Instructions to use Alex995647/loras-wan-2.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Alex995647/loras-wan-2.2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Wan-AI/Wan2.2-T2V-A14B", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Alex995647/loras-wan-2.2") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
Add 25 LoRA(s): realistic-fire-wan-2-2-i2v-5b, wan-2-2-i2v-unbuttoning-motion, female-superhero-costumes-wan, aether-blast-wan-2-2-5b-i2v-loraโฆ
6802706 verified Download wan2-2-girl-like-cdl-by-aldniki/info.txt from Alex995647/loras-wan-2.2: direct link, hf CLI and curl.
- Browser
- Download file 17.7 kB
-
https://huggingface.co/Alex995647/loras-wan-2.2/resolve/main/wan2-2-girl-like-cdl-by-aldniki/info.txt
- Command line
-
hf download hf://Alex995647/loras-wan-2.2/wan2-2-girl-like-cdl-by-aldniki/info.txt
-
curl -L -o info.txt https://huggingface.co/Alex995647/loras-wan-2.2/resolve/main/wan2-2-girl-like-cdl-by-aldniki/info.txt
17.7 kB
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| WAN2.2 GIRL LIKE CDL BY ALDNIKI | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| IDENTITY | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| 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 ยท model 1872208 ยท version 2119105 | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| WEIGHTS | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| 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 | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| TRIGGER WORDS | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| โบ "cdl_wan" | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| RECOMMENDED SETTINGS | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| Taken verbatim from the author's description: | |
| LoRA strength 1.2 | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| ADOPTION & POPULARITY | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| 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. | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| CHAINING / STACKING | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| 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): | |
| โข 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 โ two LoraLoaderModelOnly nodes | |
| on two different models, never both on one model. | |
| โข 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. | |
| โข 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. | |
| โข 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. | |
| โข Do not stack two step-distillation LoRAs on the same expert. One | |
| accelerator per expert. | |
| โข When adding subject LoRAs on top of a 4-step distill LoRA, reduce the | |
| subject LoRA strength rather than the distill LoRA strength โ the | |
| distill LoRA is what keeps 4 steps viable at cfg 1.0. | |
| โข 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. | |
| โข TI2V-5B LoRAs chain like any single-model LoRA and can never be mixed | |
| into an A14B chain, or the reverse โ the two have entirely different | |
| tensor geometry. | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| PROS | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| + Well established โ 1,166 downloads. [source: CivitAI stats] | |
| + Positively received โ 50 thumbs-up with no down-votes. [source: CivitAI | |
| stats] | |
| + Explicit trigger word(s) โ cdl_wan โ so the effect can be turned on and | |
| off from the prompt. [source: model metadata] | |
| + Compact at 293 MB โ cheap to stack with other LoRAs. [source: file | |
| size] | |
| + Author published concrete recommended settings. [source: description] | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| CONS & CAVEATS | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| (none recorded) | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| COMPATIBILITY WARNING | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| 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 โ 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". | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| AUTHOR'S DESCRIPTION | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| You can use the online workflow below. If the results are good, you can | |
| then try setting it up and running it locally. | |
| ๐ Click Here For Online WorkFlow | |
| As a fan benefit, youโll 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 โ T2I generation โ T2V generation โ Combine with other LoRAs for | |
| unique styles | |
| ๆจกๅไป็ป ่ฟๆฏไธไธชไธๆณจไบ ไบๆดฒๅฅณๆง้ฃๆ ผ ็ LoRA๏ผ ้ๅฏนไบ Wan2.2 T2V ่ฟ่ก่ฎญ็ปใ ๆ ่ฎบๆฏๆ็ๅพ่ฟๆฏๆ็่ง้ข๏ผ้ฝ่ฝๅ็ฐ่ช็ถใ็ฒพ่ด็ๆๆใ | |
| ๆจ่่ฎพ็ฝฎ - ้ซๅช็ๆ้ : 1.2 | |
| - ไฝๅช็ๆ้ : 1.2 | |
| ไฝฟ็จๅบๆฏ โ ๆๆฌ็ๆๅพ็ (T2I) โ ๆๆฌ็ๆ่ง้ข (T2V) โ ไธๅ ถไป LoRA ๆญ้ ๅฎ็ฐไธชๆงๅ้ฃๆ ผๆข็ดข | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| EXAMPLE MEDIA | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| 6 preview(s) in ./example_images/ โ 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 | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| HOW TO USE (COMFYUI) | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| 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 โ 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 โ 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 โ 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 โ 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. | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |
| 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. | |
| โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ | |