Gang WenandClaude Opus 4.6 acbe51c5a2 Use BartTokenizerFast instead of AutoTokenizer to avoid config loading ...

AutoTokenizer tries to load the model config to detect tokenizer type,
which fails because transformers 5.x CONFIG_MAPPING doesn't know
florence2_language. Use BartTokenizerFast directly with tokenizer.json
fallback for models that use different tokenizer formats.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-04-07 20:03:24 +02:00

..

BiRefNet_legacy

first commit

2024-12-05 17:11:26 +08:00

BiRefNet_v2

first commit

2024-12-05 17:11:26 +08:00

evf_sam

first commit

2024-12-05 17:11:26 +08:00

iopaint

fix bug of Lama node

2025-12-11 21:28:45 +08:00

local_groundingdino

Fix GroundingDINO bertwarper for transformers 5.x + PyTorch 2.9+

2026-02-21 10:55:47 -08:00

sam2

first commit

2024-12-05 17:11:26 +08:00

sam_hq

load sam_hq to cpu if cuda is unavailable

2025-01-05 07:42:14 +01:00

ben_ultra.py

Ultra nodes support vitmatte-base-composition-1k

2026-01-30 14:31:25 +08:00

birefnet_legacy.py

first commit

2024-12-05 17:11:26 +08:00

birefnet_ultra_v2.py

Ultra nodes support vitmatte-base-composition-1k

2026-01-30 14:31:25 +08:00

birefnet_ultra.py

Ultra nodes support vitmatte-base-composition-1k

2026-01-30 14:31:25 +08:00

blendmodes.py

first commit

2024-12-05 17:11:26 +08:00

briarmbg.py

first commit

2024-12-05 17:11:26 +08:00

collage.py

commit Collage node

2025-02-13 13:41:27 +08:00

deepseek.py

fix import bug of deepseek.py

2025-09-10 17:27:29 +08:00

evf_sam_ultra.py

Ultra nodes support vitmatte-base-composition-1k

2026-01-30 14:31:25 +08:00

florence2_ultra.py

Use BartTokenizerFast instead of AutoTokenizer to avoid config loading

2026-04-07 20:03:24 +02:00

gemini.py

Update Gemini models and fix inline_data check

2025-08-31 00:39:38 +08:00

get_color_tone_v2.py

first commit

2024-12-05 17:11:26 +08:00

get_color_tone.py

first commit

2024-12-05 17:11:26 +08:00

human_parts_ultra.py

Ultra nodes support vitmatte-base-composition-1k

2026-01-30 14:31:25 +08:00

image_auto_crop_v2.py

first commit

2024-12-05 17:11:26 +08:00

image_auto_crop_v3.py

first commit

2024-12-05 17:11:26 +08:00

image_auto_crop.py

first commit

2024-12-05 17:11:26 +08:00

image_reward_filter.py

fix ImageReward node name to Advance

2024-12-05 22:49:24 +08:00

imagefunc.py

Ultra nodes support vitmatte-base-composition-1k

2026-01-30 14:31:25 +08:00

Jimeng_API.py

commit JimengI2I_API node

2025-08-09 20:50:26 +08:00

joycaption_alpha_2.py

add use_global_model for JoyCaption2.

2025-01-23 19:57:54 +08:00

joycaption_beta_1.py

fix JoyCaptionBetaOne model CPU offload bug

2025-08-04 20:43:44 +08:00

lama.py

first commit

2024-12-05 17:11:26 +08:00

llama_vision.py

first commit

2024-12-05 17:11:26 +08:00

loadpsd.py

first commit

2024-12-05 17:11:26 +08:00

mask_by_different.py

first commit

2024-12-05 17:11:26 +08:00

mediapipe_facial_segment.py

MediapipeFacialSegment node support face_landmarker to compatible Python 3.12 and 3.13

2026-01-22 10:11:17 +08:00

object_detector.py

fix BBoxJoin merging bboxes at image-index level instead of per-image

2026-03-30 07:42:43 +08:00

person_mask_ultra_v2.py

Ultra nodes support vitmatte-base-composition-1k

2026-01-30 14:31:25 +08:00

person_mask_Ultra.py

Fix mask broadcasting error for MediaPipe ≥0.10.30

2025-12-24 17:03:20 +08:00

phi_nodes.py

first commit

2024-12-05 17:11:26 +08:00

prompt_embellish.py

first commit

2024-12-05 17:11:26 +08:00

prompt_tagger.py

first commit

2024-12-05 17:11:26 +08:00

qrcode.py

first commit

2024-12-05 17:11:26 +08:00

Qwen_image2prompt.py

first commit

2024-12-05 17:11:26 +08:00

sam_2_ultra.py

Ultra nodes support vitmatte-base-composition-1k

2026-01-30 14:31:25 +08:00

save_image_plus.py

commit SaveImagePlusV2 node

2025-05-14 20:02:35 +08:00

sd3_negative_conditioning.py

first commit

2024-12-05 17:11:26 +08:00

segment_anything_func.py

first commit

2024-12-05 17:11:26 +08:00

segment_anything_ultra_v2.py

Ultra nodes support vitmatte-base-composition-1k

2026-01-30 14:31:25 +08:00

segment_anything_ultra_v3.py

Ultra nodes support vitmatte-base-composition-1k

2026-01-30 14:31:25 +08:00

segment_anything_ultra.py

first commit

2024-12-05 17:11:26 +08:00

smol.py

fix import issue on Transformers 5.x

2026-01-30 16:31:44 +08:00

transparent_background_ultra.py

Ultra nodes support vitmatte-base-composition-1k

2026-01-30 14:31:25 +08:00

user_prompt_generator.py

first commit

2024-12-05 17:11:26 +08:00

watermark.py

first commit

2024-12-05 17:11:26 +08:00

yolov8_detect.py

Enhance YoloV8Detect node with additional parameters for detection configuration

2025-11-07 14:44:05 +08:00

zhipu_glm4.py

add support GLM-4.5V model of ZhipuGLM4V node

2025-08-13 11:56:41 +08:00