Upload model using ModelScope SDK

.gitattributes

@@ -1,35 +1,75 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -textassets/minimax_h3_fl2va_dit_4bpp.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/minimax_h3_fl2va_dit_5bpp.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/minimax_h3_fl2va_dit_6bpp.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/minimax_h3_fl2va_dit_7bpp.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/minimax_h3_fl2va_dit_8bpp.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/minimax_h3_fl2va_dit_extreme_3.0bpp.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/minimax_h3_fl2va_dit_fp8_5bpp.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/minimax_h3_ref2va_dit_4bpp.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/minimax_h3_ref2va_dit_5bpp.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/minimax_h3_ref2va_dit_6bpp.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/minimax_h3_ref2va_dit_7bpp.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/minimax_h3_ref2va_dit_8bpp.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/minimax_h3_ref2va_dit_extreme_3.0bpp.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/minimax_h3_ref2va_dit_fp8_5bpp.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/minimax_h3_ref2va_reference_woman.png filter=lfs diff=lfs merge=lfs -text
+assets/qwen_image_2.1_dit_4bpp.png filter=lfs diff=lfs merge=lfs -text
+assets/qwen_image_2.1_dit_5bpp.png filter=lfs diff=lfs merge=lfs -text
+assets/qwen_image_2.1_dit_6bpp.png filter=lfs diff=lfs merge=lfs -text
+assets/qwen_image_2.1_dit_7bpp.png filter=lfs diff=lfs merge=lfs -text
+assets/qwen_image_2.1_dit_8bpp.png filter=lfs diff=lfs merge=lfs -text
+assets/qwen_image_2.1_dit_extreme_3.0bpp.png filter=lfs diff=lfs merge=lfs -text
+assets/qwen_image_2.1_dit_fp8_5bpp.png filter=lfs diff=lfs merge=lfs -text
+assets/z_image_turbo_dit_4bpp.jpg filter=lfs diff=lfs merge=lfs -text
+assets/z_image_turbo_dit_5bpp.jpg filter=lfs diff=lfs merge=lfs -text
+assets/z_image_turbo_dit_6bpp.jpg filter=lfs diff=lfs merge=lfs -text
+assets/z_image_turbo_dit_7bpp.jpg filter=lfs diff=lfs merge=lfs -text
+assets/z_image_turbo_dit_8bpp.jpg filter=lfs diff=lfs merge=lfs -text
+assets/z_image_turbo_dit_extreme_2.3bpp.jpg filter=lfs diff=lfs merge=lfs -text
+assets/z_image_turbo_dit_fp8_5bpp.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,224 @@
+# EntroPack Pre-Quantized Models
+
+This repository releases pre-quantized weight packages produced by [**EntroPack**](https://github.com/modelscope/entropack) for representative SOTA diffusion models, to be used with the quantization features of [**DiffSynth-Studio**](https://github.com/modelscope/DiffSynth-Studio):
+
+- **Z-Image-Turbo** (DiT + text encoder)
+- **Qwen-Image-2.1** (DiT + text encoder)
+- **MiniMax-H3** (two DiTs, FL2VA / Ref2VA, sharing the text encoder and video VAE)
+
+For each model, both the **DiT and the text encoder** are provided at five fine-grained compression rates (4 / 5 / 6 / 7 / 8 bpp), plus two kinds of specialized packages:
+
+- **`fp8@5`** (`dit_fp8_5bpp`): the weights are first **FP8 W8A8-quantized** (8-bit fp8 codes), then entropy-coded by EntroPack down to **5-bit storage** (actual bpp = 5); the forward pass uses **FP8 GEMM** for faster inference;
+- **Extreme mixed-bit packages**: bit-rate is allocated per layer by sensitivity (the most sensitive layers keep a high bpp while the rest use a low bpp), pushing the whole model to a much lower bpp (Z-Image-Turbo 2.3bpp / Qwen-Image-2.1 3.0bpp / MiniMax-H3 3.0bpp).
+
+All packages are built by entropy-coding the original weights directly with EntroPack; the metrics in the tables are weighted measurements on the package artifacts:
+
+- **bpp** (bits per parameter): average bits per weight, `bpp = 8 × Σ storage bytes / Σ numel`.
+- **Linear weight compression ratio**: derived from bpp, `ratio = bpp / 16`.
+- **Weight reconstruction error** (DiT only): relative deviation between the dequantized and the original weights, `sqrt(Σ‖Wq−W‖²) / sqrt(Σ‖W‖²)`.
+- **Registration entry**: each `*.safetensors` ships with a same-named `*.json`; see the end of this document for loading.
+
+Validation outputs (images / videos) for each model can be found under `assets/`.
+
+## Update History
+
+**2026-10-15 — checkpoints repacked under new key names.** All packages in this repository were repacked
+into the single-entry container layout: a compressed layer's whole encoding now lives under one
+`<layer>.weight.entropack_quant_state` tensor, and the W8A8 row scale under `<layer>.weight_quant_scale`.
+The **updated** weights require **entropack 0.1.3**; the packages published before this update pair with
+**entropack ≤ 0.1.2**.
+
+## Z-Image-Turbo
+
+### DiT
+
+| name | file | actual bpp | weight reconstruction error | size |
+|---|---|---|---|---|
+| dit_4bpp | `models/Z-Image-Turbo/dit_4bpp.safetensors` | 4.024 | 7.013% | 2.88 GB |
+| dit_5bpp | `models/Z-Image-Turbo/dit_5bpp.safetensors` | 5.046 | 3.630% | 3.62 GB |
+| dit_6bpp | `models/Z-Image-Turbo/dit_6bpp.safetensors` | 6.055 | 1.854% | 4.34 GB |
+| dit_7bpp | `models/Z-Image-Turbo/dit_7bpp.safetensors` | 7.070 | 0.971% | 5.07 GB |
+| dit_8bpp | `models/Z-Image-Turbo/dit_8bpp.safetensors` | 8.060 | 0.532% | 5.78 GB |
