bebop
dummy9996
AI & ML interests
➯➱heartbeat➯7/26➯➱
➯➱storage➯9% used➯➱
Recent Activity
updated a model about 4 hours ago
dummy9996/vaes-bf16 updated a model about 4 hours ago
dummy9996/z-image-models-mxfp8-int8convrot updated a model about 23 hours ago
dummy9996/Qwen3-VL-4B-Instruct-Uncensored-abliteratedOrganizations
None yet
uncensored?
🧠 1
2
#1 opened 20 days ago
by
LordAnuar
Delete Samples and Workflow/new
#3 opened 13 days ago
by
dummy9996
Delete Text Encoder/int8
#5 opened 13 days ago
by
dummy9996
add mxfp8 and nvfp4 quants
❤️ 1
#2 opened 17 days ago
by
dummy9996
your model is shit. "beats Mythos" is a stupid lie, do you understand what have you done?
3
#4 opened 18 days ago
by
dummy9996
What precisely does this do? Is it for getting around the safety filter?
10
#1 opened 19 days ago
by
Eshemizu
why gemma license?
1
#2 opened 18 days ago
by
dummy9996
INT8 convrot Turbo version using INT8-Fast node from BobJohnson is way slower than expected.
7
#3 opened 20 days ago
by
Eshemizu
MXFP8 error: krea2 expects conditioning with 32x2560=81920 features (a 32-layer Qwen3-VL stack) but got 30720. Load the text encoder with CLIPLoader type 'krea2'.
5
#2 opened 20 days ago
by
jtreminio
Doesn't load
6
#1 opened 20 days ago
by
dummy9996
distilled or base?
1
#4 opened 22 days ago
by
filatkinm
please convert it to nvfp4
1
#2 opened 24 days ago
by
dummy9996
boogu_image_turbo_lora_rank_128_bf16.safetensors ?
👍 1
4
#6 opened 25 days ago
by
langchaojin
base nvfp4
2
#5 opened 25 days ago
by
trgtszr
please make nvfp4 and mxfp8 quants, comfyui
#1 opened 26 days ago
by
dummy9996
why the old gemma license instead of Apache 2.0 like the pretrained gemma4?
🔥 3
1
#36 opened 26 days ago
by
dummy9996
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
2
#1 opened about 2 months ago
by
seiban
it must be "on" not "at"
1
#1 opened 28 days ago
by
dummy9996
typo, trim the url
#2 opened 29 days ago
by
dummy9996
The video quality generated by FP4 is really poor
7
#1 opened 29 days ago
by
wuhuoO