Upload README.md

README.md

@@ -0,0 +1,221 @@
+---
+base_model: inclusionAI/LLaDA-Image
+base_model_relation: quantized
+library_name: diffusers
+pipeline_tag: text-to-image
+tags:
+- llada-image
+- image-generation
+- image-editing
+- comfyui
+- int8
+- gguf
+- quantized
+- rebelai
+---
+
+# LLaDA-Image Base — ComfyUI INT8 + GGUF
+
+Quantized **LLaDA-Image Base** weights for the **RealRebelAI LLaDA-Image ComfyUI** custom nodes.
+
+Based on **inclusionAI/LLaDA-Image**, this release is intended for lower-memory ComfyUI inference while retaining the Base model workflow.
+
+## ComfyUI Custom Nodes
+
+https://github.com/RealRebelAI/LLaDa-Image_ComfyUI
+
+Install into:
+
+```text
+ComfyUI/custom_nodes/ComfyUI-LLaDA-Image/
+```
+
+Restart ComfyUI after installation.
+
+## Upstream Model
+
+Official Base model:
+
+https://huggingface.co/inclusionAI/LLaDA-Image
+
+Official project:
+
+https://github.com/inclusionAI/LLaDA-Image
+
+This is an unofficial quantized derivative and is not affiliated with inclusionAI.
+
+## Included Weights
+
+### Base INT8 Transformer
+
+```text
+LLaDA-Image-Base-transformer-INT8.safetensors
+```
+
+Place in:
+
+```text
+ComfyUI/models/diffusion_models/
+```
+
+This is a native INT8 **Safetensors transformer**, not a transformer GGUF.
+
+### Base Q4_K_M Text Encoder
+
+```text
+LLaDA-Image-Base-text_encoder-Q4_K_M.gguf
+```
+
+Place in:
+
+```text
+ComfyUI/models/text_encoders/
+```
+
+The custom runtime uses City96 ComfyUI-GGUF support for the quantized LLaDA2 MoE text encoder.
+
+## Requirement
+
+Install City96 ComfyUI-GGUF:
+
+https://github.com/city96/ComfyUI-GGUF
+
+## VAE
+
+Place the compatible LLaDA VAE in:
+
+```text
+ComfyUI/models/vae/
+```
+
+Then select it in **LLaDA Image Loader**.
+
+The current custom nodes expose native VAE tiled decoding:
+
+```text
+vae_tiling:
+On
+Auto
+Off
+```
+
+For low-VRAM GPUs, **On** is a good starting point.
+
+## Base Recommended Settings
+
+```text
+Steps: 50
+CFG:   5.0
+```
+
+LLaDA-Image Base is the full model rather than the distilled few-step Turbo variant.
+
+## Text-to-Image
+
+```text
+LLaDA Image Loader
+        |
+        v
+LLaDA Image Text to Image
+        |
+        v
+    Save Image
+```
+
+Loader example:
+
+```text
+diffusion_model: LLaDA-Image-Base-transformer-INT8.safetensors
+text_encoder:    LLaDA-Image-Base-text_encoder-Q4_K_M.gguf
+vae:             your LLaDA VAE
+dtype:           bfloat16
+vae_tiling:      On
+```
+
+Start with **50 steps / CFG 5.0**.
+
+## Native Image Editing
+
+The custom nodes support LLaDA-Image's **native image-editing mode**.
+
+This is not conventional img2img or denoise-strength emulation. The source image is passed through LLaDA-Image's native:
+
+```text
+generation_mode="editing"
+```
+
+using its image-conditioning/SigVQ path.
+
+```text
+LLaDA Image Loader -----------+
+                              |
+Load Image -------------------+--> LLaDA Image Edit --> Save Image
+```
+
+Example:
+
+```text
+Turn the fox into a white arctic fox while preserving the forest composition and realistic photography.
+```
+
+For Base editing, start with:
+
+```text
+Steps: 50
+CFG:   5.0
+```
+
+Editing width and height must be divisible by **32**.
+
+The same Base transformer and text encoder are used for generation and editing. No separate editing checkpoint is required.
+
+## Base vs Turbo
+
+```text
+Base:
+Steps: ~50
+CFG:   ~5.0
+
+Turbo:
+Steps: ~4
+CFG:   ~1.0
+```
+
+## Low-VRAM Notes
+
+- Use the INT8 transformer.
+- Use the Q4_K_M GGUF text encoder.
+- Enable VAE tiling.
+- Use CPU offload when necessary.
+- Do not load the original full text encoder alongside the quantized encoder.
+
+## Model Placement
+
+```text
+ComfyUI/
+└── models/
+    ├── diffusion_models/
+    │   └── LLaDA-Image-Base-transformer-INT8.safetensors
+    ├── text_encoders/
+    │   └── LLaDA-Image-Base-text_encoder-Q4_K_M.gguf
+    └── vae/
+        └── <LLaDA VAE>.safetensors
+```
+
+## Important
+
+Do **not** load the INT8 transformer through a GGUF diffusion loader. It is native INT8 Safetensors.
+
+The `.gguf` file in this release is the **text encoder**, not the diffusion transformer.
+
+## Credits
+
+- **inclusionAI** — LLaDA-Image architecture and official model
+- **Hugging Face Diffusers** — pipeline/component infrastructure
+- **City96** — ComfyUI-GGUF / GGML support
+- **ComfyUI** — node and inference ecosystem
+- **RealRebelAI** — custom ComfyUI integration and quantized release
+
+## License
+
+The upstream LLaDA-Image model and components remain subject to their original licenses and terms. Review the upstream license before redistribution or commercial use.