═══════════════════════════════════════════════════════════════════════════════ WAN2.2 GIRL LIKE CDL BY ALDNIKI ═══════════════════════════════════════════════════════════════════════════════ ─────────────────────────────────────────────────────────────────────────────── IDENTITY ─────────────────────────────────────────────────────────────────────────────── Base model Wan 2.2 Generation mode T2V (Text-to-Video) Checkpoint T2V-A14B (MoE 14B, high- and low-noise experts) Category Character / subject Author aldniki217 Source https://civitai.com/models/1872208 Provenance CivitAI · model 1872208 · version 2119105 ─────────────────────────────────────────────────────────────────────────────── WEIGHTS ─────────────────────────────────────────────────────────────────────────────── File aldniki_cdl_wan22_t2v_high_v01.safetensors Version T2V High Noise v1.0 Size 292.6 MB Format SafeTensor / unknown precision SHA256 05de9384ac9a777b89ee405827f27b82b617b3e1fa7f9cfed69ed979bc35436a Published 2025-08-16 ─────────────────────────────────────────────────────────────────────────────── TRIGGER WORDS ─────────────────────────────────────────────────────────────────────────────── › "cdl_wan" ─────────────────────────────────────────────────────────────────────────────── RECOMMENDED SETTINGS ─────────────────────────────────────────────────────────────────────────────── Taken verbatim from the author's description: LoRA strength 1.2 ─────────────────────────────────────────────────────────────────────────────── ADOPTION & POPULARITY ─────────────────────────────────────────────────────────────────────────────── Downloads 1,166 Rating 100% positive (50/50) Comments 7 Published 388 days ago Download rate 1.7/day since release Adoption rank #155 of 200 in this collection (Niche) Momentum rank #191 of 200 by download rate (Long tail) Adoption tier is the percentile of total downloads within this collection; momentum is the percentile of downloads-per-day since release. Momentum is ranked rather than measured against a fixed rate, because this base model is itself new and every LoRA looks fast on an absolute scale. Both numbers are CivitAI's, read on the scrape date at the foot of this file. ─────────────────────────────────────────────────────────────────────────────── 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): • 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 — two LoraLoaderModelOnly nodes on two different models, never both on one model. • 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. • 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. • 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. • Do not stack two step-distillation LoRAs on the same expert. One accelerator per expert. • When adding subject LoRAs on top of a 4-step distill LoRA, reduce the subject LoRA strength rather than the distill LoRA strength — the distill LoRA is what keeps 4 steps viable at cfg 1.0. • 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. • TI2V-5B LoRAs chain like any single-model LoRA and can never be mixed into an A14B chain, or the reverse — the two have entirely different tensor geometry. ─────────────────────────────────────────────────────────────────────────────── PROS ─────────────────────────────────────────────────────────────────────────────── + Well established — 1,166 downloads. [source: CivitAI stats] + Positively received — 50 thumbs-up with no down-votes. [source: CivitAI stats] + Explicit trigger word(s) — cdl_wan — so the effect can be turned on and off from the prompt. [source: model metadata] + Compact at 293 MB — cheap to stack with other LoRAs. [source: file size] + Author published concrete recommended settings. [source: description] ─────────────────────────────────────────────────────────────────────────────── CONS & CAVEATS ─────────────────────────────────────────────────────────────────────────────── (none recorded) ─────────────────────────────────────────────────────────────────────────────── 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 — 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 ─────────────────────────────────────────────────────────────────────────────── You can use the online workflow below. If the results are good, you can then try setting it up and running it locally. 👉 Click Here For Online WorkFlow As a fan benefit, you’ll receive 1,000 points upon registration, plus 100 points for daily logins. Enjoy a smooth experience with an RTX 4090 and 48GB of VRAM. Model Description This is a LoRA specialized in Asian female style , trained for Wan2.2 T2V . It works well for both text-to-image and text-to- video tasks, producing natural and refined results. Recommended Settings - High-noise version weight : 1.2 - Low-noise version weight : 1.2 Use Cases ✅ T2I generation ✅ T2V generation ✅ Combine with other LoRAs for unique styles 模型介绍 这是一个专注于 亚洲女性风格 的 LoRA, 针对于 Wan2.2 T2V 进行训练。 无论是文生图还是文生视频,都能呈现自然、精致的效果。 推荐设置 - 高噪版权重 : 1.2 - 低噪版权重 : 1.2 使用场景 ✅ 文本生成图片 (T2I) ✅ 文本生成视频 (T2V) ✅ 与其他 LoRA 搭配实现个性化风格探索 ─────────────────────────────────────────────────────────────────────────────── EXAMPLE MEDIA ─────────────────────────────────────────────────────────────────────────────── 6 preview(s) in ./example_images/ — 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, 480x832) still: 01_poster.jpg 02_video.mp4 (video, 480x832) still: 02_poster.jpg 03_video.mp4 (video, 1440x2560) still: 03_poster.jpg 04_video.mp4 (video, 1440x2560) still: 04_poster.jpg 05_video.mp4 (video, 480x832) still: 05_poster.jpg 06_video.mp4 (video, 480x832) 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 — 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 — 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 — 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 — 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 2026-09-08 13:30 UTC. Stats and description are the author's; pros/cons are derived from the evidence tagged beside each line. ───────────────────────────────────────────────────────────────────────────────