Alex995647's picture
Top up example media for 150 LoRAs
5a5f29e verified
Raw History Blame Contribute Delete
21 kB
═══════════════════════════════════════════════════════════════════════════════
CAMERA TILT-UP OVERHEAD-过鑢升摇
═══════════════════════════════════════════════════════════════════════════════
───────────────────────────────────────────────────────────────────────────────
IDENTITY
───────────────────────────────────────────────────────────────────────────────
Base model Wan 2.2
Generation mode I2V (Image-to-Video)
Checkpoint not determined β€” verify before use
Category Physical effect / transformation
Author zakakki
Source https://civitai.com/models/1878750
Provenance CivitAI Β· model 1878750 Β· version 2126493
───────────────────────────────────────────────────────────────────────────────
WEIGHTS
───────────────────────────────────────────────────────────────────────────────
File Highnoise_Camera Tilt-up Overhead-过鑢升摇v1.1_e22.safetensors
Version highnoiseV1.0
Size 585.1 MB
Format SafeTensor / unknown precision
SHA256 5e073237fd7d77c5c5422f9a467760300e34d2a3ca526ed3bcafb7fac149d1b4
Published unknown
───────────────────────────────────────────────────────────────────────────────
TRIGGER WORDS
───────────────────────────────────────────────────────────────────────────────
β€Ί "(过鑢升摇)."
β€Ί "The camera travels forward, gradually soaring up and panning to an
overhead view directly above the woman's head"
───────────────────────────────────────────────────────────────────────────────
RECOMMENDED SETTINGS
───────────────────────────────────────────────────────────────────────────────
The author did not publish specific settings.
No author settings were published. Community baseline: steps Official
Wan2.2 reference code (wan/configs/): sample_steps 40 for T2V-A14B and
I2V-A14B with the expert handover at the SNR boundary, and 50 for TI2V-5B.
ComfyUI's CURRENT 14B t2v/i2v templates ship only the distilled
configuration: 4 steps total, split 2 on the high-noise expert then 2 on
the low-noise expert (two KSamplerAdvanced nodes, start/end 0->2 and 2->4).
An undistilled 20-step configuration split 10/10 shipped as a second,
bypassed node group in an earlier revision of the t2v template and still
ships as the ACTIVE default in the current video_wan2_2_14B_flf2v template
(20 steps, split 0->10 and 10->end). TI2V-5B: 20 steps in ComfyUI's
template, 50 in the reference code; single sampler, no split., cfg Official
reference sample_guide_scale is a per-expert pair: (3.0 low- noise, 4.0
high-noise) for T2V-A14B and (3.5, 3.5) for I2V-A14B β€” the two experts are
allowed different CFG. TI2V-5B: 5.0 in both the reference code and
ComfyUI's template. Undistilled ComfyUI values vary by template revision:
3.5 in the older t2v template's bypassed undistilled group, 4.0 in the
current flf2v template. With ANY 4-step distill LoRA: cfg 1.0 on both
samplers (verified in the shipped t2v and i2v templates)., sampler euler +
simple scheduler on both A14B experts, with shift set via ModelSamplingSD3:
5.0 in ComfyUI's current distilled 14B t2v/i2v templates, 8.0 in the
undistilled groups (older t2v revision, and the current flf2v template).
Official reference sample_shift differs by task: 12.0 for T2V-A14B, 5.0 for
I2V-A14B, 5.0 for TI2V-5B. TI2V-5B in ComfyUI: uni_pc + simple, shift 8.0.,
resolution A14B: 480P and 720P β€” 1280x720 or 832x480 (and portrait).
Dimensions should be multiples of 16 (Wan2.1 VAE stride 4x8x8 combined with
1x2x2 patching, both read from the reference configs); ComfyUI's templates
ship a cheap 640x640. Length 81 frames at 16 fps (~5s), frames 4n+1.
