牧瀬紅莉栖
makisekurisu-jp
AI & ML interests
未来ガジェット研究所のラボメンNo.004
Recent Activity
updated a collection 2 days ago
MiniMax H3 updated a model 3 days ago
makisekurisu-jp/Qwen-Image-2.1-Heretic updated a collection 3 days ago
Krea-2Organizations
int8 convrot version?
1
#12 opened 22 days ago
by
aamobp
Confusion About Base and Distilled Checkpoint Filenames
👍 1
1
#18 opened 10 days ago
by
makisekurisu-jp
Can You Share the System Prompt for the Flux 3 Prompt Upsampler?
1
#19 opened 10 days ago
by
makisekurisu-jp
minimax_h3_ref2va_pruned_w4a8_mixed.safetensors vs minimax_h3_ref2va_pruned_w6a8_g32.safetensors
#50 opened about 1 month ago
by
makisekurisu-jp
Request to add W4A8‑mixed quantization for “fastvideo_fasth3_8step_v2_pruned.”
1
#2 opened about 1 month ago
by
makisekurisu-jp
Multi-View support?
👍 1
7
#4 opened about 2 months ago
by
kalexan94
Please resolve the errors and warnings related to LoRA.
7
#33 opened about 2 months ago
by
makisekurisu-jp
Could your team also create a ControlNet Union model for Krea2?
🔥 3
#3 opened about 2 months ago
by
makisekurisu-jp
Quantization Method Consistency Inquiry
5
#2 opened 2 months ago
by
makisekurisu-jp
W4A8 Diffusion Model Request
6
#52 opened 2 months ago
by
makisekurisu-jp
LTX 2.5 TAE
➕ 2
1
#81 opened 2 months ago
by
makisekurisu-jp
Unpruned W4A8 Diffusion Model Request
2
#27 opened 2 months ago
by
makisekurisu-jp
Unpruned FP8 Text Encoder Request
3
#11 opened 2 months ago
by
makisekurisu-jp
Is pruned_w4a8_mixed identical to a4w8_codebook?
2
#1 opened 3 months ago
by
makisekurisu-jp
Is there an existing workflow?
2
#10 opened 2 months ago
by
QiBao20260618
audio_vae_bf16 + video_vae_fp8
👍 2
3
#10 opened 3 months ago
by
makisekurisu-jp
The model doesn’t work with Comfy’s native nodes.
1
#2 opened 3 months ago
by
makisekurisu-jp
bf16"audio_vae" and fp8"video_vae"
🔥 4
#3 opened 3 months ago
by
makisekurisu-jp
Please release an INT4-quantized version of MiniMax-H3
👍 4
9
#22 opened 3 months ago
by
makisekurisu-jp