Duplicate from lilcheaty/Krea2-INT8-ConvRot

Co-authored-by: Safzan Pirani <lilcheaty@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow 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
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Krea2-Raw-int8-ConvRot.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b45574f1098f713ab03318310141b582757220207757327165c3cc4515e7972c
+size 14132232424

Krea2-Turbo-int8-ConvRot.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:778cdba5023ce37d20024c971be097d47434db899044721b45c29b37a09fcc12
+size 14132232424

LICENSE

@@ -0,0 +1,43 @@
+KREA 2 COMMUNITY LICENSE AGREEMENT
+Copyright (c) Krea, Inc. All Rights Reserved.
+
+The model weights in this repository are an INT8 ConvRot quantized DERIVATIVE of
+the Krea 2 model and are governed in full by the Krea 2 Community License
+Agreement. The complete, authoritative agreement is published at:
+
+    https://www.krea.ai/krea-2-licensing
+
+By downloading, using, reproducing, distributing, or creating derivatives of
+these weights, you agree to be bound by that Agreement. A copy of the full
+Agreement must accompany any redistribution.
+
+----------------------------------------------------------------------
+KEY TERMS (summary — the canonical Agreement at the link above controls)
+----------------------------------------------------------------------
+
+ATTRIBUTION & DISTRIBUTION
+  - Any AI model name derived from Krea 2 must begin with "Krea".
+  - Redistribution must include a copy of the Agreement and bind each recipient
+    to its Terms, and must retain the attribution Notice (see Notice.txt).
+  - Derivatives must state that the Krea Model has been modified.
+  - You must not represent derivatives as official or endorsed by Krea.
+
+COMMERCIAL USE
+  - Permitted only for entities (incl. affiliates under common control) with
+    total annual revenue under $1,000,000 USD (trailing twelve months).
+  - At or above $1M USD, a separate Enterprise License from Krea is required.
+
+CONTENT FILTERING & SAFETY
+  - Deployers must implement reasonable content-filtering to detect, prevent,
+    and mitigate prohibited, harmful, or unlawful content.
+  - Disclose AI-generated outputs where legally required.
+  - Comply with the incorporated Acceptable Use Policy.
+
+INTELLECTUAL PROPERTY / WARRANTY
+  - Krea retains ownership of the model; you own your outputs and derivatives.
+  - Provided "AS IS" without warranties; standard disclaimers and
+    indemnification obligations apply. Termination is automatic on breach.
+
+----------------------------------------------------------------------
+This summary is provided for convenience and is NOT a substitute for the full
+Krea 2 Community License Agreement at https://www.krea.ai/krea-2-licensing

Notice.txt

@@ -0,0 +1,15 @@
+Krea 2 is licensed under the Krea 2 Community License Agreement,
+Copyright (c) Krea, Inc. All Rights Reserved.
+
+The model weights in this repository are a MODIFIED (INT8 ConvRot quantized)
+derivative of the Krea 2 model. They are not official Krea releases and are not
+endorsed by Krea. The original model and license are available at:
+https://www.krea.ai/krea-2  and  https://www.krea.ai/krea-2-licensing
+
+Modifications: the BF16 Krea 2 RAW and Turbo checkpoints were quantized to INT8
+(ConvRot, row-wise) using ComfyUI-INT8-Fast. The 28 main DiT blocks are INT8;
+the sensitive layers (first, last, tmlp, tproj, txtfusion, txtmlp) are retained
+in higher precision.
+
+Deployers must implement reasonable content-filtering measures and disclose
+AI-generated outputs where required, per the Krea 2 Community License.