+| dit_fp8_5bpp | `models/Z-Image-Turbo/dit_fp8_5bpp.safetensors` | 5.041 | 4.648% | 3.62 GB |
+| dit_extreme_2.3bpp | `models/Z-Image-Turbo/dit_extreme_2.3bpp.safetensors` | 2.319 | 24.007% | 1.66 GB |
+| nf4 (bitsandbytes) (for comparison) | - | 4.127 | 9.415% | - |
+| torchao int8 w8a16 (for comparison) | - | 8.012 | 1.078% | - |
+| torchao fp8 w8a16 (for comparison) | - | 8.010 | 2.650% | - |
+
+### Text Encoder
+
+| name | file | actual bpp | size |
+|---|---|---|---|
+| text_encoder_4bpp | `models/Z-Image-Turbo/text_encoder_4bpp.safetensors` | 4.028 | 2.43 GB |
+| text_encoder_5bpp | `models/Z-Image-Turbo/text_encoder_5bpp.safetensors` | 5.051 | 2.86 GB |
+| text_encoder_6bpp | `models/Z-Image-Turbo/text_encoder_6bpp.safetensors` | 6.058 | 3.29 GB |
+| text_encoder_7bpp | `models/Z-Image-Turbo/text_encoder_7bpp.safetensors` | 7.061 | 3.71 GB |
+| text_encoder_8bpp | `models/Z-Image-Turbo/text_encoder_8bpp.safetensors` | 8.041 | 4.13 GB |
+
+### Extreme Mixed-Bit Package
+
+The extreme package `dit_extreme_2.3bpp` uses mixed quantization (per-layer-group bit allocation, weighted target = 2.3bpp): modulation / embedding / adaLN / final layers (38 layers) @ **4.0bpp**, attention output projections `*.attention.to_out.0` (34 layers) @ **3.0bpp**, and the remaining 204 layers @ **2.1939bpp**. Measured 2.319bpp / weight reconstruction error 24.0%.
+
+## Qwen-Image-2.1
+
+### DiT
+
+| name | file | actual bpp | weight reconstruction error | size |
+|---|---|---|---|---|
+| dit_4bpp | `models/Qwen-Image-2.1/dit_4bpp.safetensors` | 4.027 | 7.064% | 3.34 GB |
+| dit_5bpp | `models/Qwen-Image-2.1/dit_5bpp.safetensors` | 5.052 | 3.658% | 4.19 GB |
+| dit_6bpp | `models/Qwen-Image-2.1/dit_6bpp.safetensors` | 6.066 | 1.868% | 5.02 GB |
+| dit_7bpp | `models/Qwen-Image-2.1/dit_7bpp.safetensors` | 7.085 | 0.978% | 5.87 GB |
+| dit_8bpp | `models/Qwen-Image-2.1/dit_8bpp.safetensors` | 8.068 | 0.536% | 6.68 GB |
+| dit_fp8_5bpp | `models/Qwen-Image-2.1/dit_fp8_5bpp.safetensors` | 5.048 | 4.662% | 4.19 GB |
+| dit_extreme_3.0bpp | `models/Qwen-Image-2.1/dit_extreme_3.0bpp.safetensors` | 3.023 | 14.247% | 2.50 GB |
+| nf4 (bitsandbytes) (for comparison) | - | 4.127 | 9.428% | - |
+| torchao int8 w8a16 (for comparison) | - | 8.008 | 1.095% | - |
+| torchao fp8 w8a16 (for comparison) | - | 8.007 | 2.648% | - |
+
+### Text Encoder
+
+| name | file | actual bpp | size |
+|---|---|---|---|
+| text_encoder_4bpp | `models/Qwen-Image-2.1/text_encoder_4bpp.safetensors` | 4.034 | 4.99 GB |
+| text_encoder_5bpp | `models/Qwen-Image-2.1/text_encoder_5bpp.safetensors` | 5.062 | 5.97 GB |
+| text_encoder_6bpp | `models/Qwen-Image-2.1/text_encoder_6bpp.safetensors` | 6.082 | 6.93 GB |
+| text_encoder_7bpp | `models/Qwen-Image-2.1/text_encoder_7bpp.safetensors` | 7.092 | 7.89 GB |
+| text_encoder_8bpp | `models/Qwen-Image-2.1/text_encoder_8bpp.safetensors` | 8.072 | 8.82 GB |
+
+### Extreme Mixed-Bit Package
+
+The extreme package `dit_extreme_3.0bpp` uses mixed quantization (weighted target = 3.0bpp): modulation-related layers (`modulation.1`, `norm_out.linear`, `time_text_embed.*`, 4 layers) @ **4.0bpp**, and the remaining 228 layers @ **2.9855bpp**. Measured 3.023bpp / weight reconstruction error 14.2%.
+
+
+## MiniMax-H3
+
+### DiT
+
+| name | file | actual bpp | weight reconstruction error | size |
+|---|---|---|---|---|
+| fl2va_dit_4bpp | `models/MiniMax-H3/FL2VA/dit_4bpp.safetensors` | 4.038 | 6.567% | 15.58 GB |
+| ref2va_dit_4bpp | `models/MiniMax-H3/REF2VA/dit_4bpp.safetensors` | 4.038 | 6.567% | 15.58 GB |
+| fl2va_dit_5bpp | `models/MiniMax-H3/FL2VA/dit_5bpp.safetensors` | 5.065 | 3.392% | 19.54 GB |
+| ref2va_dit_5bpp | `models/MiniMax-H3/REF2VA/dit_5bpp.safetensors` | 5.065 | 3.392% | 19.54 GB |
+| fl2va_dit_6bpp | `models/MiniMax-H3/FL2VA/dit_6bpp.safetensors` | 6.081 | 1.734% | 23.45 GB |
+| ref2va_dit_6bpp | `models/MiniMax-H3/REF2VA/dit_6bpp.safetensors` | 6.082 | 1.732% | 23.46 GB |
+| fl2va_dit_7bpp | `models/MiniMax-H3/FL2VA/dit_7bpp.safetensors` | 7.093 | 0.911% | 27.36 GB |
+| ref2va_dit_7bpp | `models/MiniMax-H3/REF2VA/dit_7bpp.safetensors` | 7.095 | 0.908% | 27.37 GB |
+| fl2va_dit_8bpp | `models/MiniMax-H3/FL2VA/dit_8bpp.safetensors` | 8.081 | 0.500% | 31.16 GB |
+| ref2va_dit_8bpp | `models/MiniMax-H3/REF2VA/dit_8bpp.safetensors` | 8.079 | 0.500% | 31.16 GB |
+| fl2va_dit_fp8_5bpp | `models/MiniMax-H3/FL2VA/dit_fp8_5bpp.safetensors` | 5.058 | 4.510% | 19.54 GB |
+| ref2va_dit_fp8_5bpp | `models/MiniMax-H3/REF2VA/dit_fp8_5bpp.safetensors` | 5.058 | 4.510% | 19.54 GB |
+| fl2va_dit_extreme_3.0bpp | `models/MiniMax-H3/FL2VA/dit_extreme_3.0bpp.safetensors` | 3.026 | 13.225% | 11.68 GB |
+| ref2va_dit_extreme_3.0bpp | `models/MiniMax-H3/REF2VA/dit_extreme_3.0bpp.safetensors` | 3.026 | 13.225% | 11.68 GB |
+| nf4 (bitsandbytes) (for comparison) | - | 4.127 | 9.151% | - |
+| torchao int8 w8a16 (for comparison) | - | 8.010 | 0.984% | - |
+| torchao fp8 w8a16 (for comparison) | - | 8.008 | 2.642% | - |
+
+### Text Encoder
+
+| name | file | actual bpp | size |
+|---|---|---|---|
+| text_encoder_4bpp | `models/MiniMax-H3/text_encoder_4bpp.safetensors` | 4.039 | 13.20 GB |
+| text_encoder_5bpp | `models/MiniMax-H3/text_encoder_5bpp.safetensors` | 5.073 | 16.21 GB |
