═══════════════════════════════════════════════════════════════════════════════ CLAYMATION TRANSFORMATION - MINIMAX H3 R2VA / WAN2.2-2.1 14B T2V ═══════════════════════════════════════════════════════════════════════════════ ─────────────────────────────────────────────────────────────────────────────── IDENTITY ─────────────────────────────────────────────────────────────────────────────── Base model MiniMax H3 Generation mode Reference-to-Video (Ref2VA), Text-to-Video (T2VA), First-and-Last-Frame-to-Video (FL2VA), Image-to-Video (I2VA, first frame) Checkpoint both families — see the author's builds Category Physical effect / transformation Author kabachuha Source https://civitai.com/models/1659949 Provenance CivitAI · model 1659949 · version 3222216 ─────────────────────────────────────────────────────────────────────────────── WEIGHTS ─────────────────────────────────────────────────────────────────────────────── File mh3-lys.safetensors Version v2.1-MH3-R2VA Size 284.4 MB Format SafeTensor / unknown precision SHA256 27cfa30f804a464c1e018e22efc271fa067d05abd47acca2d3545d67976a4774 Published 2026-08-12 ─────────────────────────────────────────────────────────────────────────────── TRIGGER WORDS ─────────────────────────────────────────────────────────────────────────────── › "LYS-Style" › "plasticine-transforms" › "plasticine-melts" ─────────────────────────────────────────────────────────────────────────────── RECOMMENDED SETTINGS ─────────────────────────────────────────────────────────────────────────────── Taken verbatim from the author's description: Resolution 512x512 CFG / guidance 6.0 Frame count 48 ─────────────────────────────────────────────────────────────────────────────── ADOPTION & POPULARITY ─────────────────────────────────────────────────────────────────────────────── Downloads 1,782 Rating 100% positive (143/143) Comments 0 Published 23 days ago Download rate 26.4/day since release Adoption rank #23 of 114 in this collection (High) Momentum rank #52 of 114 by download rate (Steady · fresh release) 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 What the author says (fact-checked against their own text): The author says nothing anywhere about combining this LoRA with other LoRAs - no stacking, order, weight-splitting, or incompatibility guidance. The only combination guidance concerns VACE, which is a separate model/workflow rather than a LoRA: for the Wan2.1 T2V version the author writes "Works great both standalone and with VACE for first- last-frame selection and image to video!" (verbatim in the record's description), and for those modes "For image2video/flf2video recommended to use with the kijai VACE workflows" (verbatim on the live CivitAI page; the stored description is truncated before this sentence). VACE is explicitly optional - the author states the LoRA works standalone - so it is a recommended pairing for i2v/flf2v modes only, not a requirement. General MiniMax H3 rules that apply here (see REFERENCE.txt): • Load the LoRA with LoraLoaderModelOnly between UNETLoader and your sampler; stacking means chaining several of those nodes in series. • Stacks normally on top of a single acceleration/turbo LoRA; keep only one distill LoRA active in the chain. • The author ships builds for both checkpoint families — pair each build with its own checkpoint and never cross-pair them. ─────────────────────────────────────────────────────────────────────────────── PROS ─────────────────────────────────────────────────────────────────────────────── + Well established — 1,782 downloads. [source: CivitAI stats] + Positively received — 143 thumbs-up with no down-votes. [source: CivitAI stats] + Explicit trigger word(s) — LYS-Style, plasticine-transforms, plasticine-melts — so the effect can be turned on and off from the prompt. [source: model metadata] + Author documents use across several modes (REF2V, T2V, FL2V, I2V). [source: description] + Compact at 284 MB — cheap to stack with other LoRAs. [source: file size] + Author published concrete recommended settings. [source: description] ─────────────────────────────────────────────────────────────────────────────── CONS & CAVEATS ─────────────────────────────────────────────────────────────────────────────── - Author labels this experimental — results vary shot to shot. [source: description] ─────────────────────────────────────────────────────────────────────────────── COMPATIBILITY WARNING ─────────────────────────────────────────────────────────────────────────────── MiniMax H3 ships two transformers that share tensor key names: the fl2va checkpoint (driving T2VA, I2VA, L2VA and FL2VA) and the separate ref2va checkpoint (driving Ref2VA). Loading a LoRA against the wrong family can silently degrade output instead of raising an error, so confirm the family above matches the checkpoint you have