TI2V-5B: 720P, 1280x704 or 704x1280; multiples of 32, because the
Wan2.2-VAE stride is 4x16x16 and the model card states an additional
patchification layer brings total compression to 4x32x32 β€” which is why it
is 704, not 720. Length 121 frames at 24 fps (~5s)., lora_strength Official
Lightning/lightx2v 4-step LoRAs: 1.0 on both experts β€” verified in
ComfyUI's shipped t2v and i2v templates, where both LoraLoaderModelOnly
nodes carry strength 1.0. Character/style/motion LoRAs are commonly run at
0.6-1.0, and when stacked on top of a 4-step distill LoRA the usual
community move is to pull the high-noise-side strength down (roughly
0.5-0.8); those subject-LoRA numbers are community practice, not published
by the authors β€” see "unverified"..
───────────────────────────────────────────────────────────────────────────────
ADOPTION & POPULARITY
───────────────────────────────────────────────────────────────────────────────
No statistics available.
───────────────────────────────────────────────────────────────────────────────
COMMUNITY NOTES
───────────────────────────────────────────────────────────────────────────────
17 comment(s) on the source listing; showing 5.
[+4] It would be more interesting to tilt the camera from below. to look
so to speak into the secret
[+2] Fantastic work. This allows for a lot more creative possibilities
and camera angles.
β€’ πŸ‘πŸ»πŸ‘πŸ»πŸ‘πŸ»
β€’ Thanks for including English alongside in the file name
β€’ Is there a chance that you will make one that moves the camera from
top to eye level angle?
Archive summary:
Camera Tilt-up Overhead-过鑢升摇 is a concept LoRA designed for Wan Video-
family checkpoints, published by [zakakki](/users/zakakki) on CivitAI
in August 2025, now on version 2. It layers on top of any compatible
Wan Video checkpoint. You load the checkpoint first, then apply this
LoRA on top of it. Wan 2.2 uses a two-pass architecture β€” a high-noise
model handles motion and scene composition, and a low-noise model
refines detail. Both models need to be loaded together for a complete
pipeline; a single pass on its own won't produce usable output. When
using speed LoRAs (lightx2v, CausVid, Lightnin
Source: https://civarchive.com/models/1878750?modelVersionId=2126493
Comments are other users' words, reproduced as written.
───────────────────────────────────────────────────────────────────────────────
CHAINING / STACKING
───────────────────────────────────────────────────────────────────────────────
Stacks with others not stated
The author gave no chaining guidance. The rules below are the
general Wan 2.2 ones, not anything specific to this LoRA.
General Wan 2.2 rules that apply here (see REFERENCE.txt):
β€’ The high/low pair is not a stack. Every A14B LoRA that ships two files
needs the high-noise file on the high-noise UNET chain and the low-
noise file on the low-noise UNET chain β€” two LoraLoaderModelOnly nodes
on two different models, never both on one model.
β€’ Never load a high-noise LoRA onto the low-noise expert or vice versa.
It loads without a single warning because the two checkpoints are
architecturally identical, and the damage shows up only as degraded
output. Filename is the only guard.
β€’ A single-file A14B LoRA with no high/low marking (common for Wan2.1-era
LoRAs and for LoRAs extracted from merged models) goes on BOTH experts
at the same strength. Loading it only on the low-noise expert is the
safer half-measure when it fights the composition.
β€’ Stack subject/style LoRAs after the accelerator LoRA in the chain:
UNETLoader -> Lightning LoRA -> subject LoRA -> ModelSamplingSD3. Order
within LoraLoaderModelOnly chains is additive so it rarely matters
mathematically, but keeping the accelerator first matches every
reference workflow.
β€’ Do not stack two step-distillation LoRAs on the same expert. One
accelerator per expert.
β€’ When adding subject LoRAs on top of a 4-step distill LoRA, reduce the
subject LoRA strength rather than the distill LoRA strength β€” the
distill LoRA is what keeps 4 steps viable at cfg 1.0.
β€’ Keep the LoRA strength for the two experts independently tunable.
Because the high-noise expert owns layout and the low-noise expert owns
detail, the community routinely runs a style LoRA weaker on high-noise
and full-strength on low-noise.