+| text_encoder_6bpp | `models/MiniMax-H3/text_encoder_6bpp.safetensors` | 6.102 | 19.20 GB |
+| text_encoder_7bpp | `models/MiniMax-H3/text_encoder_7bpp.safetensors` | 7.127 | 22.18 GB |
+| text_encoder_8bpp | `models/MiniMax-H3/text_encoder_8bpp.safetensors` | 8.095 | 24.99 GB |
+
+### Video VAE
+
+| name | file | actual bpp | size |
+|---|---|---|---|
+| video_vae_4bpp | `models/MiniMax-H3/video_vae_4bpp.safetensors` | 4.020 | 1.47 GB |
+| video_vae_5bpp | `models/MiniMax-H3/video_vae_5bpp.safetensors` | 5.040 | 1.76 GB |
+| video_vae_6bpp | `models/MiniMax-H3/video_vae_6bpp.safetensors` | 6.045 | 2.04 GB |
+| video_vae_7bpp | `models/MiniMax-H3/video_vae_7bpp.safetensors` | 7.055 | 2.33 GB |
+| video_vae_8bpp | `models/MiniMax-H3/video_vae_8bpp.safetensors` | 8.056 | 2.61 GB |
+
+### Extreme Mixed-Bit Package
+
+The extreme package `dit_extreme_3.0bpp` (identical configuration for FL2VA / Ref2VA) uses mixed quantization (weighted target = 3.0bpp): low-dimensional patch/final modules (`time_embedder.proj_in/proj_out`, `video/audio_patch_proj`, `condition_proj`, `final_layer.video_out/audio_out`, 7 layers) @ **8.0bpp**, modulation (`*.adaln_proj.linear`, 51 layers) and `attn.out_proj` (52 layers) @ **3.0bpp**, and the remaining 156 layers @ **2.9876bpp**. Measured 3.026bpp / weight reconstruction error 13.2%.
+
+## Usage
+
+### Install from Source
+
+```bash
+# DiffSynth-Studio
+git clone https://github.com/modelscope/DiffSynth-Studio.git
+cd DiffSynth-Studio && pip install -e .
+
+# EntroPack (pick the extra matching your CUDA version: cuda13 / cuda12)
+git clone https://github.com/modelscope/entropack.git
+cd entropack && pip install -e '.[cuda13]'
+```
+
+### Example Script (Z-Image-Turbo)
+
+```python
+"""
+Z-Image-Turbo — EntroPack pre-quantized inference example.
+
+Downloads the pre-quantized packages and their json sidecars from the
+`DiffSynth-Studio/EntroPackPreQuants` model repo (each json is a ready-to-use
+`MODEL_CONFIGS` entry), then runs inference.
+
+Available packages (paths inside the prequant model repo):
+
+    dit:
+        models/Z-Image-Turbo/dit_4bpp.safetensors             4bpp
+        models/Z-Image-Turbo/dit_5bpp.safetensors             5bpp
+        models/Z-Image-Turbo/dit_6bpp.safetensors             6bpp
+        models/Z-Image-Turbo/dit_7bpp.safetensors             7bpp
+        models/Z-Image-Turbo/dit_8bpp.safetensors             8bpp
+        models/Z-Image-Turbo/dit_extreme_2.3bpp.safetensors   mixed allocation, 2.3bpp
+        models/Z-Image-Turbo/dit_fp8_5bpp.safetensors         fp8 weights, 5bpp
+    text_encoder:
+        models/Z-Image-Turbo/text_encoder_4bpp.safetensors    4bpp
+        models/Z-Image-Turbo/text_encoder_5bpp.safetensors    5bpp
+        models/Z-Image-Turbo/text_encoder_6bpp.safetensors    6bpp
+        models/Z-Image-Turbo/text_encoder_7bpp.safetensors    7bpp
+        models/Z-Image-Turbo/text_encoder_8bpp.safetensors    8bpp
+
+`dit_package` and `text_encoder_package` are chosen independently: any combination works
+(e.g. `dit_8bpp` with `text_encoder_4bpp`).
+"""
+import json
+
+import torch
+
+from diffsynth.configs import MODEL_CONFIGS
+from diffsynth.pipelines.z_image import ZImagePipeline, ModelConfig
+
+prequant_model_id = "DiffSynth-Studio/EntroPackPreQuants"
+dit_package = "models/Z-Image-Turbo/dit_4bpp.safetensors"
+text_encoder_package = "models/Z-Image-Turbo/text_encoder_4bpp.safetensors"
+
+
+def register_prequantized(package_pattern):
+    """Download the pre-quantized package and its json sidecar (a ready-to-use MODEL_CONFIGS entry), return a loadable ModelConfig."""
+    package = ModelConfig(model_id=prequant_model_id, origin_file_pattern=package_pattern)
+    package.download_if_necessary()
+    sidecar = ModelConfig(model_id=prequant_model_id, origin_file_pattern=package_pattern.replace(".safetensors", ".json"))
+    sidecar.download_if_necessary()
+    with open(sidecar.path) as handle:
+        MODEL_CONFIGS.append(json.load(handle))
+    return package
+
+
+pipe = ZImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        register_prequantized(dit_package),
+        register_prequantized(text_encoder_package),
+        ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+    ],
+    tokenizer_config=ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="tokenizer/"),
+)
+prompt = "Young Chinese woman in red Hanfu, intricate embroidery. Impeccable makeup, red floral forehead pattern. Elaborate high bun, golden phoenix headdress, red flowers, beads. Holds round folding fan with lady, trees, bird. Neon lightning-bolt lamp (⚡️), bright yellow glow, above extended left palm. Soft-lit outdoor night background, silhouetted tiered pagoda (西安大雁塔), blurred colorful distant lights."
+image = pipe(prompt=prompt, seed=42, rand_device="cuda")
+image.save("image_Z-Image-Turbo-EntroPack.jpg")
+```
+
+`dit_package` and `text_encoder_package` can be chosen independently in any combination; the extreme and fp8 packages work in exactly the same way — just point to the corresponding `.safetensors` path (mixed-quantization `configs` and other details live in the same-named `.json`, no script changes needed). For Qwen-Image-2.1 and MiniMax-H3, swap in the corresponding pipeline and package paths.

