assertEqual(temporal_overlap, 17)
 
+    def test_unload_upscale_model_defers_while_held(self):
+        latent = importlib.import_module("dumas_h3_latent_upscale")
+
+        class FakeParam:
+            device = "cuda"
+
+        class FakeModel:
+            def __init__(self):
+                self.moves = []
+
+            def parameters(self):
+                return iter((FakeParam(),))
+
+            def to(self, device):
+                self.moves.append(device)
+                return self
+
+        cache_key = "upscale.safetensors::cuda::fp16"
+        original_cache_value = latent._MODEL_CACHE.get(cache_key)
+        original_hold_depth = latent._MODEL_HOLD_DEPTH
+        fake_model = FakeModel()
+        try:
+            latent._MODEL_CACHE[cache_key] = fake_model
+            latent._MODEL_HOLD_DEPTH = 0
+            with latent._hold_upscale_model_loaded():
+                latent.unload_upscale_model("upscale.safetensors", "cuda", "fp16")
+            self.assertEqual(fake_model.moves, [])
+
+            latent.unload_upscale_model("upscale.safetensors", "cuda", "fp16")
+            self.assertEqual(fake_model.moves, ["cpu"])
+        finally:
+            latent._MODEL_HOLD_DEPTH = original_hold_depth
+            if original_cache_value is None:
+                latent._MODEL_CACHE.pop(cache_key, None)
+            else:
+                latent._MODEL_CACHE[cache_key] = original_cache_value
+
+    def test_model_upscale_releases_cached_model_after_pass(self):
+        latent = importlib.import_module("dumas_h3_latent_upscale")
+        calls = []
+
+        original_temporal = latent._upscale_video_temporal_chunks
+        original_unload_now = latent._unload_upscale_model_now
+        original_cuda = latent.torch.cuda
+        original_device = getattr(latent.torch, "device", None)
+        try:
+            latent.torch.cuda = types.SimpleNamespace(is_available=lambda: True)
+            latent.torch.device = lambda value: value
+
+            def temporal(video, param, upscaler):
+                calls.append(("temporal", latent._MODEL_HOLD_DEPTH))
+                return "video", 8, 16
+
+            def unload_now(name, device, precision):
+                calls.append(("unload", name, device, precision, latent._MODEL_HOLD_DEPTH))
+
+            latent._upscale_video_temporal_chunks = temporal
+            latent._unload_upscale_model_now = unload_now
+
+            result = latent.upscale_latent_video("source", {
+                "mode": "model",
+                "model_name": "upscale.safetensors",
+                "device": "cuda",
+                "precision": "fp16",
+            })
+
+            self.assertEqual(result, ("video", 8, 16))
+            self.assertEqual(calls[0], ("temporal", 1))
+            self.assertEqual(calls[1], ("unload", "upscale.safetensors", "cuda", "fp16", 1))
+            self.assertEqual(latent._MODEL_HOLD_DEPTH, 0)
+        finally:
+            latent._upscale_video_temporal_chunks = original_temporal
+            latent._unload_upscale_model_now = original_unload_now
+            latent.torch.cuda = original_cuda
+            if original_device is None:
+                delattr(latent.torch, "device")
+            else:
+                latent.torch.device = original_device
+
+    def test_model_upscale_oom_falls_back_to_interp(self):
+        latent = importlib.import_module("dumas_h3_latent_upscale")
+        calls = []
+
+        original_temporal = latent._upscale_video_temporal_chunks
+        original_interp = latent.upscale_video_interp
+        original_unload_now = latent._unload_upscale_model_now
+        original_cuda = latent.torch.cuda
+        original_device = getattr(latent.torch, "device", None)
+        try:
+            latent.torch.cuda = types.SimpleNamespace(
+                is_available=lambda: True,
+                empty_cache=lambda: calls.append(("empty_cache",)),
+            )
+            latent.torch.device = lambda value: value
+
+            def temporal(_video, _param, _upscaler):
+                calls.append(("temporal", latent._MODEL_HOLD_DEPTH))
+                raise RuntimeError("H3 latent upscale exhausted its GPU spatial fallbacks")
+
+            def interp(video, param):
+                calls.append(("interp", video, param.get("mode"), param.get("method")))
+                return "interp_video", 8, 16
+
+            def unload_now(name, device, precision):
+                calls.append(("unload", name, device, precision, latent._MODEL_HOLD_DEPTH))
+
+            latent._upscale_video_temporal_chunks = temporal
+            latent.upscale_video_interp = interp
+            latent._unload_upscale_model_now = unload_now
+
+            result = latent.upscale_latent_video("source", {
+                "mode": "model",
+                "model_name": "upscale.safetensors",
+                "method": "bilinear",
+                "device": "cuda",
+                "precision": "fp16",
+            })
