nodes/neverbiasu-ComfyUI-BAGEL
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
35 Commits 6 Branches 0 Tags
master
Commit Graph
6 Commits
Author SHA1 Message Date
Faych 5fa366d4d6 feat: Migrating the project into ComfyUI native style (#42) 
* docs: design ComfyUI-native BAGEL migration

* docs: plan ComfyUI-native BAGEL migration

* docs: align BAGEL migration with custom node layout

* docs: define BAGEL test environment constraints

* docs: split BAGEL nodes by responsibility

* docs: retain flat custom node entrypoints

* feat: add converted BAGEL runtime loader

* feat: register native BAGEL ComfyUI nodes

* docs: document native BAGEL workflows

* fix: add custom node root to import path

* fix: log skipped BAGEL model discovery entries

* fix: prefer BAGEL model folder for native checkpoints

* feat: add BAGEL sidecar metadata helper

* fix: list BAGEL safetensors without metadata precheck

* fix: preserve BAGEL extra model paths

* fix: set Qwen token ids for BAGEL config fallback

* fix: decouple default Qwen RoPE from transformers registry

* feat: add streaming BAGEL metadata embedder

* feat: add free Colab metadata release workflow

* feat: describe BAGEL variant release metadata

* feat: prepare remaining BAGEL metadata releases

* fix: declare Echo-4o release as fp16

* fix: validate BAGEL latent image geometry

* fix: align BAGEL edit workflow preprocessing

* docs: add native BAGEL workflow figures

* chore: prepare 1.1.0 release contents

* docs: finalize release README and metadata validation

* fix: restore native BAGEL parity and lifecycle

* fix: align native controls with BAGEL app

* fix: migrate native thinking workflow controls

* docs: update native workflow examples

* fix: mark legacy nodes as deprecated
 2026-07-31 01:56:08 +01:00
Fayche 1aaced4169 chore: bump version to 1.0.7 2025-08-29 17:45:06 +08:00
绯世 Haise e806fc1ca0 feat: Enhance BAGEL Model Loader with Dynamic Quantization Support (#30) 
* feat: Enhance BAGEL Model Loader with Dynamic Quantization Support

- Added support for dynamic quantization modes (BF16, NF4, INT8) in BagelModelLoader.
- Updated INPUT_TYPES to include quantization options and advanced settings.
- Enhanced VALIDATE_INPUTS to validate quantization modes and check for bitsandbytes availability.
- Modified load_model to handle different quantization modes and improved memory management.
- Updated model loading logic to accommodate quantization configurations.
- Adjusted cfg_renorm_min default values in BagelTextToImage and BagelImageEdit classes.
- Added bitsandbytes as a requirement in requirements.txt.

* feat: Add optimal memory calculation for GPU based on quantization mode

* feat: Update README and pyproject.toml for advanced quantization support and version bump to 1.0.4

* fix: Revise device_map

* refactor: Clean up comments and improve code readability in BagelModelLoader

* feat: Update BAGEL workflows with enhanced node configurations and improved properties

* feat: Add offload directory creation for model dispatch in BagelModelLoader
 2025-06-06 01:54:43 +08:00
Faych Chen 777a359273 Merge pull request #21 from neverbiasu/df 
feat: Refactor inferencer and improve df11 model loading logic
 2025-05-30 12:22:06 +08:00
Fayche e0d074858c feat: Update example workflows and assets 2025-05-29 00:45:57 +08:00
Fayche 3e7687af2d feat: Add examples and update README 2025-05-26 13:08:16 +08:00