assets/minimax_h3_fl2va_dit_4bpp.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3c820132ea422b6c6aeea52ec2133f769bdb1e1307edaa66c0bb6e6d8457db1
+size 20493430

assets/minimax_h3_fl2va_dit_5bpp.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f40aa364480b35a38ee26f856b4f6fdc9161a87362cb78c2ffb572e0519ef8c1
+size 19141428

assets/minimax_h3_fl2va_dit_6bpp.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47df7cc3f4780d25fc5671b275a2bdd1b832feadf55d695b8f1f3dd8f6535723
+size 17279249

assets/minimax_h3_fl2va_dit_7bpp.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1544df8e9160996b53b33c777c1f6d9179fbf7129fd0797c07653a4465b23f88
+size 16816039

assets/minimax_h3_fl2va_dit_8bpp.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881b4691e16ac0b5253fb1292fb70a0d2fea43b0254a44e9ac0e02f673f3a415
+size 16122668

assets/minimax_h3_fl2va_dit_extreme_3.0bpp.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c7a1986fba2db7fadb0950a2749ee77fe616210ae7fbffb03742b09141de68d
+size 29696339

assets/minimax_h3_fl2va_dit_fp8_5bpp.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1897a3d014bee8edd56ac58a76552deb6ec2403026bcd97ddb6a5f1e4619ad4
+size 16393608

assets/minimax_h3_ref2va_dit_4bpp.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbd52567fa0c8a2c0146ac090e0963f9f0e92c8b24fd6db5bd757bcebcf3cea0
+size 24277888

assets/minimax_h3_ref2va_dit_5bpp.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b559bf47f0a89f876df19815f9a02285324cc3791e215e299b3baf320cb1a81
+size 17917329

assets/minimax_h3_ref2va_dit_6bpp.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fbd1bff45719c41fd9eb9fd70f736899b4b1e571cb5aa56cb4cf9b0b5e16a43
+size 13943028

assets/minimax_h3_ref2va_dit_7bpp.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40b63d9cbd1041c46a483eefc1350d91ccffdc2c7407a630c3c32ea35988df22
+size 12921232

assets/minimax_h3_ref2va_dit_8bpp.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b240f3b569cb1d575154ff05512f103ba6f3a266603f22fc0912d4cd14589fa
+size 12527535

assets/minimax_h3_ref2va_dit_extreme_3.0bpp.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cfb1350ffd0cb8ecbaa67b6f65a879a872be28646aa8a8cb7dedb0e00fa2098
+size 24864847

assets/minimax_h3_ref2va_dit_fp8_5bpp.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b600c61f47a9493a5292247920dd02dad85fd0e2603a0fa77c75ce5d6615646
+size 17608131

configuration.json

@@ -0,0 +1 @@
+{"task":"text-to-image-synthesis"}

models/MiniMax-H3/FL2VA/dit_4bpp.json

@@ -0,0 +1,44 @@
+{
+  "model_hash": "612cc4c6e1da912c8ce01e63e113215f",
+  "model_name": "minimax_h3_dit",
+  "model_class": "diffsynth.models.minimax_h3_dit.MiniMaxH3DiT",
+  "quant_config": {
+    "load_prequantized": true,
+    "configs": [
+      {
+        "method": "entropack_lossy_quant",
+        "backend_config_kwargs": {
+          "target_bpp": 4.0,
+          "row_rdo_iterations": 2,
+          "row_rdo_candidates": 20
+        },
+        "exclude_modules": [
+          "time_embedder.proj_in",
+          "time_embedder.proj_out",
+          "video_patch_proj",
+          "audio_patch_proj",
+          "condition_proj",
+          "final_layer.video_out",
+          "final_layer.audio_out"
+        ]
+      },
+      {
+        "method": "entropack_lossy_quant",
+        "backend_config_kwargs": {
+          "target_bpp": 8.0,
+          "row_rdo_iterations": 2,
+          "row_rdo_candidates": 20
+        },
+        "target_modules": [
+          "time_embedder.proj_in",
+          "time_embedder.proj_out",
+          "video_patch_proj",
+          "audio_patch_proj",
+          "condition_proj",
+          "final_layer.video_out",
+          "final_layer.audio_out"
+        ]
+      }
+    ]
+  }
+}

models/MiniMax-H3/FL2VA/dit_4bpp.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bc847b6205a2efdaa30e8895c71433a6b3ed677563adff1c43a577e774dce29
+size 16726248296

