All issues

Search results

Missing FP8 quantized MiniMax-H3 models referenced in configs

Status: Open.

#1445 In ModelTC/LightX2V;

· nanwanj opened on Aug 26, 2026

[Bug] Qwen-Image-Edit-2509 Scaled FP8 inference fails with BF16/FP8 dtype mismatch on RTX A6000

bugSomething isn't workingSomething isn't working

Status: Open.

#1439 In ModelTC/LightX2V;

· zddpk-cyber opened on Aug 26, 2026

[Model Request] T3-Video (generates 2k videos very fast, almost realtime)

Status: Open.

#1425 In ModelTC/LightX2V;

· MeiYi-dev opened on Aug 24, 2026

Replace deprecated v2.ToTensor() in wan_matrix_game2_runner.py with v2.ToImage() + v2.ToDtype(scale=True)

Status: Open.

#1418 In ModelTC/LightX2V;

· xyf5432 opened on Aug 23, 2026

[Bug] Qwen2.5-VL image-edit encoder drops mm_token_type_ids with Transformers 5.15

Status: Open.

#1416 In ModelTC/LightX2V;

· llc1123 opened on Aug 22, 2026

[model request] sensenova/SenseNova-U1.5-8B-MoT-Preview

Status: Open.

#1347 In ModelTC/LightX2V;

· dape1984 opened on Aug 10, 2026

[Model Request]新增对MiniMax H3的视频模型的4或8 steps LoRA支持

Status: Open.

#1321 In ModelTC/LightX2V;

· Goan114 opened on Aug 3, 2026

[Question] Scail-2 dedicated distill lora

Status: Open.

#1295 In ModelTC/LightX2V;

· bondobrus opened on Jul 24, 2026

how can I get InfiniteTalk-4StepDistill-Mean-w-ITAudioAdaptorV6.1-fp8.safetensors

Status: Open.

#1293 In ModelTC/LightX2V;

· lianshiyong opened on Jul 24, 2026

Release distilled SGMD video checkpoints on Hugging Face

Status: Open.

#1286 In ModelTC/LightX2V;

· NielsRogge opened on Jul 23, 2026

[Bug] Wan2.2 LightX2V LoRA Merge Fails to Match cross_attn.k_img and cross_attn.v_img Keys

bugSomething isn't workingSomething isn't working

Status: Open.

#1246 In ModelTC/LightX2V;

· xuansu-genmo opened on Jul 14, 2026

Do you have any plan to train a lightning lora for flux.2-klein-base 4B/9B?

Status: Open.

#1182 In ModelTC/LightX2V;

· 2502128021 opened on Jun 25, 2026