Hello everyone. I am Dr. Furkan Gözükara. PhD Computer Engineer. SECourses is a dedicated YouTube channel for the following topics : Tech, AI, News, Science, Robotics, Singularity, ComfyUI, SwarmUI, ML, Artificial Intelligence, Humanoid Robots, Wan 2.2, FLUX, Krea, Qwen Image, VLMs, Stable Diffusion
[CMD] Model loaded successfully. [CMD] Using resolution: width=480 height=832 Only num_frames % 4 != 1num_frames % 4 != 1 is acceptable. We round it up to 121. 0%| | 0/50 [00:00<?, ?it/s]WAN 2.1 14B Image-to-Video 480P
MIDI is a novel paradigm for compositional 3D scene generation from a single image, extending pre-trained 3D object generation models to multi-instance diffusion models for simultaneous generation of multiple 3D instances.
@Furkan Gözükara SECourses Are you seeing the full 32GB in windows from your 5090? Mine only reports 31.5GB and its the difference between fitting the full Wan Model or not.. My 3090 reports 24.0 - in the same task manager so I'm thinking its not the 1024 calculation.
Yeah something different between 30xx/50xx. My 3090 = 24.0 in task manager, 5090 = 31.5 in task manager - and I can't load the full FP16 WAN 2.1 model in 32GB because its 500MB short!! it goes to shared GPU which slows it down a lot.
@Furkan Gözükara SECourses have you found perfect teacache settings for Wan2.1? with no visible quality loss to me: teacache at 0.250 T2V 14B model, with Sage and torch-acceleration i got a 49 frame Wan down to 101 seconds. I can get it faster, but start to notice degradation.
Will you be doing wan/hunyuan lora training tests? I got hunyuan down well, but wan lora's are not coming out well for me with musubi-tuner, but can't tell if its 5090 problem. So much instability with cuda 12.8, sage, triton 3.3
will you use musubi-tuner? I just can't get good lora's for wan with the same dataset as used for good loras on hunyuan. I actually think captions might be required this time for more flexibilty during prompting. But not sure yet. I didn't caption hunyuan and they came out good, sometimes better than flux with kohya.
I just modified TTplanet's one. its a good starting point. Let me know how your Wan Lora success is. I'm going to keep experimenting, and will let you know what i discover too. I think there is a reason character lora's aren't being released as fast as "motion/animation" loras
Also TorchCompileModelWan (for wan21) breaks Lora's on 50xx but not 30xx. Must be the 3.3 triton, or torch nightlies. I just tested. Same workflow works fine on 30xx. but not 50xx with Torchcompile running on both.