Update README.md

README.md

@@ -1,51 +1,25 @@
 ---
-license: mit
-library_name: custom
-pipeline_tag: text-to-image
 tags:
-  - image-generation
-  - image-editing
-  - graphic-design
-  - rgba
+- diffusion-single-file
+base_model:
+- inclusionAI/Ming-Image-0.1-Design
 ---
 
-# Ming Image 0.1 Design for WanGP
+You will find here all the Ming-Image-0.1-Design models used with WanGP (https://github.com/deepbeepmeep/Wan2GP) :
 
-These are single-file checkpoints prepared for WanGP from
-[inclusionAI/Ming-Image-0.1-Design](https://huggingface.co/inclusionAI/Ming-Image-0.1-Design)
-at revision `208087ada1486931692c1896f38d4cd16ff3df82`.
-The original checkpoint and inference code are MIT licensed. See `LICENSE`.
 
-The repository contains a BF16 diffusion transformer and its INT8 ConvRot
-version at the root, a project-specific BailingMM2 text encoder and its INT8
-ConvRot version under `BailingMM2-Ming-Image/`, and the VAE and runtime
-configuration under `ming_image/`. The tokenizer lives beside the text encoder.
-The INT8 files use WanGP's MMGP ConvRot loader rather than stock Diffusers.
+WanGP by DeepBeepMeep : The best Open Source Video Generative Models Accessible to the GPU Poor
 
-The BF16 files were merged from upstream shards with tensor verification.
-The connector's upstream FP32 weights were converted to BF16 for the BF16
-inference variant. The original model sources and conversion notes are in
-WanGP's `models/ming_image/` directory.
+WanGP supports the Wan (and derived models), MiniMax H3, Hunyuan Video, Minimax H3, Krea-2, Flux 1 & 2, Qwen Image 1/2.1, Z-Image and LTX-2, LTX Video models with:
 
-WanGP supports text-to-image and one-reference image editing with these files.
+Low VRAM requirements (as low as 6 GB of VRAM is sufficient for certain models)
+Support for old GPUs (RTX 10XX, 20xx, ...)
+Very Fast on the latest GPUs
+Easy to use Full Web based interface
+Auto download of the required model adapted to your specific architecture
+Tools integrated to facilitate Video Generation : Mask Editor, Prompt Enhancer, Temporal and Spatial Generation
+Loras Support to customize each model
+Queuing system : make your shopping list of videos to generate and come back later
+Discord Server to get Help from Other Users and show your Best Videos: https://discord.gg/g7efUW9jGV
 
-## Ming Image 0.1 Design-Layer
-
-Design-Layer separates a flattened reference image into ordered RGBA raster layers. WanGP places every layer in the gallery, frontmost first, and saves a ZIP. Supply one reference image and a front-to-back layer plan. Start with 12 steps, guidance 2, and the 1024 working bucket; 512 is faster.
-
-Its BF16 and INT8 ConvRot transformer checkpoints are at the repository root. The Layer-specific Bailing encoder checkpoints and tokenizer are under `BailingMM2-Ming-Image-Layer/`, and runtime configs are under `ming_image_layer/`. The Design and Design-Layer checkpoints use the same VAE from `ming_image/`. Their Bailing base weights are identical, but the Layer connector, MLP, and tokenizer differ, so WanGP uses a separate complete Layer encoder.
-
-Source: [inclusionAI/Ming-Image-0.1-Design-Layer](https://huggingface.co/inclusionAI/Ming-Image-0.1-Design-Layer), revision `9fabca8b62a67f1f53a957d46389c00451c11e52` (MIT). The released Layer transformer was converted from FP32 to BF16 to match upstream BF16 inference. The merged encoder and ConvRot files were verified against their source tensors and exercised in WanGP generation.
-
-Example plan:
-
-```text
-Decompose this image into 4 layers with the following specifications:
-Number of layers: 4
-Layer 1: All clearly readable foreground text, preserving its exact wording and placement.
-Layer 2: The card or panel directly behind the text.
-Layer 3: The main foreground subject or illustration.
-Layer 4: The complete background and remaining supporting shapes.
-```
-
-The layers are raster images, including any text. The last gallery image is the background.
+Follow DeepBeepMeep on Twitter/X to get the Latest News: https://x.com/deepbeepmeep