84 lines
3.4 KiB
Markdown
84 lines
3.4 KiB
Markdown
# MiniMax H3 Best Current R2V Master 480p 3x10s
|
|
|
|
## Summary
|
|
|
|
Best-current `MiniMax H3` continuation master for Chris's actual priority:
|
|
`reference-to-video` first, not generic `t2v`. This workflow keeps the
|
|
extender's validated clip-by-clip cache flow, but locks it into the safest
|
|
current local shape: `480p`, `3 x 10s`, lighter `Ref2VA` stack, and reusable
|
|
subject-definition prompts for continuity across the chain.
|
|
|
|
## Status
|
|
|
|
- `best-current-r2v-master`
|
|
|
|
## Workflow asset
|
|
|
|
- `workflow.json`
|
|
|
|
## This pass
|
|
|
|
- Tightened the clip prompts so `<Picture 1>` carries the master scene and `<Picture 2>` carries the primary full-body identity, matching the current Ref2VA prompt hierarchy.
|
|
- Kept the `clip_by_clip` validation flow and the `480p` / `3 x 10s` budget intact.
|
|
|
|
## Built from
|
|
|
|
- `optimized/image-to-video/minimax-h3-extender-3070-r2v-480p-clip-by-clip/`
|
|
- `models/minimax/minimax-h3-extender-ref2va/`
|
|
- `models/minimax/minimax-h3-int8-r2v-javano2608-23/`
|
|
- current MiniMax Ref2VA prompt guidance in `optimized/notes/minimax-h3-ref2va-prompt-guidelines.md`
|
|
- local lessons from:
|
|
- `optimized/image-to-video/minimax-h3-contex-loop-3070-compact-prepend-480p-3x10s/`
|
|
- `optimized/image-to-video/minimax-h3-contex-loop-3070-compact-30s/`
|
|
|
|
## Key model stack
|
|
|
|
- `minimax_h3_ref2va_pruned_w4a8_mixed.safetensors`
|
|
- `qwen3vl_32b_heretic_minimax_h3_nvfp4.safetensors`
|
|
- `minimax_h3_video_vae_int8_convrot.safetensors`
|
|
- `minimax_h3_audio_vae_fp32.safetensors`
|
|
- `minimax\minimax_h3_fl2v_lightx2v_turbo_4step_v0.1_comfy.safetensors`
|
|
|
|
## Main changes
|
|
|
|
- keeps `clip_by_clip` validation instead of `full_batch`
|
|
- keeps the safer `864x480` working canvas
|
|
- keeps `5` steps rather than the source graph's more brittle `4`
|
|
- expands the starter plan to `3 x 10s` clips so the default chain matches the
|
|
safer continuation cadence already established by the compact local MiniMax
|
|
masters
|
|
- uses neutral reusable `R2V` prompts instead of a source-specific demo scene
|
|
- keeps `context_length=22` and `ref_image_size=match`
|
|
|
|
## Why this is the best current one
|
|
|
|
- Chris's standing preference is `reference-to-video` first, so this workflow
|
|
is optimized around `Ref2VA` continuation instead of plain `t2v`
|
|
- the extender node's validation/cache loop is the strongest current UX for
|
|
building a long sequence progressively without rerendering accepted clips
|
|
- the current compact `Contex Loop` masters still define the safe local budget,
|
|
and this workflow inherits that budget shape instead of pretending the source
|
|
defaults are free
|
|
- the newer same-day `javawock7618` `INT8 R2V` import is the strongest current
|
|
donor for tighter subject retention, so the maintained master now spells out
|
|
the scene/subject authority order more explicitly
|
|
- this is the cleanest current merge of:
|
|
- better continuation workflow UX
|
|
- safer `3070 / 8 GB` assumptions
|
|
- `R2V`-first control
|
|
|
|
## When to use this
|
|
|
|
- use this first when the goal is: keep one or more reference images stable and
|
|
extend the action across several connected clips
|
|
- use the compact `Contex Loop` masters instead when the main job is extending
|
|
an already existing source video rather than generating a new reference-driven
|
|
chain
|
|
|
|
## Notes
|
|
|
|
- Start with one strong main reference and short clips.
|
|
- Validate each clip before moving on.
|
|
- Add extra image references only when they solve a real identity or scene
|
|
problem, because more references also increase fragility.
|