β€’ TI2V-5B LoRAs chain like any single-model LoRA and can never be mixed
into an A14B chain, or the reverse β€” the two have entirely different
tensor geometry.
β€’ The author never states which weight family this targets. Three
distinct answers. The structural half of each is verified from the
shipped config.json and safetensors index files; the behavioural
severity is community-reported and flagged in "unverified". (1) A14B
<-> TI2V-5B: INCOMPATIBLE. The 5B model is dim 3072 / 30 layers / 24
head
───────────────────────────────────────────────────────────────────────────────
PROS
───────────────────────────────────────────────────────────────────────────────
+ Widely adopted β€” 6,578 downloads. [source: CivitAI stats]
+ Positively received β€” 225 thumbs-up with no down-votes. [source:
CivitAI stats]
+ Explicit trigger word(s) β€” (过鑢升摇)., The camera travels forward,
gradually soaring up and panning to an overhead view directly above the
woman's head β€” so the effect can be turned on and off from the prompt.
[source: model metadata]
───────────────────────────────────────────────────────────────────────────────
CONS & CAVEATS
───────────────────────────────────────────────────────────────────────────────
- Thin documentation β€” expect trial and error. [source: description
length]
───────────────────────────────────────────────────────────────────────────────
COMPATIBILITY WARNING
───────────────────────────────────────────────────────────────────────────────
Three distinct answers. The structural half of each is verified from the
shipped config.json and safetensors index files; the behavioural severity
is community-reported and flagged in "unverified". (1) A14B <-> TI2V-5B:
INCOMPATIBLE. The 5B model is dim 3072 / 30 layers / 24 heads / ffn 14336
against the A14B's dim 5120 / 40 layers / 40 heads / ffn 13824 (both
configs fetched and compared). In ComfyUI native this is SILENT
DEGRADATION, not a hard error: keys for blocks 30-39 hit
logging.warning("lora key not loaded: {}") in comfy/lora.py, and keys for
blocks 0-29 match by name but not by shape, so they hit the shape guard
logging.warning("WARNING SHAPE MISMATCH {} WEIGHT NOT MERGED") in
comfy/lora.py or the caught exception logging.error("ERROR ...") in
comfy/weight_adapter/lora.py, which returns the weight unmodified. All
three call sites were read in the current ComfyUI source. The queue
completes, no exception reaches the UI, and the output is effectively that
of the LoRA node bypassed. (2) T2V-A14B <-> I2V-A14B: STRUCTURALLY
COMPATIBLE, behaviourally risky. Verified from the safetensors index files:
both experts carry exactly 1095 tensors with identical key names, and the
only tensor whose shape differs is patch_embedding.weight (in_dim 16 vs
36), which LoRA trainers normally exclude. So a T2V-A14B LoRA loads onto
I2V-A14B and vice versa with no warnings. What you get is a real but off-
target effect. Treat cross-loading as "loads and does something", never as
"certified". (3) High-noise expert <-> low-noise expert (within one A14B
family): the two checkpoints have identical architecture, so a LoRA trained
on one loads onto the other with zero warnings. This is the most dangerous
case in the family, because there is no signal at all that you mismatched.
Filename is the ONLY discriminator. (4) Wan2.1 14B LoRAs. Verified:
Wan2.1-T2V-14B's config.json is dim 5120 / ffn 13824 / 40 layers / 40 heads
/ in_dim 16 β€” the same block geometry as Wan2.2-A14B, so Wan2.1 T2V LoRAs
load. Wan2.1-I2V-14B is only a partial match: its index has 1303 tensors
including 8 img_emb.* keys and 200 cross_attn k_img/v_img keys for its CLIP
path, which Wan2.2-I2V dropped entirely (0 such keys); those will be
skipped with "lora key not loaded".
───────────────────────────────────────────────────────────────────────────────
AUTHOR'S DESCRIPTION
───────────────────────────────────────────────────────────────────────────────
(the author left no description)
───────────────────────────────────────────────────────────────────────────────
EXAMPLE MEDIA
───────────────────────────────────────────────────────────────────────────────
6 preview(s) in ./example_images/ β€” community results for
this LoRA. Videos keep a matching _poster.jpg still frame.
