DeepBeepMeep commited on
Commit
effee3f
·
verified ·
1 Parent(s): e94e6e9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -7
README.md CHANGED
@@ -1,13 +1,25 @@
1
  ---
2
- license: other
3
- pipeline_tag: text-to-image
 
 
4
  ---
5
 
6
- # Krea 2 for WanGP
7
 
8
- This repository contains the WanGP-ready Krea 2 RAW and Turbo transformer checkpoints, their Quanto BF16 INT8 variants, the shared Qwen3-VL text encoder package, and the Krea 2 transformer config.
9
 
10
- The VAE is not duplicated here. Krea 2 uses the tensor-identical shared Qwen Image VAE:
11
 
12
- - `DeepBeepMeep/Qwen_image/qwen_vae.safetensors`
13
- - `DeepBeepMeep/Qwen_image/qwen_vae_config.json`
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model:
3
+ - krea/Krea-2-Turbo
4
+ tags:
5
+ - diffusion-single-file
6
  ---
7
 
8
+ You will find here all the Krea 2 image models used with WanGP (https://github.com/deepbeepmeep/Wan2GP) :
9
 
 
10
 
11
+ WanGP by DeepBeepMeep : The best Open Source Video Generative Models Accessible to the GPU Poor
12
 
13
+ WanGP supports the Wan (and derived models), Hunyuan Video, Flux 1 & 2, Qwen, Z-Image and LTX Video models with:
14
+
15
+ Low VRAM requirements (as low as 6 GB of VRAM is sufficient for certain models)
16
+ Support for old GPUs (RTX 10XX, 20xx, ...)
17
+ Very Fast on the latest GPUs
18
+ Easy to use Full Web based interface
19
+ Auto download of the required model adapted to your specific architecture
20
+ Tools integrated to facilitate Video Generation : Mask Editor, Prompt Enhancer, Temporal and Spatial Generation
21
+ Loras Support to customize each model
22
+ Queuing system : make your shopping list of videos to generate and come back later
23
+ Discord Server to get Help from Other Users and show your Best Videos: https://discord.gg/g7efUW9jGV
24
+
25
+ Follow DeepBeepMeep on Twitter/X to get the Latest News: https://x.com/deepbeepmeep