AGGA 2026: The Sampler & Scheduler Pack
세부 정보
파일 다운로드
이 버전에 대해
모델 설명
Yep: Intelligent Rendering Engine for Stable Diffusion (A1111 / Forge / ComfyUI)
You're probably wondering: "Are you still alive...?" No. Well... actually, I'm back with something juicy. The truth is, I'm in the red and I simply refuse to buy another external hard drive just to fill it with thousands of LoRAs.
So, instead of more gigabytes, I brought you Intelligence. There are always new LoRAs, LyCORIS, and VAEs, but nobody looks at the "brain" of the checkpoint. We need to make it smarter, not just limit ourselves to the classics.
This is not just a set of scripts; it is an intelligent rendering engine designed for Stable Diffusion. While standard samplers traverse noise linearly, AGGA uses latent masks, dynamic momentum, and temporal anchors to ensure every pixel has a purpose.
Compatibility Note: These samplers and schedulers are fully cross-compatible with the original A1111/Forge samplers. You can mix standard samplers with AGGA schedulers and vice versa.
⚠️ Installation (The "Core Touch" Method)
I had some issues wrapping this as a standard extension (too much overhead), so I went for the most efficient, "Power User" route: Direct Core Integration. It's faster, lighter, and works natively in A1111 and WebUI Forge.
Step 1: Drop the .py files into your modules folder.
Step 2: Open modules/sd_schedulers.py and add this line at the very end:
Python
import modules.sd_agga_schedulers
Step 3: Open modules/sd_samplers_kdiffusion.py and add this line at the very end:
Python
import modules.sd_samplers_pseudo_hires_loader
That's it. No complex installation, just pure python logic injection.
🧠 The "Landing Phase" Concept
The main difference between AGGA and standard tools lies in the Landing Phase and Noise Injection. Standard samplers often "wash out" details in the final 20% of steps to eliminate noise. AGGA does the opposite: it detects where the edges and textures are and reinforces detail just before finishing.
🛠️ Sampler Guide (Movement Engines)
The "Pseudo-Hires" Series (General Purpose)
Pseudo-Hires Soft: The base engine. It uses a pure Euler trajectory with a custom noise ramp for a balanced composition without artifacts.
Pseudo-Hires Sharp: Introduces an energy reinforcement of 1.12x in the last third of generation (step > 65%), ideal for defining metallic edges and hard textures.
Pseudo-Hires Ultra: Our most aggressive configuration. It applies a progressive boost that scales up to
1.18 + progress * 0.10to maximize detail in hair and skin.DPM++ 2M Pseudo-Hires: A second-order version for those who prefer DPM stability, but with an extra "push" at the end to avoid that typical soft/washed-out look of standard DPM.
AGGA Pseudo-Hires Flash v2: Optimized for speed. It uses a stronger DPM correction (0.6 / 0.4) and a final refinement of 15% to eliminate blur in low-step counts.
The "Native" Series (Detail & Structure)
AGGA Detail-Native: An internal "Refiner" mode. In the last 40% of generation, it "tricks" the model with a lower sigma to force it to draw micro-details like pores and fine hairs without changing the composition.
AGGA Structural-Detail (Hybrid) [NEW]: The best of both worlds. The first 45% uses DPM++ 2M logic for perfect anatomical coherence, then seamlessly switches to the AGGA Detail engine to inject texture. Perfect for complex bodies.
AGGA Hyper-Detail Hybrid: Splits generation into two distinct phases: the first 66% is dedicated to clean structure (V2) and the rest to aggressive edge refinement (V4).
The "Specialist" Series
AGGA DMD-Turbo Landing: Specifically for distilled models (Lightning/Turbo/4-8 steps). It replaces the last Euler step with a direct interpolation toward the clean image for a "crystalline" finish.
AGGA Herrscher-Native: Momentum-based engine (0.50). Includes a recovery system that "pushes" tensor energy if it drops below 1.0, keeping colors and contrast vibrant.
AGGA Style-Repair: Designed to rescue the essence of Checkpoints. It extracts a "Style-Delta" by perturbing noise every 3 steps to recover concepts diluted by the model.
AGGA Style-Repair Ultra: The definitive version for a "Studio Look". It includes an atmospheric mask that protects the background while repairing the 3D volume of the main subject.
AGGA Pixel-Master: A latent quantization engine. It forces the model to work on a fixed pixel grid and a limited color palette. Use this for authentic Latent Pixel Art.
📐 Scheduler Guide (Noise Maps)
The scheduler decides how much "strength" the noise has at each step. AGGA offers maps that standard schedulers cannot replicate.
Intelligent & Adaptive
AGGA Smart: Intelligent logic. If you set ≤ 8 steps, it automatically uses a Rho 7.0 power curve (DMD). If you set more, it activates Dynamic Rho for maximum quality.
Dynamic Rho: The value of ρ evolves from 5.0 to 9.0. This provides a very stable structure at the beginning (low rho) and ultra-fine refinement at the end (high rho).
Anchors (Temporal Warping)
Style-Anchor: Creates a sinusoidal time "plateau" in the style sigmas. The sampler spends more real-time processing the middle steps where aesthetics are defined.
Ultra-Anchor: Reinforced version of the anchor (factor 0.32). Creates a pseudo-plateau where time seems to stop to inject the maximum amount of style possible.
Double-Anchor (The Sniper): Our most advanced scheduler. It combines style anchoring with a "sniper" dip at 82% of the process to fix critical details like eyes and faces.
AGGA AYS-Anchor [NEW]: Combines NVIDIA's "Align Your Steps" (AYS) optimized values with AGGA's anchor warping. It uses the scientifically calculated AYS steps but warps the time to focus on concept formation.
Specialized
AGGA DMD: Extreme power curve (ρ = 7.0). Ideal for Lightning or Turbo models, concentrating detail in the early steps.
Log-Linear: A perfect logarithmic distribution. The "gold standard" for the Detail-Native sampler, ensuring a noise transition without abrupt jumps.
Pixel-Staircase V1 & V2: A staircase of sigmas. It groups steps (e.g., 3 by 3) so the sampler has time to "settle" the pixel quantization before dropping to the next noise level. V2 adds "Edge Locking" for cleaner sprites.