No prompts are recorded below: CivitAI's public API flags these posts as
having generation metadata but does not return it, so the prompts cannot be
scraped. Open the model page to read them.
01_video.mp4 (video, 432x672)
still: 01_poster.jpg
02_video.mp4 (video, 400x720)
still: 02_poster.jpg
03_video.mp4 (video, 464x624)
still: 03_poster.jpg
04_video.mp4 (video, 448x640)
still: 04_poster.jpg
05_video.mp4 (video, 832x480)
still: 05_poster.jpg
06_video.mp4 (video, 832x480)
still: 06_poster.jpg
───────────────────────────────────────────────────────────────────────────────
HOW TO USE (COMFYUI)
───────────────────────────────────────────────────────────────────────────────
1. Put every LoRA .safetensors in ComfyUI/models/loras/ (subfolders are
fine and are used by reference workflows). Confirmed by the file-layout
tree inside ComfyUI's own video_wan2_2_14B_t2v template note.
2. Install the base weights alongside them. A14B (from Comfy-
Org/Wan_2.2_ComfyUI_Repackaged, split_files/):
diffusion_models/wan2.2_{t2v,i2v}_high_noise_14B_fp8_scaled.safetensors AND
the matching _low_noise_ file β€” you need both;
text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors;
vae/wan_2.1_vae.safetensors. TI2V-5B:
diffusion_models/wan2.2_ti2v_5B_fp16.safetensors, the same umt5 text
encoder, and vae/wan2.2_vae.safetensors.
3. Load the base model with UNETLoader ("Load Diffusion Model"), NOT
CheckpointLoaderSimple β€” Wan2.2 ships as a bare diffusion model, with the
text encoder loaded separately by CLIPLoader (type "wan") and the VAE by
VAELoader. This is the node set used in every shipped Wan2.2 template.
4. For A14B, build two parallel chains, one per expert: UNETLoader
(high_noise) -> LoraLoaderModelOnly -> ModelSamplingSD3(shift) ->
KSamplerAdvanced, and separately UNETLoader (low_noise) ->
LoraLoaderModelOnly -> ModelSamplingSD3(shift) -> KSamplerAdvanced. Use
LoraLoaderModelOnly, not LoraLoader β€” Wan LoRAs patch the DiT only, there
is no CLIP side to patch.
5. Put the high-noise LoRA file on the high-noise chain and the low-noise
LoRA file on the low-noise chain. If a LoRA ships as a single file with no
high/low marking, loading the same file on both chains is the standard
community handling.
6. Wire the two KSamplerAdvanced nodes in series on one latent: the first
(high-noise) runs add_noise=enable, start_at_step 0, end_at_step =
boundary, return_with_leftover_noise=enable; the second (low-noise) runs
add_noise=disable, start_at_step = boundary, end_at_step = total,
return_with_leftover_noise=disable. Boundary is step 2 of 4 with a 4-step
Lightning LoRA, step 10 of 20 undistilled.
7. For TI2V-5B there is only one chain and one KSampler: UNETLoader ->
LoraLoaderModelOnly -> ModelSamplingSD3 -> KSampler. No expert split, no
second sampler.
8. Fastest correct start: load ComfyUI's built-in templates
video_wan2_2_14B_t2v / video_wan2_2_14B_i2v / video_wan2_2_14B_flf2v /
video_wan2_2_5B_ti2v (Workflow > Browse Templates) and swap the LoRA
filenames β€” the 14B templates already ship the two-expert plumbing and the
Lightning LoRA nodes wired correctly. Note the 14B t2v/i2v templates are
now packaged as a subgraph.
───────────────────────────────────────────────────────────────────────────────
Scraped by lorakit on 2026-09-05 03:49 UTC.
Stats and description are the author's; pros/cons are derived from the
evidence tagged beside each line.
───────────────────────────────────────────────────────────────────────────────