ANIMA_BOOSTER for ComfyUI ⚡
The ultimate high-performance optimization suite designed to maximize inference speed and optimize the performance of the Anima DiT 2B model.
Delivers a massive 3.5× to 5.0× speedup with virtually no loss in visual quality!
> 💡 Ultimate Quality & Speed Combo:
> We highly recommend pairing this optimization suite with our companion node FLSampler (BSS) to perfectly restore any lost micro-details at lightning-fast speeds!
🔗 GitHub Repository (Full Guide & Docs): https://github.com/BlackSnowSkill/ANIMA_BOOSTER
🌟 Key Features (v1.3.0)
📥 Anima Checkpoint & UNET Loaders: Tailored loaders supporting standalone UNETs and full Checkpoints with built-in bfloat16 auto-detection.
⚡ Safe One-Click torch.compile: Stable JIT compilation toggle boosting speed by 20% to 40%.
🚀 SageAttention: Integrated accelerated 8-bit attention tailored for DiT.
🧠 Adaptive TeaCache: Timestep-aware latent caching that skips redundant calculations, protecting early structural steps.
🎨 BSS Premium UI: Elegant, high-contrast dark-matte interface with clean controls and zero intrusive tooltips.
📂 Quick Installation
1. Open ComfyUI Manager -> Install via Git URL.
2. Paste this URL: https://github.com/BlackSnowSkill/ANIMA_BOOSTER
3. Click Install and restart ComfyUI.
For detailed parameters, portable environment wheels, and manual installation, please refer to the GitHub README
☕ Support & License
Support Development: Support me and get exclusive models on Boosty!
License & Usage: © 2026 blacksnowskill (BSS). All rights reserved. This project is protected by copyright. Copying, distribution, merging, or use on other websites/repositories without explicit written permission is strictly prohibited.
Description
What's New
🧹 Streamlined Interface Removed non-functional options that caused crashes with Anima DiT models:
Removed
weight_dtypeselector — Anima models are natively bfloat16. Forcing FP8 causedLayerNormKernelImpl not implemented for Float8_e4m3fncrashes because PyTorch does not support FP8 in RMSNorm operations used by DiT architectures. The loader now always uses the optimal native dtype.Removed
compile_modeselector — Modesreduce-overheadandmax-autotuneuse CUDA Graphs internally, which conflict with Anima's in-place tensor operations, causingCUDAGraphs tensor overwrittenerrors. The loader now always uses the stabledefaultcompilation mode.
🔬 SageAttention Fix
Fixed a critical bug where selecting specific quantization kernels (sageattn_qk_int8_pv_fp16_cuda / fp8) silently failed due to API changes in sageattention >= 1.0.6. The library migrated from C++ extensions to Triton kernels and removed those functions from the public API. The node now correctly uses the auto mode which delegates to ComfyUI's built-in SageAttention integration — this automatically selects the optimal quantization strategy for your GPU.
📦 New: Checkpoint Loader Added Anima Booster Checkpoint Loader — a new node for loading bundled Anima checkpoints that contain Model + CLIP + VAE in a single file. Outputs all three components while applying the same SageAttention and torch.compile optimizations as the standard Anima Booster Loader.
⚡ Clean Node Design Both loaders now feature a minimal, crash-proof interface:
Model selector
SageAttention toggle (auto / disabled)
torch.compile toggle (on / off)
No unnecessary options that could lead to errors. Just plug in and generate.