Sumire Komurasaki

sumirecccp's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in llmfan46/Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved-GGUF 4 minutes ago

The only Qwen3.8-27B that has worked for me so far

🚀👍 2

3

#2 opened 8 days ago by

dimocritus

New activity in Qwen/Qwen-Image-2.1 1 day ago

Test comparison. Minimax h3 vs Qwen-Image-2.1. Image generation.

🔥 12

6

#27 opened 1 day ago by

Pvok

New activity in Qwen/Qwen-Image-2.1 2 days ago

光影，参考能力，脸不变能力仍不及预期，希望再接再厉

1

#11 opened 2 days ago by

sumirecccp

New activity in Qwen/Qwen3.8-27B about 1 month ago

代码能力可能变强了，但是写作能力明显变弱了

👍 6

12

#107 opened about 1 month ago by

sumirecccp

New activity in MiniMaxAI/MiniMax-H3 about 2 months ago

脱领带，脱上衣，脱带搭袢的鞋等还无法正常表现

1

#59 opened about 2 months ago by

sumirecccp

New activity in QrusherZA/H3_Turbo_ComfyUI about 2 months ago

The real‑human video test works well.

1

#4 opened about 2 months ago by

xtanqn

New activity in Abiray/MiniMax-H3-Turbo-Lora-Pruned-ComfyUI about 2 months ago

[ERROR] !!! Exception during processing !!! Error while deserializing header: incomplete metadata, file not fully covered

2

#1 opened about 2 months ago by

sumirecccp

New activity in larryvrh/MiniMax-H3-Turbo-Lora about 2 months ago

[ERROR] ERROR lora diffusion_model.blocks.0.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384

5

#9 opened about 2 months ago by

sumirecccp

[ERROR] ERROR lora diffusion_model.blocks.0.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384

5

#9 opened about 2 months ago by

sumirecccp

[ERROR] ERROR lora diffusion_model.blocks.0.adaln_proj.linear.weight shape '[96768, 8]' is invalid for input of size 260112384

5

#9 opened about 2 months ago by

sumirecccp