Final LoRA release

.gitattributes

@@ -2235,3 +2235,4 @@ assets/storybookfox_turbo_8step.jpg filter=lfs diff=lfs merge=lfs -text
 assets/swordsman_turbo_4step_lora.jpg filter=lfs diff=lfs merge=lfs -text
 assets/swordsman_turbo_4step.jpg filter=lfs diff=lfs merge=lfs -text
 assets/thumbs/poster.jpg filter=lfs diff=lfs merge=lfs -text
+LICENSE.pdf filter=lfs diff=lfs merge=lfs -text

LICENSE.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b82a2805162bde714a4eb27b9063c4fc3345d08a30be055134a6160e5430ba74
+size 137711

NOTICE.txt

@@ -0,0 +1,5 @@
+Krea 2 is licensed under the Krea 2 Community License Agreement. For more information, visit https://krea.ai/krea-2-licensing.
+
+This repository distributes a Derivative of the Krea 2 Turbo model, as defined in that agreement: a LoRA adapter produced by distilling Krea 2 Turbo to a 4-step schedule. The Krea Model has been modified. This adapter is not an official Krea product and is not endorsed by Krea.ai, Inc.
+
+Use of this adapter is subject to the Krea 2 Community License Agreement (LICENSE.pdf in this repository) and the Krea Acceptable Use Policy (https://krea.ai/krea-2-use-policy), exactly as use of Krea 2 Turbo itself is.