models/MiniMax-H3/FL2VA/dit_5bpp.json

@@ -0,0 +1,44 @@
+{
+  "model_hash": "d3c067cb3761cd4dfc3d245a241062d4",
+  "model_name": "minimax_h3_dit",
+  "model_class": "diffsynth.models.minimax_h3_dit.MiniMaxH3DiT",
+  "quant_config": {
+    "load_prequantized": true,
+    "configs": [
+      {
+        "method": "entropack_lossy_quant",
+        "backend_config_kwargs": {
+          "target_bpp": 5.0,
+          "row_rdo_iterations": 2,
+          "row_rdo_candidates": 20
+        },
+        "exclude_modules": [
+          "time_embedder.proj_in",
+          "time_embedder.proj_out",
+          "video_patch_proj",
+          "audio_patch_proj",
+          "condition_proj",
+          "final_layer.video_out",
+          "final_layer.audio_out"
+        ]
+      },
+      {
+        "method": "entropack_lossy_quant",
+        "backend_config_kwargs": {
+          "target_bpp": 8.0,
+          "row_rdo_iterations": 2,
+          "row_rdo_candidates": 20
+        },
+        "target_modules": [
+          "time_embedder.proj_in",
+          "time_embedder.proj_out",
+          "video_patch_proj",
+          "audio_patch_proj",
+          "condition_proj",
+          "final_layer.video_out",
+          "final_layer.audio_out"
+        ]
+      }
+    ]
+  }
+}

models/MiniMax-H3/FL2VA/dit_5bpp.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb44baaf9a1e0fa98b9ed1cca900cc855de03ab1b8eb3dbfe069899820067842
+size 20978626656

models/MiniMax-H3/FL2VA/dit_6bpp.json

@@ -0,0 +1,44 @@
+{
+  "model_hash": "dcbfbfa6dfa5228b6b207879687c58d8",
+  "model_name": "minimax_h3_dit",
+  "model_class": "diffsynth.models.minimax_h3_dit.MiniMaxH3DiT",
+  "quant_config": {
+    "load_prequantized": true,
+    "configs": [
+      {
+        "method": "entropack_lossy_quant",
+        "backend_config_kwargs": {
+          "target_bpp": 6.0,
+          "row_rdo_iterations": 2,
+          "row_rdo_candidates": 20
+        },
+        "exclude_modules": [
+          "time_embedder.proj_in",
+          "time_embedder.proj_out",
+          "video_patch_proj",
+          "audio_patch_proj",
+          "condition_proj",
+          "final_layer.video_out",
+          "final_layer.audio_out"
+        ]
+      },
+      {
+        "method": "entropack_lossy_quant",
+        "backend_config_kwargs": {
+          "target_bpp": 8.0,
+          "row_rdo_iterations": 2,
+          "row_rdo_candidates": 20
+        },
+        "target_modules": [
+          "time_embedder.proj_in",
+          "time_embedder.proj_out",
+          "video_patch_proj",
+          "audio_patch_proj",
+          "condition_proj",
+          "final_layer.video_out",
+          "final_layer.audio_out"
+        ]
+      }
+    ]
+  }
+}

models/MiniMax-H3/FL2VA/dit_6bpp.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10ef6ef8eb8e7cee584f6ce92d2a790d66147d1e96c167206b977f939a5d3bae
+size 25183663296

models/MiniMax-H3/FL2VA/dit_7bpp.json

@@ -0,0 +1,44 @@
+{
+  "model_hash": "19f12bd0e985a00a192cac32fd605833",
+  "model_name": "minimax_h3_dit",
+  "model_class": "diffsynth.models.minimax_h3_dit.MiniMaxH3DiT",
+  "quant_config": {
+    "load_prequantized": true,
+    "configs": [
+      {
+        "method": "entropack_lossy_quant",
+        "backend_config_kwargs": {
+          "target_bpp": 7.0,
+          "row_rdo_iterations": 2,
+          "row_rdo_candidates": 20
+        },
+        "exclude_modules": [
+          "time_embedder.proj_in",
+          "time_embedder.proj_out",
+          "video_patch_proj",
+          "audio_patch_proj",
+          "condition_proj",
+          "final_layer.video_out",
+          "final_layer.audio_out"
+        ]
+      },
+      {
+        "method": "entropack_lossy_quant",
+        "backend_config_kwargs": {
+          "target_bpp": 8.0,
+          "row_rdo_iterations": 2,
+          "row_rdo_candidates": 20
+        },
+        "target_modules": [
+          "time_embedder.proj_in",
+          "time_embedder.proj_out",
+          "video_patch_proj",
+          "audio_patch_proj",
+          "condition_proj",
+          "final_layer.video_out",
+          "final_layer.audio_out"
+        ]
+      }
+    ]
+  }
+}

models/MiniMax-H3/FL2VA/dit_7bpp.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:149a454b25635b82d373b7fc7f276b3bf51271571313510c90a47928366b3c48
+size 29372100480

models/MiniMax-H3/FL2VA/dit_8bpp.json

@@ -0,0 +1,44 @@
+{
+  "model_hash": "601fbcb5f5e5b3531a46754b93d5750b",
+  "model_name": "minimax_h3_dit",
+  "model_class": "diffsynth.models.minimax_h3_dit.MiniMaxH3DiT",
+  "quant_config": {
+    "load_prequantized": true,
+    "configs": [
+      {
+        "method": "entropack_lossy_quant",
+        "backend_config_kwargs": {
+          "target_bpp": 8.0,
+          "row_rdo_iterations": 2,
+          "row_rdo_candidates": 20
+        },
+        "exclude_modules": [
+          "time_embedder.proj_in",
+          "time_embedder.proj_out",
+          "video_patch_proj",
+          "audio_patch_proj",
+          "condition_proj",
+          "final_layer.video_out",
+          "final_layer.audio_out"
+        ]
+      },
+      {
+        "method": "entropack_lossy_quant",
+        "backend_config_kwargs": {
+          "target_bpp": 8.0,
+          "row_rdo_iterations": 2,
+          "row_rdo_candidates": 20
+        },
+        "target_modules": [
+          "time_embedder.proj_in",
+          "time_embedder.proj_out",
+          "video_patch_proj",
+          "audio_patch_proj",
+          "condition_proj",
+          "final_layer.video_out",
+          "final_layer.audio_out"
+        ]
+      }
+    ]
+  }
+}

models/MiniMax-H3/FL2VA/dit_8bpp.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e32600e8280b7e87aff01e80f0357ecd16e203b87fe69bf74b976dc78e1498cf
+size 33462978544

