Create first optimized workflow masters
This commit is contained in:
Morpheus
@@ -11,3 +11,12 @@ Use it to capture:
|
||||
- what should be ignored next time
|
||||
|
||||
These notes exist so future review passes do not have to re-trawl every collected workflow from scratch.
|
||||
|
||||
## Current note files
|
||||
|
||||
- `flux.md`
|
||||
- `flux2klein.md`
|
||||
- `ltx.md`
|
||||
- `minimax.md`
|
||||
- `zimage.md`
|
||||
- `reviews/`
|
||||
|
||||
@@ -0,0 +1,35 @@
|
||||
# LTX Notes
|
||||
|
||||
## Current default assumptions
|
||||
|
||||
- Low-VRAM practicality matters more than graph sophistication.
|
||||
- The first question is whether `LTX 2.3` is usable at all on Chris's `3070`.
|
||||
|
||||
## Strong current source workflows
|
||||
|
||||
- `models/ltx/ltx23-i2v-t2v-simple-single-pass/`
|
||||
- `models/ltx/ltx23-t2v-simple-single-pass/`
|
||||
- `models/ltx/ltx23-first-last-frame/`
|
||||
- `models/ltx/ltx23-character-sheet-best-face-id/`
|
||||
|
||||
## Strong current heuristics
|
||||
|
||||
- Start with simple single-pass before trying larger consistency graphs.
|
||||
- Prefer split-model and extracted-model routes when the source pack says they are easier locally.
|
||||
- Treat first-last-frame and character-sheet workflows as second-wave tests, not the baseline.
|
||||
|
||||
## Current weak areas
|
||||
|
||||
- No real proof yet for what is genuinely practical on Chris's box.
|
||||
- Community packs bundle lots of helper nodes, which raises import fragility.
|
||||
|
||||
## Best current optimization direction
|
||||
|
||||
- Keep `optimized/image-to-video/ltx23-3070-simple-master/` as the first `LTX` default.
|
||||
- Only promote first-last-frame or character-sheet variants after the simple master proves viable.
|
||||
|
||||
## What needs Monday proof
|
||||
|
||||
- whether the simple master loads and runs at all on the `3070`
|
||||
- whether preview/decode or the core model path is the real bottleneck
|
||||
- whether `LTX` has any realistic chance of displacing `MiniMax` for local use
|
||||
@@ -0,0 +1,35 @@
|
||||
# MiniMax Notes
|
||||
|
||||
## Current default assumptions
|
||||
|
||||
- `MiniMax H3` is promising, but brute-force paths are too heavy to be the first bet on a `3070`.
|
||||
- Speed-first and low-VRAM community workflows matter more than official purity for the first real test.
|
||||
|
||||
## Strong current source workflows
|
||||
|
||||
- `models/minimax/minimax-h3-official-t2v/`
|
||||
- `models/minimax/minimax-h3-official-i2v/`
|
||||
- `models/minimax/minimax-h3-turbo-lora-community/`
|
||||
- `models/minimax/minimax-h3-int8-r2v-community/`
|
||||
|
||||
## Strong current heuristics
|
||||
|
||||
- Prefer Turbo LoRA for the first `text-to-video` attempt.
|
||||
- Prefer INT8-based community workflows for `reference-to-video` exploration.
|
||||
- Keep attention and memory-efficiency helpers if they are already integrated and well documented.
|
||||
|
||||
## Current weak areas
|
||||
|
||||
- No proof yet that MiniMax is truly practical on Chris's box.
|
||||
- Custom-node stack is more fragile than the current `flux2klein` path.
|
||||
|
||||
## Best current optimization direction
|
||||
|
||||
- Keep `optimized/text-to-video/minimax-h3-3070-turbo-master/` as the first MiniMax default.
|
||||
- Keep the INT8 reference-video workflow as the next donor for future low-VRAM optimization.
|
||||
|
||||
## What needs Monday proof
|
||||
|
||||
- whether the Turbo LoRA workflow is just technically possible or actually usable
|
||||
- whether the source-recommended `8`-step path holds up in quality
|
||||
- whether MiniMax feels like a real challenger to `LTX` locally
|
||||
@@ -13,7 +13,7 @@
|
||||
2. `zimage`
|
||||
3. `ltx`
|
||||
4. `minimax`
|
||||
4. category masters in:
|
||||
5. category masters in:
|
||||
- `image-edit`
|
||||
- `image-to-video`
|
||||
- `text-to-video`
|
||||
|
||||
@@ -0,0 +1,42 @@
|
||||
# Optimization Review 2026-08-08
|
||||
|
||||
## Scope
|
||||
|
||||
First manual optimization pass before the Sunday cadence has enough historical material to build from.
|
||||
|
||||
## Created masters
|
||||
|
||||
- `optimized/text-to-image/zimage-turbo-3070-fast-start/`
|
||||
- `optimized/image-edit/zimage-turbo-3070-inpaint-start/`
|
||||
- `optimized/image-edit/flux2klein-9b-fp8-edit-master/`
|
||||
- `optimized/image-to-video/ltx23-3070-simple-master/`
|
||||
- `optimized/text-to-video/minimax-h3-3070-turbo-master/`
|
||||
|
||||
## Source workflows used
|
||||
|
||||
- `models/zimage/z-image-turbo-official-example/`
|
||||
- `models/zimage/z-image-turbo-inpainting-community/`
|
||||
- `models/flux2klein/image-edit-9b-distilled/`
|
||||
- `models/ltx/ltx23-i2v-t2v-simple-single-pass/`
|
||||
- `models/minimax/minimax-h3-turbo-lora-community/`
|
||||
|
||||
## What was optimized in this pass
|
||||
|
||||
- Chose low-complexity or speed-first baselines instead of heavier graphs.
|
||||
- Aligned `flux2klein` with Chris's `9B fp8` preference.
|
||||
- Treated `LTX` and `MiniMax` as "prove viability first" families.
|
||||
- Added durable notes so future passes can build on judgments instead of re-reading everything.
|
||||
|
||||
## What was deliberately not done
|
||||
|
||||
- no graph surgery without testing
|
||||
- no blind node removal
|
||||
- no fake "one workflow to rule them all" claims
|
||||
- no promotion of first-last-frame or INT8 reference-video paths to default status yet
|
||||
|
||||
## Monday proof needed
|
||||
|
||||
- whether the two `Z-Image` masters are actually lighter and pleasant to use
|
||||
- whether `flux2klein 9B distilled` behaves well enough for edit/outpaint work
|
||||
- whether the `LTX` simple master is viable on a `3070`
|
||||
- whether `MiniMax Turbo` is practically usable or still too tight
|
||||
Reference in New Issue
Block a user