ai-models/WanVideo_comfy_fp8_scaled
2
0
Fork 0
mirror of https://www.modelscope.cn/Kijai/WanVideo_comfy_fp8_scaled.git synced 2026-04-02 14:02:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

Upload SCAIL/Wan21-14B-SCAIL-preview_fp8_scaled_mixed.safetensors with ModelScope SDK (batch 1/1)

Browse Source
This commit is contained in:
systemd
2026-02-27 11:24:59 +00:00
parent ffd6279832
commit 1ffd509551
7 changed files with 34 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
.gitattributes vendored
View File

@ -110,3 +110,9 @@ OneToAllAnimation/Wan21-OneToAllAnimation_fp8_e4m3fn_scaled_KJ.safetensors filte
WanMove/Wan21-WanMove_fp8_scaled_e4m3fn_KJ.safetensors filter=lfs diff=lfs merge=lfs -text
SCAIL/Wan21-14B-SCAIL-preview_fp8_e4m3fn_scaled_KJ.safetensors filter=lfs diff=lfs merge=lfs -text
SkyReelsV3/Wan21-SkyReelsV3-A2V_fp8_scaled_mixed.safetensors filter=lfs diff=lfs merge=lfs -text
SCAIL/Wan21-14B-SCAIL-preview_fp8_scaled_mixed.safetensors filter=lfs diff=lfs merge=lfs -text
SkyReelsV3/Wan21_SkyReelsV3-R2V_fp8_scaled_mixed.safetensors filter=lfs diff=lfs merge=lfs -text
SkyReelsV3/Wan21-SkyReelsV3-V2V_fp8_scaled_mixed.safetensors filter=lfs diff=lfs merge=lfs -text
SkyReelsV3/Wan21-SkyReelsV3-V2V_shot_fp8_scaled_mixed.safetensors filter=lfs diff=lfs merge=lfs -text

3
SCAIL/Wan21-14B-SCAIL-preview_fp8_scaled_mixed.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:62b6a9cecae97b3d8b569002715a7c5288d68e5650a8814849a2802518d8bf5c
size 16642119256

13
SkyReelsV3/README.md Normal file
View File

@ -0,0 +1,13 @@
SkyReels V3 models in ComfyUI compatible fp8 scaled format:
Source:
https://huggingface.co/collections/Skywork/skyreels-v3
A2V (TalkingAvatar) is Multitalk variant, works in WanVideoWrapper
R2V (Reference to video) is Phantom variant, should work in any Phantom workflow
V2V is video extension and works same way as Pusa with per token timesteps, so runs in Pusa workflows in WanVideoWrapper
V2V_shot is variant of above that generates new scenes from video, this one still lacks proper workflow but does run same as above.

3
SkyReelsV3/Wan21-SkyReelsV3-A2V_fp8_scaled_mixed.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d48b82c7ed3544449032799a330b591e3f7252919a898dc8f85b5740849350f6
size 19130441452

3
SkyReelsV3/Wan21-SkyReelsV3-V2V_fp8_scaled_mixed.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b88aec3ec8f198a8e019c7a6821c8a73dc77038aa625a4775ad47dacd5a0b492
size 14526278384

3
SkyReelsV3/Wan21-SkyReelsV3-V2V_shot_fp8_scaled_mixed.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:71d4f42b02863f7dfb4fa183c678383b4ec1aa7a873bded533aca869da9beb24
size 14526278392

3
SkyReelsV3/Wan21_SkyReelsV3-R2V_fp8_scaled_mixed.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:54e58e675dc313ccbc7a8ea6c54b3242497d7923746baa6213dfbb33593af839
size 14526278376