models/MiniMax-H3/FL2VA/dit_extreme_3.0bpp.json

@@ -0,0 +1,306 @@
+{
+  "model_hash": "29795a310c0b91df83abc8990d2ea8fd",
+  "model_name": "minimax_h3_dit",
+  "model_class": "diffsynth.models.minimax_h3_dit.MiniMaxH3DiT",
+  "quant_config": {
+    "load_prequantized": true,
+    "configs": [
+      {
+        "method": "entropack_lossy_quant",
+        "backend_config_kwargs": {
+          "target_bpp": 2.9875992063492065,
+          "row_rdo_iterations": 2,
+          "row_rdo_candidates": 20
+        },
+        "target_modules": [
+          "blocks.0.attn.qkv_proj",
+          "blocks.0.mlp.fc2",
+          "blocks.0.mlp.fc1",
+          "blocks.1.attn.qkv_proj",
+          "blocks.1.mlp.fc2",
+          "blocks.1.mlp.fc1",
+          "blocks.2.mlp.fc2",
+          "blocks.2.mlp.fc1",
+          "token_refiner.blocks.0.attn.qkv_proj",
+          "token_refiner.blocks.0.mlp.fc2",
+          "token_refiner.blocks.0.mlp.fc1",
+          "token_refiner.blocks.1.attn.qkv_proj",
+          "token_refiner.blocks.1.mlp.fc2",
+          "token_refiner.blocks.1.mlp.fc1",
+          "blocks.2.attn.qkv_proj",
+          "blocks.3.attn.qkv_proj",
+          "blocks.3.mlp.fc2",
+          "blocks.3.mlp.fc1",
+          "blocks.4.attn.qkv_proj",
+          "blocks.4.mlp.fc2",
+          "blocks.4.mlp.fc1",
+          "blocks.5.attn.qkv_proj",
+          "blocks.5.mlp.fc2",
+          "blocks.5.mlp.fc1",
+          "blocks.6.mlp.fc2",
+          "blocks.6.mlp.fc1",
+          "blocks.10.mlp.fc2",
+          "blocks.10.mlp.fc1",
+          "blocks.6.attn.qkv_proj",
+          "blocks.7.attn.qkv_proj",
+          "blocks.7.mlp.fc2",
+          "blocks.7.mlp.fc1",
+          "blocks.8.attn.qkv_proj",
+          "blocks.8.mlp.fc2",
+          "blocks.8.mlp.fc1",
+          "blocks.9.attn.qkv_proj",
+          "blocks.9.mlp.fc2",
+          "blocks.9.mlp.fc1",
+          "blocks.10.attn.qkv_proj",
+          "blocks.11.attn.qkv_proj",
+          "blocks.11.mlp.fc2",
+          "blocks.11.mlp.fc1",
+          "blocks.12.attn.qkv_proj",
+          "blocks.12.mlp.fc2",
+          "blocks.12.mlp.fc1",
+          "blocks.13.attn.qkv_proj",
+          "blocks.13.mlp.fc2",
+          "blocks.13.mlp.fc1",
+          "blocks.14.mlp.fc2",
+          "blocks.14.mlp.fc1",
+          "blocks.14.attn.qkv_proj",
+          "blocks.15.attn.qkv_proj",
+          "blocks.15.mlp.fc2",
+          "blocks.15.mlp.fc1",
+          "blocks.16.attn.qkv_proj",
+          "blocks.16.mlp.fc2",
+          "blocks.16.mlp.fc1",
+          "blocks.17.attn.qkv_proj",
+          "blocks.17.mlp.fc2",
+          "blocks.17.mlp.fc1",
+          "blocks.18.mlp.fc2",
+          "blocks.18.mlp.fc1",
+          "blocks.18.attn.qkv_proj",
+          "blocks.19.attn.qkv_proj",
+          "blocks.19.mlp.fc2",
+          "blocks.19.mlp.fc1",
+          "blocks.20.attn.qkv_proj",
+          "blocks.20.mlp.fc2",
+          "blocks.20.mlp.fc1",
+          "blocks.21.attn.qkv_proj",
+          "blocks.21.mlp.fc2",
+          "blocks.21.mlp.fc1",
+          "blocks.22.mlp.fc2",
+          "blocks.22.mlp.fc1",
+          "blocks.22.attn.qkv_proj",
+          "blocks.23.attn.qkv_proj",
+          "blocks.23.mlp.fc2",
+          "blocks.23.mlp.fc1",
+          "blocks.24.attn.qkv_proj",
+          "blocks.24.mlp.fc2",
+          "blocks.24.mlp.fc1",
+          "blocks.25.attn.qkv_proj",
+          "blocks.25.mlp.fc2",
+          "blocks.25.mlp.fc1",
+          "blocks.26.mlp.fc2",
+          "blocks.26.mlp.fc1",
+          "blocks.26.attn.qkv_proj",
+          "blocks.27.attn.qkv_proj",
+          "blocks.27.mlp.fc2",
+          "blocks.27.mlp.fc1",
+          "blocks.28.attn.qkv_proj",
+          "blocks.28.mlp.fc2",
+          "blocks.28.mlp.fc1",
+          "blocks.29.attn.qkv_proj",
+          "blocks.29.mlp.fc2",
+          "blocks.29.mlp.fc1",
+          "blocks.30.mlp.fc2",
+          "blocks.30.mlp.fc1",
+          "blocks.30.attn.qkv_proj",
+          "blocks.31.attn.qkv_proj",
+          "blocks.31.mlp.fc2",
+          "blocks.31.mlp.fc1",
+          "blocks.32.attn.qkv_proj",
+          "blocks.32.mlp.fc2",
+          "blocks.32.mlp.fc1",
+          "blocks.33.attn.qkv_proj",
+          "blocks.33.mlp.fc2",
+          "blocks.33.mlp.fc1",
+          "blocks.34.mlp.fc2",
+          "blocks.34.mlp.fc1",
+          "blocks.34.attn.qkv_proj",
+          "blocks.35.attn.qkv_proj",
+          "blocks.35.mlp.fc2",
+          "blocks.35.mlp.fc1",
+          "blocks.36.attn.qkv_proj",
+          "blocks.36.mlp.fc2",
+          "blocks.36.mlp.fc1",
+          "blocks.37.attn.qkv_proj",
+          "blocks.37.mlp.fc2",
+          "blocks.37.mlp.fc1",
+          "blocks.38.mlp.fc2",
+          "blocks.38.mlp.fc1",
+          "blocks.38.attn.qkv_proj",
+          "blocks.39.attn.qkv_proj",
+          "blocks.39.mlp.fc2",
+          "blocks.39.mlp.fc1",
+          "blocks.40.attn.qkv_proj",
+          "blocks.40.mlp.fc2",
+          "blocks.40.mlp.fc1",
+          "blocks.41.attn.qkv_proj",
+          "blocks.41.mlp.fc2",
+          "blocks.41.mlp.fc1",
+          "blocks.42.mlp.fc2",
+          "blocks.42.mlp.fc1",
+          "blocks.42.attn.qkv_proj",
+          "blocks.43.attn.qkv_proj",
+          "blocks.43.mlp.fc2",
+          "blocks.43.mlp.fc1",
+          "blocks.44.attn.qkv_proj",
+          "blocks.44.mlp.fc2",
+          "blocks.44.mlp.fc1",