+
+            self.assertEqual(result, ("interp_video", 8, 16))
+            self.assertEqual(calls[0], ("temporal", 1))
+            self.assertEqual(calls[1], ("unload", "upscale.safetensors", "cuda", "fp16", 1))
+            self.assertIn(("empty_cache",), calls)
+            self.assertEqual(calls[-1], ("interp", "source", "interp", "bilinear"))
+            self.assertEqual(latent._MODEL_HOLD_DEPTH, 0)
+        finally:
+            latent._upscale_video_temporal_chunks = original_temporal
+            latent.upscale_video_interp = original_interp
+            latent._unload_upscale_model_now = original_unload_now
+            latent.torch.cuda = original_cuda
+            if original_device is None:
+                delattr(latent.torch, "device")
+            else:
+                latent.torch.device = original_device
+
+    def test_model_upscale_skips_learned_model_on_8gb_cuda(self):
+        latent = importlib.import_module("dumas_h3_latent_upscale")
+        calls = []
+
+        original_temporal = latent._upscale_video_temporal_chunks
+        original_interp = latent.upscale_video_interp
+        original_cuda = latent.torch.cuda
+        try:
+            latent.torch.cuda = types.SimpleNamespace(
+                is_available=lambda: True,
+                mem_get_info=lambda: (1 * 1024 * 1024 * 1024, 8 * 1024 * 1024 * 1024),
+                empty_cache=lambda: calls.append(("empty_cache",)),
+            )
+
+            def temporal(_video, _param, _upscaler):
+                calls.append(("temporal",))
+                raise AssertionError("learned model path should be skipped on 8GB CUDA")
+
+            def interp(video, param):
+                calls.append(("interp", video, param.get("mode"), param.get("method")))
+                return "interp_video", 8, 16
+
+            latent._upscale_video_temporal_chunks = temporal
+            latent.upscale_video_interp = interp
+
+            result = latent.upscale_latent_video("source", {
+                "mode": "model",
+                "model_name": "upscale.safetensors",
+                "method": "bilinear",
+                "device": "cuda",
+                "precision": "fp16",
+            })
+
+            self.assertEqual(result, ("interp_video", 8, 16))
+            self.assertNotIn(("temporal",), calls)
+            self.assertIn(("empty_cache",), calls)
+            self.assertEqual(calls[-1], ("interp", "source", "interp", "bilinear"))
+        finally:
+            latent._upscale_video_temporal_chunks = original_temporal
+            latent.upscale_video_interp = original_interp
+            latent.torch.cuda = original_cuda
+
     def test_upscale_video_model_raises_when_gpu_cannot_shrink(self):
         latent = importlib.import_module("dumas_h3_latent_upscale")
 

tests/test_dumas_image_nodes.py

@@ -356,6 +356,159 @@ class DumasImageNodeTests(unittest.TestCase):
         required = self.image_nodes.DumasLocationReferenceNode.INPUT_TYPES()["required"]
         self.assertNotIn("picture_id", required)
 
+    def test_character_helper_restores_image_and_text_outputs(self):
+        node = self.image_nodes.DumasCharacterHelperNode()
+        image1 = FakeTensorBatch()
+        image2 = FakeTensorBatch()
+
+        result = node.build_character_text(
+            image1=image1,
+            image2=image2,
+            image1_picture_id="1",
+            image2_picture_id="2",
+            character_id="char_dave",
+            name="Dave",
+            alias="The Locksmith",
+            gender="male",
+            age="41",
+            nationality="English",
+            occupation="a detective",
+            height_feet="6",
+            height_inches="2",
+            accent="English",
+            general="Moves carefully and notices every exit",
+            wardrobe="weathered red flight jacket, grey cargo shorts, black boots",
+        )
+
+        self.assertIs(result[0], image1)
+        self.assertIs(result[1], image2)
+        self.assertIn("<Picture 1> and <Picture 2> reference the same character", result[2])
+        self.assertIn("Dave is also known as The Locksmith", result[2])
+        self.assertIn("is 41 years old", result[2])
+        self.assertEqual(result[3], "Dave = weathered red flight jacket, grey cargo shorts, black boots")
+
+    def test_location_helper_matches_character_helper_shape_without_wardrobe(self):
+        node = self.image_nodes.DumasLocationHelperNode()
+        image1 = FakeTensorBatch()
+        image2 = FakeTensorBatch()
+
+        result = node.build_location_text(
+            image1=image1,
+            image2=image2,
+            image1_picture_id="3",
+            image2_picture_id="4",
+            location_id="coffee-shop-01",
+            name="Coffee Shop",
+            alias="Cafe Interior",
+            description="Warm tungsten lighting, narrow counter, rainy front window",
+            general="Evening ambience, cramped but cozy",
+        )
+
