These Loras can be used with GGUF?
2
#68 opened about 24 hours ago
by
Noire1

MTVCrafter
2
#66 opened 1 day ago
by
wallen0322

Wan2_1-VACE_module_14B GGUF quants?
#65 opened 2 days ago
by
Flambo111
'Stand In' in official text-to-video workflow
π
1
1
#64 opened 8 days ago
by
makisekurisu-jp

any chance of converting fastwan 14b 720p into a Lora?
π
2
#62 opened 10 days ago
by
ChargeUk
Wan-Lighting : 4steps per model or 4steps total?
4
#59 opened 13 days ago
by
NielsGx
What is the difference between the A14B and 14B models?
3
#58 opened 13 days ago
by
AbsAnon
Could you consider support for the wan 2.2 all-in-one Models.
4
#57 opened 14 days ago
by
lhucklen
Request: MultiTalk support for Wan 2.2 GGUF I2V weights in ComfyUI-WanVideoWrapper
π€
π
9
9
#56 opened 14 days ago
by
squirez
Issue with Wan2_1-T2V-14B_fp8 model. Images look unfinished even after 50 steps.
3
#55 opened 14 days ago
by
healthyfat
i have a request
2
#54 opened 14 days ago
by
markasd

Add prompt extension with local Qwen
π
1
6
#53 opened 15 days ago
by
Breeven
FP16 Lora on FP8 scaled model
4
#52 opened 16 days ago
by
NielsGx
Expose all camera properties of WanVideo Uni3C Embeds
4
#51 opened 16 days ago
by
MavenDE
Base ft model for `Wan21_CausVid_14B_T2V_lora_rank32_v2.safetensors`
π₯
1
#49 opened 16 days ago
by
flymin

A really short question about MultiTalk... please help.
π₯
1
#48 opened 25 days ago
by
JackieZaaa

what is fastwan
19
#47 opened 25 days ago
by
markasd

pusa model
2
#46 opened 29 days ago
by
rahul7star

anisora t2v?
1
#45 opened about 1 month ago
by
MiaoshouAI
This is so great! Thank you very much!
#44 opened about 1 month ago
by
weathon
A minor suggestion: categorize these models and put them into folders.
π
2
7
#43 opened about 1 month ago
by
qq807502278
NLP
#42 opened about 1 month ago
by
Abdulwaisa

LeapFusion Lora for WAN?
#40 opened about 1 month ago
by
whatsadjango
WanCameraEmbedding workflow?
8
#39 opened about 1 month ago
by
MavenDE
ATI lora ? Can ATI Lora be extracted to work with other i2v model such as Magref
1
#35 opened about 2 months ago
by
jasoncow

Magref Lora?
π
2
3
#34 opened about 2 months ago
by
Elvaxorn
Question about LoRA Training Sources
1
#33 opened 2 months ago
by
ZAHNGYUXUAN

ΨͺΨΩΩΩ Ψ§ΩΨ΅ΩΨ±Ω ΩΩ ΩΨ·ΨΉ ΩΩΨ―ΩΩ
π€
1
2
#31 opened 2 months ago
by
bjash922

AccVideo-WanX-I2V-480P-14B
#28 opened 2 months ago
by
kcod
Causvid v2 parameters
3
#27 opened 3 months ago
by
aip0p
No new causvid for 1.3b?
β
2
#26 opened 3 months ago
by
Kutches

e5m2 for T2V & DF 540P SkyReels missing, attempted my own conversion, some direction would be appreciated
2
#23 opened 3 months ago
by
phazei
Add metadata
#22 opened 3 months ago
by
nielsr

img2vid MoviiGen workflow available somewhere?
#21 opened 3 months ago
by
infoperobueno

Model loader bridge to connect GGUF model loader
π
π
5
2
#20 opened 3 months ago
by
PixelPlayer
Wan2_1-VACE_module_1_3B_bf16.safetensors no fp16, where to download ?
#19 opened 3 months ago
by
LeonW666
WAN 2.1 VACE 14B
π
5
#16 opened 3 months ago
by
Rudra-ai
θ―·ζ±δΈθ½½
#15 opened 4 months ago
by
cs13608563672
FP8 version of Fun-V1.1-14B-Control-Camera and Fun-V1.1-14B-InP
β
6
#14 opened 4 months ago
by
deepfree
wan2.1 1.3b Lora - ValueError: Invalid LoRA checkpoint.
2
#13 opened 4 months ago
by
rahul7star

1.3B Fun InP Model
2
#11 opened 5 months ago
by
PixelPlayer
taew2_1.safetensors
1
#10 opened 5 months ago
by
arroyoghost

Which one is lora file? and which is which style?
#9 opened 5 months ago
by
seaman100
FP16 & BF16
2
#7 opened 5 months ago
by
pftq
Why are the model weights larger than the official ComfyUI repo?
1
#6 opened 5 months ago
by
HappyLion2
e4m3fn vs e5m2 for FP8
13
#5 opened 5 months ago
by
NielsGx
Multiple GPUs
π
1
1
#3 opened 6 months ago
by
BigDeeper
Is umt5-xxl-enc-bf16.safetensors the only text encoder model to use with Wan?
2
#2 opened 6 months ago
by
bkmikko