+          "blocks.45.attn.qkv_proj",
+          "blocks.45.mlp.fc2",
+          "blocks.45.mlp.fc1",
+          "blocks.46.mlp.fc2",
+          "blocks.46.mlp.fc1",
+          "blocks.46.attn.qkv_proj",
+          "blocks.47.attn.qkv_proj",
+          "blocks.47.mlp.fc2",
+          "blocks.47.mlp.fc1",
+          "blocks.48.attn.qkv_proj",
+          "blocks.48.mlp.fc2",
+          "blocks.48.mlp.fc1",
+          "blocks.49.attn.qkv_proj",
+          "blocks.49.mlp.fc2",
+          "blocks.49.mlp.fc1"
+        ]
+      },
+      {
+        "method": "entropack_lossy_quant",
+        "backend_config_kwargs": {
+          "target_bpp": 3.0,
+          "row_rdo_iterations": 2,
+          "row_rdo_candidates": 20
+        },
+        "target_modules": [
+          "blocks.0.adaln_proj.linear",
+          "blocks.0.attn.out_proj",
+          "blocks.1.adaln_proj.linear",
+          "blocks.1.attn.out_proj",
+          "blocks.2.adaln_proj.linear",
+          "token_refiner.blocks.0.attn.out_proj",
+          "token_refiner.blocks.1.attn.out_proj",
+          "blocks.2.attn.out_proj",
+          "blocks.3.adaln_proj.linear",
+          "blocks.3.attn.out_proj",
+          "blocks.4.adaln_proj.linear",
+          "blocks.4.attn.out_proj",
+          "blocks.5.adaln_proj.linear",
+          "blocks.5.attn.out_proj",
+          "blocks.6.adaln_proj.linear",
+          "blocks.10.adaln_proj.linear",
+          "blocks.6.attn.out_proj",
+          "blocks.7.adaln_proj.linear",
+          "blocks.7.attn.out_proj",
+          "blocks.8.adaln_proj.linear",
+          "blocks.8.attn.out_proj",
+          "blocks.9.adaln_proj.linear",
+          "blocks.9.attn.out_proj",
+          "blocks.10.attn.out_proj",
+          "blocks.11.adaln_proj.linear",
+          "blocks.11.attn.out_proj",
+          "blocks.12.adaln_proj.linear",
+          "blocks.12.attn.out_proj",
+          "blocks.13.adaln_proj.linear",
+          "blocks.13.attn.out_proj",
+          "blocks.14.adaln_proj.linear",
+          "blocks.14.attn.out_proj",
+          "blocks.15.adaln_proj.linear",
+          "blocks.15.attn.out_proj",
+          "blocks.16.adaln_proj.linear",
+          "blocks.16.attn.out_proj",
+          "blocks.17.adaln_proj.linear",
+          "blocks.17.attn.out_proj",
+          "blocks.18.adaln_proj.linear",
+          "blocks.18.attn.out_proj",
+          "blocks.19.adaln_proj.linear",
+          "blocks.19.attn.out_proj",
+          "blocks.20.adaln_proj.linear",
+          "blocks.20.attn.out_proj",
+          "blocks.21.adaln_proj.linear",
+          "blocks.21.attn.out_proj",
+          "blocks.22.adaln_proj.linear",
+          "blocks.22.attn.out_proj",
+          "blocks.23.adaln_proj.linear",
+          "blocks.23.attn.out_proj",
+          "blocks.24.adaln_proj.linear",
+          "blocks.24.attn.out_proj",
+          "blocks.25.adaln_proj.linear",
+          "blocks.25.attn.out_proj",
+          "blocks.26.adaln_proj.linear",
+          "blocks.26.attn.out_proj",
+          "blocks.27.adaln_proj.linear",
+          "blocks.27.attn.out_proj",
+          "blocks.28.adaln_proj.linear",
+          "blocks.28.attn.out_proj",
+          "blocks.29.adaln_proj.linear",
+          "blocks.29.attn.out_proj",
+          "blocks.30.adaln_proj.linear",
+          "blocks.30.attn.out_proj",
+          "blocks.31.adaln_proj.linear",
+          "blocks.31.attn.out_proj",
+          "blocks.32.adaln_proj.linear",
+          "blocks.32.attn.out_proj",
+          "blocks.33.adaln_proj.linear",
+          "blocks.33.attn.out_proj",
+          "blocks.34.adaln_proj.linear",
+          "blocks.34.attn.out_proj",
+          "blocks.35.adaln_proj.linear",
+          "blocks.35.attn.out_proj",
+          "blocks.36.adaln_proj.linear",
+          "blocks.36.attn.out_proj",
+          "blocks.37.adaln_proj.linear",
+          "blocks.37.attn.out_proj",
+          "blocks.38.adaln_proj.linear",
+          "blocks.38.attn.out_proj",
+          "blocks.39.adaln_proj.linear",
+          "blocks.39.attn.out_proj",
+          "blocks.40.adaln_proj.linear",
+          "blocks.40.attn.out_proj",
+          "blocks.41.adaln_proj.linear",
+          "blocks.41.attn.out_proj",
+          "blocks.42.adaln_proj.linear",
+          "blocks.42.attn.out_proj",
+          "blocks.43.adaln_proj.linear",
+          "blocks.43.attn.out_proj",
+          "blocks.44.adaln_proj.linear",
+          "blocks.44.attn.out_proj",
+          "blocks.45.adaln_proj.linear",
+          "blocks.45.attn.out_proj",
+          "blocks.46.adaln_proj.linear",
+          "blocks.46.attn.out_proj",
+          "blocks.47.adaln_proj.linear",
+          "blocks.47.attn.out_proj",
+          "blocks.48.adaln_proj.linear",
+          "blocks.48.attn.out_proj",
+          "blocks.49.adaln_proj.linear",
+          "blocks.49.attn.out_proj",
+          "final_layer.adaln_proj.linear"
+        ]
+      },
+      {
+        "method": "entropack_lossy_quant",
+        "backend_config_kwargs": {
+          "target_bpp": 8.0,
+          "row_rdo_iterations": 2,
+          "row_rdo_candidates": 20
+        },
+        "target_modules": [
+          "audio_patch_proj",
+          "time_embedder.proj_in",
+          "time_embedder.proj_out",
+          "video_patch_proj",
+          "condition_proj",
+          "final_layer.audio_out",
+          "final_layer.video_out"
+        ]
+      }
+    ]
+  }
+}

