patientx
patientxtr
AI & ML interests
None yet
Recent Activity
new activity 16 days ago
Kijai/LTX2.3_comfy:ltx-2.3 720p, 832p, 1080p Test updated a model 27 days ago
patientxtr/qwen-image-edit-fp8-e5m2 new activity about 1 month ago
circlestone-labs/Anima:Fine-tuned / uncensored versions of Qwen 0.6BOrganizations
None yet
ltx-2.3 720p, 832p, 1080p Test
π₯ 1
3
#15 opened 16 days ago
by
lanranjun
Fine-tuned / uncensored versions of Qwen 0.6B
π 8
46
#56 opened about 1 month ago
by
TeoR4eg
On my Tesla V100, it's ten times slower than SDXL.
11
#15 opened about 2 months ago
by
dawn6666
Model Use
π 5
2
#4 opened about 2 months ago
by
dearest
Comfy ui support?
π 1
1
#1 opened 2 months ago
by
ryg81
index_timestep_zero possible solution
2
#5 opened 3 months ago
by
patientxtr
Lora
ππ 4
1
#6 opened 6 months ago
by
Yndear
can you do the newly released x0 as well ?
1
#1 opened 3 months ago
by
patientxtr
do we get q8 for v14 as well ?
1
#2 opened 4 months ago
by
patientxtr
can you look at the clip as well ?
6
#3 opened 4 months ago
by
patientxtr
source quality
2
#15 opened 5 months ago
by
patientxtr
Feedback
π 5
11
#2 opened 5 months ago
by
SG161222
Are these possible to quantize? (lynx models)
2
#21 opened 6 months ago
by
patientxtr
η»OPPOε’ιηΉθ΅οΌη»§η»δΌεγγγ
π 1
8
#5 opened 6 months ago
by
wikeeyang
regarding the "lite" model
2
#9 opened 6 months ago
by
patientxtr
refiner gguf's -old and the new v2- doesn't work with torch.compile or sage-attention
3
#6 opened 6 months ago
by
patientxtr
can you upload "hunyuanimage2.1-distilled-v2-q3" ?
1
#3 opened 6 months ago
by
patientxtr
I'm willing to help with the FP16 version
4
#10 opened 8 months ago
by
TekeshiX
Awesome
π₯ 3
5
#15 opened 9 months ago
by
tbsmsks
fp16 for anisora?
π 1
2
#41 opened 8 months ago
by
jtyy111