drowzeys's picture
sealed config pp20260813: stock int8-convrot TE (heretic retired), bf16 finals, OOM/farm doctrine — README.md
ea1afed verified
|
Raw
History Blame Contribute Delete
7.08 kB
---
license: other
language:
- en
tags:
- minimax-h3
- comfyui
- dgx-spark
- blackwell
- video-generation
- dual-gpu
- parallel
- power-pack
- 2k
- esrgan
library_name: comfyui
pipeline_tag: text-to-video
---
# keys-2k MiniMax-H3 — Parallel processing for **Two DGX Sparks**
**One-command pull · pinned quality stack · master-K0 dual-Spark parallel · ESRGAN “2K” · Spectrum audio fix · Contex-Loop / MultiRef · optional realism LoRA**
| | |
|--|--|
| **Docker (arm64, published)** | `ghcr.io/drowzeys/keys-2k-minimax-h3-parallel-two-dgx-sparks:0.31.1-pp20260811` (~16GB, Comfy+nodes; mount models) |
| **HF package** | this repo |
| **Power Pack** | [keys-DGX-Sparkticus-Ultimate-Power-Pack-Unleashed](https://github.com/drowzeys/keys-DGX-Sparkticus-Ultimate-Power-Pack-Unleashed-Dual-DGX-Sparks-Needed) |
| **Dual-serve foundation** | [tonyd2wild/ds4-h3-video-gen-factory](https://github.com/tonyd2wild/ds4-h3-video-gen-factory) (Tony) |
> Dual-serve DS4 + dual H3 on two DGX Sparks was made possible by **Tony (tonyd2wild)**.
> This package is the **keyspark quality specialization** (ablit co-tenant profile + **sealed bf16 finals with stock int8-convrot TE** — heretic retired — + farm-mode dual parallel + 2K workflows).
---
## Why this exists
Agents and users often `git clone` **old** Spectrum / Motion Context / Comfy builds and lose:
- Spectrum **v0.2.1** audio fix (`offline_smoothing_replay=true`)
- Contex-Loop / MultiRef seam fixes
- Legal native sizes for upscale-to-2K
- Dual-node **master-K0** parallel spans
This package **pins** the full integrated stack in a **Docker image** + **manifest** so the default path is the upgraded one.
---
## One-command pull
```bash
curl -fsSL https://huggingface.co/drowzeys/keys-2k-MiniMax-H3-Parallel-Two-DGX-Sparks/raw/main/scripts/one_command_pull.sh | bash
```
Or:
```bash
git clone https://huggingface.co/drowzeys/keys-2k-MiniMax-H3-Parallel-Two-DGX-Sparks
cd keys-2k-MiniMax-H3-Parallel-Two-DGX-Sparks
bash scripts/one_command_pull.sh
```
Pull Docker only:
```bash
docker pull ghcr.io/drowzeys/keys-2k-minimax-h3-parallel-two-dgx-sparks:0.31.1-pp20260811
# also tagged :latest
```
---
## What’s in the image (pinned)
| Component | Version / pin |
|-----------|----------------|
| ComfyUI | **0.31.1** |
| Spectrum MiniMax H3 | **0.2.1** (audio fix defaults) |
| Contex-Loop | **0.3.8** |
| Motion Context + MultiRef | pinned SHAs in `manifest/H3_STACK_MANIFEST.json` |
| Sol-attn Blackwell + Triton SolAttn | pinned |
| KJNodes (Sage) | 1.4.9 · `sageattention==1.0.6` |
| NKD Preview Tools | 3.3.0 |
| Launch flags | `--disable-pinned-memory --reserve-vram 48 --vram-headroom 10` |
**Not for quality:** Turbo / few-step LoRA graphs (present optional; leave off).
See **`manifest/H3_STACK_MANIFEST.json`** and **`scripts/verify_h3_stack.sh`**.
---
## 2K path (open weights)
Open MiniMax-H3 does **not** native 2K in one pass. This package’s production path:
```text
Native denoise 704 × 1280 (multiple of 32 — 720×1280 fails)
↓ RealESRGAN ×2 (inline on spans)
Delivery 2K ~1408 × 2560
```
Parallelism: **master-K0** keyframes + **parallel FL2VA spans** on two Sparks
(`h3-spans.py --kf-mode master-parallel --upscale`).
Workflow package: `workflows/anime_2k_bench/`
Lab sample run `0811_012837`: ~**18.8 min** wall for ~4.8 s @ 704×1280 dual-node (co-tenant DS4).