models/MiniMax-H3/FL2VA/dit_extreme_3.0bpp.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce5d26f13ad42a80bd5b515096ecef1ca6b062ed8c5765ac8950383a45ed5e91
+size 12535981160

models/MiniMax-H3/FL2VA/dit_fp8_5bpp.json

@@ -0,0 +1,44 @@
+{
+  "model_hash": "16ca1fa6f82125d160f4b185a3ba2096",
+  "model_name": "minimax_h3_dit",
+  "model_class": "diffsynth.models.minimax_h3_dit.MiniMaxH3DiT",
+  "quant_config": {
+    "load_prequantized": true,
+    "configs": [
+      {
+        "method": "entropack_lossy_quant_fp8",
+        "backend_config_kwargs": {
+          "target_bpp": 5.0,
+          "row_rdo_iterations": 2,
+          "row_rdo_candidates": 20
+        },
+        "exclude_modules": [
+          "time_embedder.proj_in",
+          "time_embedder.proj_out",
+          "video_patch_proj",
+          "audio_patch_proj",
+          "condition_proj",
+          "final_layer.video_out",
+          "final_layer.audio_out"
+        ]
+      },
+      {
+        "method": "entropack_lossy_quant",
+        "backend_config_kwargs": {
+          "target_bpp": 8.0,
+          "row_rdo_iterations": 2,
+          "row_rdo_candidates": 20
+        },
+        "target_modules": [
+          "time_embedder.proj_in",
+          "time_embedder.proj_out",
+          "video_patch_proj",
+          "audio_patch_proj",
+          "condition_proj",
+          "final_layer.video_out",
+          "final_layer.audio_out"
+        ]
+      }
+    ]
+  }
+}

models/MiniMax-H3/FL2VA/dit_fp8_5bpp.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c017b2f9118486aaedafd57797826bd1108a83fbd237074f62e0000eaed52c05
+size 20981618128

models/MiniMax-H3/REF2VA/dit_4bpp.json

@@ -0,0 +1,44 @@
+{
+  "model_hash": "49df57910799fd05dca1e79ec1fbf0e9",
+  "model_name": "minimax_h3_dit",
+  "model_class": "diffsynth.models.minimax_h3_dit.MiniMaxH3DiT",
+  "quant_config": {
+    "load_prequantized": true,
+    "configs": [
+      {
+        "method": "entropack_lossy_quant",
+        "backend_config_kwargs": {
+          "target_bpp": 4.0,
+          "row_rdo_iterations": 2,
+          "row_rdo_candidates": 20
+        },
+        "exclude_modules": [
+          "time_embedder.proj_in",
+          "time_embedder.proj_out",
+          "video_patch_proj",
+          "audio_patch_proj",
+          "condition_proj",
+          "final_layer.video_out",
+          "final_layer.audio_out"
+        ]
+      },
+      {
+        "method": "entropack_lossy_quant",
+        "backend_config_kwargs": {
+          "target_bpp": 8.0,
+          "row_rdo_iterations": 2,
+          "row_rdo_candidates": 20
+        },
+        "target_modules": [
+          "time_embedder.proj_in",
+          "time_embedder.proj_out",
+          "video_patch_proj",
+          "audio_patch_proj",
+          "condition_proj",
+          "final_layer.video_out",
+          "final_layer.audio_out"
+        ]
+      }
+    ]
+  }
+}

models/MiniMax-H3/REF2VA/dit_4bpp.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6f974fc0d9ba9286c23fd9764b1ee2cda679b507139a8b2b69e9cbb04dc4a08
+size 16726551560

models/MiniMax-H3/REF2VA/dit_5bpp.json

@@ -0,0 +1,44 @@
+{
+  "model_hash": "e6e4edc4382aac92c772ff56625eb108",
+  "model_name": "minimax_h3_dit",
+  "model_class": "diffsynth.models.minimax_h3_dit.MiniMaxH3DiT",
+  "quant_config": {
+    "load_prequantized": true,
+    "configs": [
+      {
+        "method": "entropack_lossy_quant",
+        "backend_config_kwargs": {
+          "target_bpp": 5.0,
+          "row_rdo_iterations": 2,
+          "row_rdo_candidates": 20
+        },
+        "exclude_modules": [
+          "time_embedder.proj_in",
+          "time_embedder.proj_out",
+          "video_patch_proj",
+          "audio_patch_proj",
+          "condition_proj",
+          "final_layer.video_out",
+          "final_layer.audio_out"
+        ]
+      },
+      {
+        "method": "entropack_lossy_quant",
+        "backend_config_kwargs": {
+          "target_bpp": 8.0,
+          "row_rdo_iterations": 2,
+          "row_rdo_candidates": 20
+        },
+        "target_modules": [
+          "time_embedder.proj_in",
+          "time_embedder.proj_out",
+          "video_patch_proj",
+          "audio_patch_proj",
+          "condition_proj",
+          "final_layer.video_out",
+          "final_layer.audio_out"
+        ]
+      }
+    ]
+  }
+}

models/MiniMax-H3/REF2VA/dit_5bpp.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcb400d282ed59bf54388b0a684e2556a33a6a66869d90255b7de1e0cc998f9f
+size 20978285280