+        self.assertIs(result[0], image1)
+        self.assertIs(result[1], image2)
+        self.assertIn("<Picture 3> and <Picture 4> reference the same location", result[2])
+        self.assertIn("Coffee Shop is also known as Cafe Interior", result[2])
+        self.assertIn("Warm tungsten lighting, narrow counter, rainy front window.", result[2])
+        self.assertIn("Evening ambience, cramped but cozy.", result[2])
+        self.assertEqual(len(result), 3)
+
+    def test_soundscape_helper_defaults_to_selected_preset_description(self):
+        node = self.image_nodes.DumasSoundscapeHelperNode()
+
+        result = node.build_soundscape("rainy street", "")
+
+        self.assertEqual(result[0], "steady rain, wet pavement, distant traffic hum")
+
+    def test_h3_prompt_curator_compacts_named_references(self):
+        node = self.image_nodes.DumasH3PromptCuratorNode()
+        dave_image = FakeTensorBatch()
+        cafe_image = FakeTensorBatch()
+        van_image = FakeTensorBatch()
+        dave = self.image_nodes.make_reference(
+            kind="character",
+            image=dave_image,
+            name="Dave",
+            aliases="The Locksmith",
+            description="tired eyes, cropped brown hair",
+            wardrobe="red flight jacket",
+        )
+        cafe = self.image_nodes.make_reference(
+            kind="location",
+            image=cafe_image,
+            name="Coffee Shop",
+            description="warm tungsten lighting and rainy windows",
+        )
+        van = self.image_nodes.make_reference(
+            kind="location",
+            image=van_image,
+            name="Blue Van",
+            description="scuffed blue delivery van",
+        )
+
+        result = node.curate_prompt(
+            action_prompt="Dave runs from the Coffee Shop into the rain.",
+            anatomy_guard="auto",
+            anchor="grounded handheld thriller",
+            soundscape="steady rain",
+            ref_1=dave,
+            ref_2=van,
+            ref_3=cafe,
+        )
+
+        prompt = result[0]
+        self.assertIn("<Picture 1> Dave", prompt)
+        self.assertIn("<Picture 2> Coffee Shop", prompt)
+        self.assertIn("Action: Dave runs from the Coffee Shop into the rain.", prompt)
+        self.assertIn("Anatomy guard:", prompt)
+        self.assertIs(result[1], dave_image)
+        self.assertIs(result[2], cafe_image)
+        self.assertIsNone(result[3])
+        self.assertEqual(result[10], 2)
+        self.assertIn("input 3-><Picture 2> Coffee Shop", result[11])
+
+    def test_h3_prompt_curator_renumbers_explicit_reference_tags(self):
+        node = self.image_nodes.DumasH3PromptCuratorNode()
+        image1 = FakeTensorBatch()
+        image3 = FakeTensorBatch()
+        unused = FakeTensorBatch()
+        first = self.image_nodes.make_reference(kind="character", image=image1, name="Maya")
+        second = self.image_nodes.make_reference(kind="location", image=unused, name="Lobby")
+        third = self.image_nodes.make_reference(kind="location", image=image3, name="Rooftop")
+
+        result = node.curate_prompt(
+            action_prompt="<Picture 1> Maya crosses to <ref3> as the wind rises.",
+            anatomy_guard="off",
+            ref_1=first,
+            ref_2=second,
+            ref_3=third,
+        )
+
+        prompt = result[0]
+        self.assertIn("<Picture 1> Maya crosses to <Picture 2>", prompt)
+        self.assertNotIn("<Picture 3>", prompt)
+        self.assertIs(result[1], image1)
+        self.assertIs(result[2], image3)
+        self.assertIsNone(result[3])
+        self.assertEqual(result[10], 2)
+
+    def test_helper_node_mappings_use_general_purpose_helpers(self):
+        mappings = self.image_nodes.NODE_CLASS_MAPPINGS
+        display = self.image_nodes.NODE_DISPLAY_NAME_MAPPINGS
+
+        self.assertIs(mappings["DumasCharacterHelper"], self.image_nodes.DumasCharacterHelperNode)
+        self.assertIs(mappings["DumasLocationHelper"], self.image_nodes.DumasLocationHelperNode)
+        self.assertIs(mappings["DumasSoundscapeHelper"], self.image_nodes.DumasSoundscapeHelperNode)
+        self.assertIs(mappings["DumasH3PromptCurator"], self.image_nodes.DumasH3PromptCuratorNode)
+        self.assertEqual(display["DumasCharacterHelper"], "Dumas Character Helper")
+        self.assertEqual(display["DumasLocationHelper"], "Dumas Location Helper")
+        self.assertEqual(display["DumasSoundscapeHelper"], "Dumas Soundscape Helper")
+        self.assertEqual(display["DumasH3PromptCurator"], "Dumas H3 Prompt Curator")
+
+    def test_h3_prompt_curator_uses_documented_reference_limits(self):
+        node = self.image_nodes.DumasH3PromptCuratorNode()
+        self.assertEqual(len(node.RETURN_TYPES), 12)
+        self.assertEqual(node.RETURN_NAMES[1:10], tuple(f"ref_image_{i}" for i in range(1, 10)))
+
     def test_normalize_reference_upgrades_generic_summary_with_socket_picture_id(self):
         image = FakeTensorBatch()