krea2_turbo_4step_lora_t2i.json

@@ -74,7 +74,7 @@
         "cnr_id": "comfy-core"
       },
       "widgets_values": [
-        "krea2_turbo_4step_rank_64_lora_latest_comfyui.safetensors",
+        "krea2_turbo_4step_rank_64_lora_comfyui.safetensors",
         1.0
       ]
     },
@@ -408,7 +408,7 @@
       "outputs": [],
       "properties": {},
       "widgets_values": [
-        "## Krea 2 Turbo \u2014 4-step distillation LoRA\n\nKrea 2 Turbo normally needs **8 steps**. With this LoRA it runs at **4**.\n\n### Files\n| file | put it in |\n| --- | --- |\n| `krea2_turbo_bf16.safetensors` | `models/diffusion_models/` |\n| `qwen3vl_4b_bf16.safetensors` | `models/text_encoders/` |\n| `qwen_image_vae.safetensors` | `models/vae/` |\n| `krea2_turbo_4step_rank_64_lora_latest_comfyui.safetensors` | `models/loras/` |\n\nThe first three are from [Comfy-Org/Krea-2](https://huggingface.co/Comfy-Org/Krea-2).\n\n**The LoRA is independent of the base build.** It is applied on top of the diffusion model by ComfyUI's own loader, which handles any dequantisation, so a quantised or otherwise optimised build of Krea 2 Turbo behaves just as bf16 does. Please use whichever variant suits your hardware \u2014 set it in **Load Diffusion Model** and leave the rest of the workflow untouched.\n\nThis workflow ships **full bf16** only because it is the one build guaranteed to run everywhere: bf16 needs no backend-specific kernel, so it works on CUDA, Apple Silicon and CPU alike. Smaller options: `krea2_turbo_int8_convrot` (13.5 GB, either platform), or `krea2_turbo_fp8_scaled` (13.1 GB) which is **NVIDIA-only** \u2014 MPS has no `Float8_e4m3fn` support and fails at the sampler. The text encoder has bf16 and fp8 builds only; there is no int8 one.\n\n> **Do not use `fp8_scaled` on Apple Silicon.** MPS has no `Float8_e4m3fn` support, so it fails at the sampler with *\"Trying to convert Float8_e4m3fn to the MPS backend\"*. It is fine on NVIDIA. `krea2_turbo_bf16` (26.3 GB) also works everywhere if you prefer full precision \u2014 just set the matching name in the loader.\n\n### Settings that matter\n- **steps 4**, **cfg 1.0** (Turbo is CFG-free), sampler **euler**, scheduler **simple**\n- LoRA strength **1.0**\n- The negative is a `ConditioningZeroOut` \u2014 at cfg 1.0 it is not evaluated, so there is nothing to write in it\n\nSet steps back to 8 and bypass the LoRA node (Ctrl+B) to compare against stock Turbo.\n\n### Work in progress\n**`_latest` currently points to `chk00060000`** (60,000 training samples).\n\nTraining is ongoing and better checkpoints may be published later. This workflow points at `..._latest_comfyui.safetensors`, which always holds the newest accepted checkpoint \u2014 **re-download that one file and the workflow keeps working**, no edit needed.\n\nNumbered copies (`..._chk00060000_comfyui.safetensors`) are kept alongside it so a specific checkpoint can be pinned. Every file records which checkpoint it is in its safetensors metadata (`checkpoint`, `training_samples`)."
+        "## Krea 2 Turbo \u2014 4-step distillation LoRA\n\nKrea 2 Turbo normally needs **8 steps**. With this LoRA it runs at **4**.\n\n### Files\n| file | put it in |\n| --- | --- |\n| `krea2_turbo_bf16.safetensors` | `models/diffusion_models/` |\n| `qwen3vl_4b_bf16.safetensors` | `models/text_encoders/` |\n| `qwen_image_vae.safetensors` | `models/vae/` |\n| `krea2_turbo_4step_rank_64_lora_comfyui.safetensors` | `models/loras/` |\n\nThe first three are from [Comfy-Org/Krea-2](https://huggingface.co/Comfy-Org/Krea-2).\n\n**The LoRA is independent of the base build.** It is applied on top of the diffusion model by ComfyUI's own loader, which handles any dequantisation, so a quantised or otherwise optimised build of Krea 2 Turbo behaves just as bf16 does. Please use whichever variant suits your hardware \u2014 set it in **Load Diffusion Model** and leave the rest of the workflow untouched.\n\nThis workflow ships **full bf16** only because it is the one build guaranteed to run everywhere: bf16 needs no backend-specific kernel, so it works on CUDA, Apple Silicon and CPU alike. Smaller options: `krea2_turbo_int8_convrot` (13.5 GB, either platform), or `krea2_turbo_fp8_scaled` (13.1 GB) which is **NVIDIA-only** \u2014 MPS has no `Float8_e4m3fn` support and fails at the sampler. The text encoder has bf16 and fp8 builds only; there is no int8 one.\n\n> **Do not use `fp8_scaled` on Apple Silicon.** MPS has no `Float8_e4m3fn` support, so it fails at the sampler with *\"Trying to convert Float8_e4m3fn to the MPS backend\"*. It is fine on NVIDIA. `krea2_turbo_bf16` (26.3 GB) also works everywhere if you prefer full precision \u2014 just set the matching name in the loader.\n\n### Settings that matter\n- **steps 4**, **cfg 1.0** (Turbo is CFG-free), sampler **euler**, scheduler **simple**\n- LoRA strength **1.0**\n- The negative is a `ConditioningZeroOut` \u2014 at cfg 1.0 it is not evaluated, so there is nothing to write in it\n\nSet steps back to 8 and bypass the LoRA node (Ctrl+B) to compare against stock Turbo.\n\n### Metadata\nThe LoRA file carries its training details in its safetensors metadata: base model, method, sample count and the inference settings above."
       ],
       "color": "#432",
       "bgcolor": "#653"

krea2_turbo_4step_rank_64_lora.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20c1fb1bb66477fb3b19e501d69b55e1d2a25c7ce6550bb142529220838d80a4
+size 438160440

krea2_turbo_4step_rank_64_lora_comfyui.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7590b2d2772f45d7b1252124c63918b1b807e93fbf9eab20546fa7233b4dc482
+size 438140968