---
## Dual DGX Spark — parallel H3
```bash
export HEAD=10.100.10.1 WORKER=10.100.10.5 # your fabric IPs
export MODELS_DIR=$HOME/keys-2k-minimax-h3-parallel/models
# weights once
bash scripts/fetch_weights.sh
# or: rsync -a /path/to/lab/h3-cotenancy/ComfyUI/models/ $MODELS_DIR/
# H3 on both nodes
bash scripts/run_dual_h3.sh
# quality 2K parallel bench
bash scripts/run_anime_2k_bench.sh
# optional realism LoRA (file in models/loras/):
REALISM=1 bash scripts/run_anime_2k_bench.sh
```
Single node smoke:
```bash
docker run --rm --gpus all --network host \
-v $MODELS_DIR:/opt/powerpack-h3/ComfyUI/models \
-v $HOME/Videos/h3-out:/opt/powerpack-h3/ComfyUI/output \
ghcr.io/drowzeys/keys-2k-minimax-h3-parallel-two-dgx-sparks:0.31.1-pp20260811
# UI/API: http://<host>:8188
```
Compose: `compose/docker-compose.yml`
---
## Co-tenancy with DeepSeek-V4-Flash (Tony’s rule)
If running **DS4 + H3** on the same two Sparks:
1. **DS4 first** until `/v1/models` healthy
2. **H3 second** (this image)
3. Power Pack util **0.76** / 888k (or ≤ **0.85** hard cap)
4. Teardown: **H3 → DS4**
5. One heavy video job per Spark (`concurrency=2` = two boxes)
Full dual-boot recipe: Power Pack `deploy/keyspark/bringup.sh`.
---
## A/V glitch mitigations (baked into graphs)
| Fix | Setting |
|-----|---------|
| Spectrum speech stutter | `offline_smoothing_replay=true`, `audio_blend_weight=0` |
| Multishot seams | Motion Context / Contex-Loop / MultiRef |
| Long-gen hallucination | master-K0 short parallel spans (not one long gen) |
---
## Weights (not fully redistributed here)
Place under `models/` (bind-mount into the container):
| File | Role |
|------|------|
| `diffusion_models/minimax_h3_fl2va_pruned_bf16.safetensors` | FL2VA DiT — **FINALS (sealed)** |
| `diffusion_models/minimax_h3_ref2va_pruned_bf16.safetensors` | ref2va — **FINALS (sealed)** |
| `diffusion_models/minimax_h3_fl2va_pruned_int8_convrot.safetensors` | FL2VA DiT — draft tier only |
| `diffusion_models/minimax_h3_ref2va_pruned_int8_convrot.safetensors` | ref2va — draft tier only |
| `text_encoders/qwen3vl_32b_minimax_h3_int8_convrot.safetensors` | **STOCK int8-convrot TE** (sealed; heretic retired) |
| `vae/minimax_h3_video_vae_fp16.safetensors` | video VAE |
| `vae/minimax_h3_audio_vae_fp32.safetensors` | audio VAE |
| `upscale_models/RealESRGAN_x2plus.pth` | 2K upscale |
| `loras/h3-realism-people-t2v-i2v-r2v.safetensors` | optional realism |
Helpers: `scripts/fetch_weights.sh`
Upstream: [Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3), [Kijai/MiniMax-H3_comfy](https://huggingface.co/Kijai/MiniMax-H3_comfy).
---
## Verify (agents must pass)
```bash
bash scripts/verify_h3_stack.sh 10.100.10.1
bash scripts/verify_h3_stack.sh 10.100.10.5
```
Fails if Spectrum audio-fix default is wrong or core nodes are missing.
---
## Credits
| | |
|--|--|
| Dual-serve co-tenancy | **Tony / [tonyd2wild](https://github.com/tonyd2wild)** — [ds4-h3-video-gen-factory](https://github.com/tonyd2wild/ds4-h3-video-gen-factory) |
| Spectrum v0.2.1 audio fix | xmarre / ComfyUI-Spectrum-MiniMax-H3 |
| Motion Context | NikoDemon80 |
| MultiRef | seitanism |
| Contex-Loop | ethanfel |
| NKD Preview | Nekodificador |
| Sol / Sage / heretic | NVIDIA Sol-engine community · KJNodes · sakamakismile et al. |
| Packaging | keyspark / [@drowzeys](https://huggingface.co/drowzeys) Power Pack |
---
## License
- Package scripts/docs: see Power Pack repo
- Model weights: **their respective licenses** (not all redistributed here)
- ComfyUI and custom nodes: upstream licenses (GPL where applicable)