Rebaked a WAI-Anima character LoRA onto upstream Anima-Base with off-distribution Gemini data. Trigger-only usable, face fidelity beats v1, intakes still cap out.
Tested on M1 Max 64GB ComfyUI: one character LoRA across 6 Anima derivatives, same prompt/seed. Trigger-only never stabilizes, RDBT bolts to beast-ears, structure tags fix it.
Tested on M1 Max ComfyUI: two WAI-Anima character LoRAs in one image. Side-by-side works, but only non-overlapping inpaint keeps the design pixel-exact; Qwen-Image-Edit elongates the side ponytail even with training tags, and overlapping interaction poses jam at skeleton extraction.
WAI-Anima LoRA trained only on images the model itself made. Distribution shift drops to ~zero, so the sweet spot hits epoch 20 not 150 (7.5x faster). What the trigger bakes in vs what still needs tags, plus pose/angle control.
Hands-on with Tencent Hy-MT2 1.8B Q4_K_M (1.08GB) on M1 Max 64GB via llama-server. JSON, SRT, HTML, glossary, and minority-language prompts with full input-output pairs. The 1.25bit 440MB build does not load on stock llama.cpp 8990, and 30B-A3B (hy_v3) is not in the Mac route yet.
Tested on ComfyUI with Anima Turbo LoRA: hair intakes don't fire from the single tag. The 27-condition recipe — character NL reference + negative identity strip + (hair intakes:1.5) + 22.5° upper-front camera — also revealed the generic prompt was accidentally a Blue Archive character spec, and that Kanon's whole female cast has intakes as a cluster prior.
On M1 Max with Anima-Base v1.0 and WAI-Anima v1: the official negative is short. Trim the long Illustrious bad-hands list, move structure to positive tags, keep `safe` upfront.
Ran WAI-Anima v1.0 with a custom character LoRA on an M1 Mac to see if 2- and 3-character compositions actually hold up. Notes on what breaks and what holds at different LoRA weights, with practical settings that stay stable.
On M1 Max 64GB, SetLatentNoiseMask returns unchanged images with no error. LanPaint alone takes 32 min; adding Crop-and-Stitch drops text inpaint to 2:31.
Tested MinishLab/semble on a 1595-md Astro blog: warm bm25 returns symbol definitions in 0.84s, hybrid mode loses `seasonalBanner` to the article corpus.
Tested on M1 Max 64GB ComfyUI: Anima-Base v1.0 matches preview3-base in speed; WAI-Anima kana LoRA hits 22% on light prompts but 67% with hood+robe+embroidery added.