README.md

@@ -0,0 +1,86 @@
+---
+license: other
+license_name: krea-2-community-license
+license_link: https://www.krea.ai/krea-2-licensing
+base_model: krea/Krea-2
+tags:
+  - text-to-image
+  - krea
+  - krea2
+  - int8
+  - convrot
+  - comfyui
+  - quantized
+---
+
+# Krea 2 — INT8 ConvRot
+
+INT8 **ConvRot** quantized weights for **[Krea 2 (K2)](https://www.krea.ai/krea-2)**, for fast, low-VRAM
+inference in ComfyUI via the [ComfyUI-INT8-Fast](https://github.com/BobJohnson24/ComfyUI-INT8-Fast) node.
+
+> **This is a modified (quantized) version of the Krea 2 model.** It is **not** an official Krea release and is
+> **not** endorsed by Krea. The original weights are © Krea, licensed under the
+> [Krea 2 Community License](https://www.krea.ai/krea-2-licensing).
+
+ConvRot is a near-lossless INT8 scheme (~GGUF-Q8 quality) that runs on the INT8 tensor cores of any NVIDIA GPU
+with sufficient INT8 TOPS (RTX 30-series and up). On a 3090, INT8 is meaningfully faster than FP8 (which has no
+tensor-core acceleration on Ampere) and roughly half the VRAM of BF16.
+
+## Models
+
+| File | Precision | Size | Use |
+|------|-----------|------|-----|
+| `Krea2-Turbo-int8-ConvRot.safetensors` | INT8 ConvRot | 14.1 GB | 8-step distilled, fast text-to-image |
+| `Krea2-Raw-int8-ConvRot.safetensors` | INT8 ConvRot | 14.1 GB | Undistilled base — fine-tuning / LoRA training / research |
+
+Original BF16 checkpoints are ~26.6 GB each. Quantized with the K2 profile: the 28 main DiT blocks are INT8,
+while the sensitive layers (`first`, `last`, `tmlp`, `tproj`, `txtfusion`, `txtmlp`) are kept in high precision.
+
+## Requirements
+
+- **ComfyUI ≥ 0.25.0** (native Krea 2 support).
+- **[ComfyUI-INT8-Fast](https://github.com/BobJohnson24/ComfyUI-INT8-Fast)** custom node (with a `krea2`
+  model-type profile — see note below).
+- Text encoder: **`qwen3vl_4b_fp8_scaled.safetensors`** → `ComfyUI/models/text_encoders/`
+  (from [Comfy-Org/Qwen3-VL](https://huggingface.co/Comfy-Org/Qwen3-VL)).
+- VAE: **`qwen_image_vae.safetensors`** → `ComfyUI/models/vae/`
+  (from [Comfy-Org/Qwen-Image_ComfyUI](https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI)).
+- Put the INT8 `.safetensors` in `ComfyUI/models/diffusion_models/`.
+
+> **Note on the `krea2` profile:** Krea 2 is newer than INT8-Fast's built-in model list. These weights were
+> produced with a small added `krea2` exclusion profile (keep `first`/`last`/`tmlp`/`tproj`/`txtfusion`/`txtmlp`
+> in high precision). Loading the *pre-quantized* files here does not require that profile — ConvRot metadata
+> is embedded per-layer — but reproducing the conversion does.
+
+## Usage
+
+Load with **Load Diffusion Model INT8 (W8A8)** (`OTUNetLoaderW8A8`):
+- `unet_name`: the INT8 file
+- `on_the_fly_quantization`: **false** (already quantized)
+- `enable_convrot`: **true**
+- `model_type`: `krea2`
+
+Then the standard K2 graph: `CLIPLoader (type: krea2)` → `VAELoader` → `CLIPTextEncode` → `KSampler` → `VAEDecode`.
+
+Recommended sampler settings:
+- **Turbo:** 8 steps, CFG 1.0, `euler` / `simple`, shift 1.15 (model default).
+- **Raw:** ~52 steps, CFG ~3.5, `euler` / `simple` (undistilled base; mainly for training).
+
+## Quantization
+
+- **Method:** INT8 ConvRot (row-wise INT8 with convolutional rotation), via ComfyUI-INT8-Fast.
+- **Compute:** `torch._int_mm` on INT8 tensor cores; Triton kernels.
+- **Quality:** near-lossless vs BF16/FP8 in testing (verified by generation).
+
+## License & attribution
+
+Krea 2 is licensed under the **Krea 2 Community License Agreement**,
+Copyright © Krea, Inc. All Rights Reserved. See `LICENSE` / https://www.krea.ai/krea-2-licensing.
+
+These files are a **quantized derivative** of Krea 2; the Krea 2 model name is retained per the license.
+Commercial use is permitted only for entities under $1M USD trailing-twelve-month revenue; above that an
+Enterprise License from Krea is required. **Deployers must implement reasonable content-filtering** (e.g.
+NudeNet, Falconsai/nsfw_image_detection, Hive, or human review) to prevent prohibited content, and disclose
+AI-generated outputs where required.
+
+**Credits:** [Krea](https://www.krea.ai) (base model) · [BobJohnson24/ComfyUI-INT8-Fast](https://github.com/BobJohnson24/ComfyUI-INT8-Fast) (INT8 ConvRot method).