Cseti/MiniMax-H3_Ref2VA-LoRA-CrossView-Warp_v1
Updated • 1.15k • 60
Tamás cseh PRO
Cseti
AI & ML interests
Independent AI engineer focused on fine-tuning open-source video and audio generation models.
What I publish here:
• Video LoRAs across
• Image LoRAs
• Hungarian-language TTS/ASR/LLM model finetunes
• ComfyUI workflows
Recent Activity
published a model 4 days ago
Cseti/MiniMax-H3_Ref2VA-LoRA-CrossView-Warp_v1 updated a dataset 4 days ago
Cseti/ComfyUI-Workflows updated a model 5 days ago
Cseti/MiniMax-H3_Ref2VA-LoRA-CrossView-Warp_v1Organizations
published a
model 4 days ago
updated a
dataset 4 days ago
updated a
model 5 days ago
updated a
Space 13 days ago
published a
Space 14 days ago
updated a
model about 1 month ago
published a
model about 1 month ago
Vibe voice hun
3
#2 opened about 1 month ago
by 
Grimbord
color shift on 2nd pass if resolution larger then 1024
1
#2 opened about 2 months ago
by 
billyBang
Any tips to have a 1:1 motion match ?
1
#5 opened about 2 months ago
by 
HarryB
Demo for this model on Spaces
2
#1 opened about 2 months ago
by 
multimodalart
Adapted stereogram version possible?
1
#2 opened 2 months ago
by 
cblinde
distillation
1
#1 opened 2 months ago
by 
anth0nx
updated a
model about 2 months ago
published a
model 2 months ago
The generated results are often mixed up with the reference video content.
2
#4 opened 2 months ago
by 
liuxingsyue
Demo for this model on Spaces
1
#3 opened 2 months ago
by multimodalart
Demo for this model on Spaces
2
#1 opened 2 months ago
by multimodalart