Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
The big one. Everything since v1.4, consolidated - headlined by something no other H3 workflow does: voice identity that survives the chain .
Runtime profile
Source description
The big one. Everything since v1.4, consolidated - headlined by something no other H3 workflow does: voice identity that survives the chain .
A character's voice now holds across every chained shot
Chained multishot re-performs the voice from text each shot, and it drifts - that has been the known limitation since v1.1. Two new controls on the multishot sampler end it:
voice_ref (AUDIO input): feed a voice clip and it anchors EVERY shot as . Stereo, sample rate, and length are guarded internally - a mono clip no longer crashes the packed layout.
self_anchor_voice (toggle): no file at all. Shot 1's own rendered voice automatically becomes the reference for every later shot. Write shot 1 so the character speaks a clean solo line, and the scene anchors on itself.
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Use this MiniMax-H3 Multishot workflow to make a continuous multi-shot video with sound from story prompts, with an optional photo to open shot 1 and an optional voice clip to guide the speaker.
The `voice_ref` audio input anchors the speaker across chained shots; `self_anchor_voice` can instead use shot 1’s rendered voice for later shots.
H3 Ref Folder, H3 Auto Refs, and H3 Ref Batch support folder-based casting for up to 9 images, with dialogue removed before character-name matching.
H3 Episode Split, H3 Last Frame, and H3 Concat A/V support two-stage episode assembly; the join matches stage B’s sharpness and tone to stage A at the seam.
Enter prompts in the box or point it to a prompt file; for manual shot text, set the writer to passthrough and use raw JSON with shots separated by `---`.
Run it in ComfyUI with the MiniMax-H3 Multishot node pack and a MiniMax-H3 checkpoint; the VAEs are preset.
The AIO workflow lists these model files: `minimax_h3_audio_vae_fp32.safetensors`, `minimax_h3_video_vae_fp16.safetensors`, `MiniMax-H3-encoder-Q4_K_M.gguf`, and `MiniMax-H3-fl2va-Q5_1.gguf`.
With `activation_reserve_gb` set to 0, reserve sizing adjusts to the render shape; a manual value pins the reserve.
The four-slot MODEL-only H3 LoRA Stack sits between the loader and sampler; empty slots pass through, and slot 1 accepts a LoRA without rewiring.
H3 Studio Controls lets width, height, frames, steps, sampler, and scheduler settings drive the full multi-stage graph.
Voice anchoring requires a ref2va checkpoint; fl2va was not trained with reference rows.
At 10–12 steps with the 4-step turbo distill, multistep solvers can distort audio.
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 10753 downloads · Type Workflows · Base model MiniMax H3
Verified A/B - same seed, same start frame, same continuation line: the plain chain drifted off the character's voice; the anchored render held it and matched the source loudness within 1 dB. Requirements: run the chained shots on a ref2va checkpoint (fl2va was not trained with reference rows) and bind the ref in each shot's prompt: Her voice is the voice in . The AIO workflow ships with a muted VOICE ANCHOR node ready to unmute.
VRAM management is now automatic
Leave activation_reserve_gb at 0 and the pack sizes the reserve from the actual render shape, measures the true allocator peak of every run, and tightens itself per GPU, model, and shape. The trap where lowering the resolution made renders 5-10x slower (the reserve shrank below the allocator pool and the driver thrashed) is gone. Manual values still pin, and multi-GPU rigs no longer evict a dedicated-GPU text encoder every shot - thanks @VladiCz for measuring that one at a third of his render.
LoRA stack, in every workflow
A four-slot MODEL-only H3 LoRA Stack sits inert between loader and sampler in every bundled workflow. Empty slots are a true pass-through; pick a LoRA in slot 1 (the turbo distill, a style LoRA) instead of rewiring.
New nodes
H3 Ref Folder / H3 Auto Refs / H3 Ref Batch - folder-driven reference casting, up to 9 images, with dialogue stripped before name-matching so a merely mentioned character does not cast.
H3 Cartridge Loader - portable .riftcast character cartridges (anchor frames + references + voice), drop-in auto-install.
H3 Episode Split / Last Frame / Concat A/V - two-stage episode assembly. The concat matches stage B's sharpness and tone to stage A at the seam, and passes stage A through untouched for single-shot renders.
H3 Studio Controls (+ Sampler by Name / Sigmas by Name) - one node whose width/height/frames/steps/sampler/scheduler drive an entire multi-stage graph. No more stage A rendered at one size and stage B at another.
H3 Keyframe Inject (experimental) + the merge patch that lets references and keyframes COMPOSE in one conditioning instead of the refs silently discarding the keyframe.
Worth knowing
With the 4-step turbo distill at 10-12 steps, sample with euler + beta . Multistep solvers extrapolate across step history, and H3's audio runs on a different sigma clock than the video - on a distilled model that math over-steps the AUDIO stream and it comes out distorted.
GGUF loading stays fully automatic (the v1.4.1 fix), and the pack in this zip is the complete current node set - nothing requires a separate download.
Hardware and download-size estimates are not available yet.
Requirements
minimax_h3_audio_vae_fp32.safetensors
File unverifiedVAE · SAFETENSORS · Unknown
minimax_h3_video_vae_fp16.safetensors
File unverifiedVAE · SAFETENSORS · Unknown
MiniMax-H3-encoder-Q4_K_M.gguf
Not resolvedText encoder · Unknown
MiniMax-H3-fl2va-Q5_1.gguf
Not resolvedCheckpoint · Unknown
