Instructions to use AlperKTS/Krea2_FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use AlperKTS/Krea2_FP8 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("AlperKTS/Krea2_FP8", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Add native ComfyUI workflow instructions and required file links
Browse files
README.md
CHANGED
|
@@ -63,25 +63,29 @@ Below are official sample outputs from the original Krea 2 OSS Turbo model (gene
|
|
| 63 |
|
| 64 |
---
|
| 65 |
|
| 66 |
-
## 🚀 How to Use in ComfyUI
|
| 67 |
|
| 68 |
-
|
| 69 |
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
- Path: `ComfyUI/models/unet/` OR `ComfyUI/models/diffusion_models/` OR `ComfyUI/models/krea2/`
|
| 73 |
|
| 74 |
-
###
|
| 75 |
-
To run Krea 2 OSS, you will also need the original text encoder and VAE:
|
| 76 |
-
- **Text Encoder**: Qwen3-VL-4B-Instruct (`Qwen/Qwen3-VL-4B-Instruct` on Hugging Face).
|
| 77 |
-
- **VAE**: Qwen-Image Autoencoder (`Qwen/Qwen-Image` subfolder `vae`).
|
| 78 |
|
| 79 |
-
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
-
|
| 83 |
-
|
| 84 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 85 |
|
| 86 |
---
|
| 87 |
|
|
|
|
| 63 |
|
| 64 |
---
|
| 65 |
|
|
|
|
| 66 |
|
| 67 |
+
## 🚀 How to Use in ComfyUI (Native — 0.25.0+)
|
| 68 |
|
| 69 |
+
ComfyUI 0.25.0+ has **built-in Krea2 support**. No custom nodes needed.
|
| 70 |
+
Drop the workflow JSON into ComfyUI and drag it to the canvas.
|
|
|
|
| 71 |
|
| 72 |
+
### 1. Download Required Files
|
|
|
|
|
|
|
|
|
|
| 73 |
|
| 74 |
+
Place these in your `ComfyUI/models/` folder:
|
| 75 |
+
|
| 76 |
+
| File | Folder | Source |
|
| 77 |
+
|------|--------|--------|
|
| 78 |
+
| `krea2_turbo_fp8.safetensors` | `unet/` | [AlperKTS/Krea2_FP8](https://huggingface.co/AlperKTS/Krea2_FP8) ← You are here |
|
| 79 |
+
| `qwen3vl_4b_fp8_scaled.safetensors` | `text_encoders/` | [Comfy-Org/Qwen3-VL](https://huggingface.co/Comfy-Org/Qwen3-VL/tree/main/text_encoders) |
|
| 80 |
+
| `qwen_image_vae.safetensors` | `vae/` | [Comfy-Org/Qwen-Image_ComfyUI](https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/vae) |
|
| 81 |
+
|
| 82 |
+
### 2. Load the Workflow
|
| 83 |
+
|
| 84 |
+
Drag [`workflows/Krea 2 simple workflow.json`](workflows/Krea%202%20simple%20workflow.json) onto your ComfyUI canvas.
|
| 85 |
+
|
| 86 |
+
### 3. Queue & Generate!
|
| 87 |
+
|
| 88 |
+
Turbo defaults: **8 steps, CFG 1.0, `er_sde` sampler, `simple` scheduler, 1280×720.**
|
| 89 |
|
| 90 |
---
|
| 91 |
|