[Bugfix] Fix diffusion pipeline CFG (guidance_scale parsing failure bug) (#922)

Signed-off-by: samithuang <285365963@qq.com>
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
SamitandHongsheng Liu authored and GitHub committed 2026-01-26 05:09:03 +00:00
1 parent 52bf1e2f40
commit 978a290d6e
9 files changed
+51 -27

No files matched your search

@@ -9,10 +9,11 @@ python text_to_video.py \
--prompt "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage." \
--negative_prompt "<optional quality filter>" \
--height 480 \
--width 640 \
--width 832 \
--num_frames 33 \
--guidance_scale 4.0 \
--guidance_scale_high 3.0 \
--flow_shift 12.0 \
--num_inference_steps 40 \
--fps 16 \
--output t2v_out.mp4
@@ -21,9 +22,9 @@ python text_to_video.py \
Key arguments:
- `--prompt`: text description (string).
- `--height/--width`: output resolution (defaults 720x1280). Dimensions should align with Wan VAE downsampling (multiples of 8).
- `--height/--width`: output resolution (defaults 480x832, i.e. 480P). Dimensions should align with Wan VAE downsampling (multiples of 8).
- `--num_frames`: Number of frames (Wan default is 81).
- `--guidance_scale` and `--guidance_scale_high`: CFG scale (applied to low/high)..
- `--guidance_scale` and `--guidance_scale_high`: CFG scale (applied to low/high).
- `--negative_prompt`: optional list of artifacts to suppress (the PR demo used a long Chinese string).
- `--boundary_ratio`: Boundary split ratio for low/high DiT.
- `--fps`: frames per second for the saved MP4 (requires `diffusers` export_to_video).