loaded. Likewise, LoRAs built for full checkpoints often throw adaln_proj shape errors on pruned ones — match the build to your checkpoint. ─────────────────────────────────────────────────────────────────────────────── AUTHOR'S DESCRIPTION ─────────────────────────────────────────────────────────────────────────────── Claymation Transformation - MiniMax H3 / Wan2.2-2.1 14b I2V Where objects melt, stretch, and squish into something entirely new! This Minimax H3 Reference2Video LoRA aims to replicate the surreal, handcrafted look of plasticine/claymation animations, where objects morph into others with fluidity. Heavily inspired by the classic cartoon "Last Year's Snow was Falling" (LYS). (although the likeliness is obviously not 100% because of MH3's training rigidness) Trained for 159 epochs using a musubi-tuner fork by AkaneTendo. Special thanks for the implementation of the stop-flag file as it allowed me to save the model at the minimum loss of a very unstable train. Training techniques: ostris de-distill adapter, CFG loss, base preservation loss. MiniMax H3 Prompting Info Example prompt: LYS-style transformation video. realistic cup of coffee is shown on a table. Suddenly, the realistic cup of coffee plasticine- transforms into a realistic parrot. The two necessary trigger words are: "LYS-style", "plasticine- transforms"/"plasticine-melts". This model is trained in reference2video-audio_omni mode and is very versatile! You can throw many reference images, or 1 or 0 for text2video. Workflow in JSON form: https://huggingface.co/kabachuha/mh3-r2va- claymation-transformation/blob/main/mh3-r2va-lys-workflow.json . Wan2.2 I2V Prompting Info While this doesn't generate videos from scratch, it leverages the power of Wan.2.2 I2V 14b to create really stunning transformations. Just input the first or the last frame. If you have no idea where to source them, you can use the version for Wan2.1 text2video (read below) in the "text2image" mode when you set the input latent frame count to 1 and then save this 1 resulting frame as a picture. The trigger words are 'Claymation transformation' and 'plasticine- transforms'. The best prompts are: Claymation transformation. The video begins with an [object] standing before a [describe background]. [optional object description]. Then the [object] plasticine-transforms into an [another object, object description]. Simplified: Claymation transformation. The video begins with an [object]. Then the [object] plasticine-transforms into [another object]. Bonus. You can specify multiple transformations in the same video! Claymation transformation. The video begins with an [subject] sitting on a table. Then the [subject] [does triggering action]. The [subject] squishes, shrinks and the [subject] then plasticine-transforms into an [object_1], which then plasticine-melts into a [object_2]. This LoRA should be quite beginner-friendly. Wan2.1 T2V Info Works great both standalone and with VACE for first-last-frame selection and image to video! The examples illustrate each mode: 3 x pure text2video, 2 x image2video (set start, set end), 1 x flf2video (interpolation). The generation resolution is advised to be 480p or close (e.g. 512x512). The trained durations are from 1 to 5 seconds, with the most tested one of 3 seconds. (48 frames) The t2v training was made using diffusion-pipe for 135 epochs and flow shift of 4.0 on the dataset of metamorphoses from the legendary plasticine animation "Last Year's Snow Was Falling" . Due to the specifics of the train material, you may sometimes encounter a hut-like interior with four-sectional windows in the default mode, so it's encouraged to write the background appearance in the text2video mode manually. Though less often, some parts of the main character's appearance can happen (like the villager hat), in this case add 'lys-man' to the negative prompt. For text2video I tested with cfg 6.0, shift 5.0. For image2video/flf2video recommended to use with the kijai VACE workflows, standard 1.0 lora weight, 6.0 cfg, 16.0 shift + cfg_zero_star. (see videos meta) ─────────────────────────────────────────────────────────────────────────────── 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, 800x800) still: 01_poster.jpg 02_video.mp4 (video, 800x800) still: 02_poster.jpg 03_video.mp4 (video, 800x800) still: 03_poster.jpg 04_video.mp4 (video, 800x800) still: 04_poster.jpg 05_video.mp4 (video, 800x800) still: 05_poster.jpg 06_video.mp4 (video, 800x800) still: 06_poster.jpg ─────────────────────────────────────────────────────────────────────────────── HOW TO USE (COMFYUI) ─────────────────────────────────────────────────────────────────────────────── 1. Copy the .safetensors file into ComfyUI/models/loras/ 2. Load the matching H3 checkpoint with UNETLoader. 3. Insert LoraLoaderModelOnly between the loader and your sampler. 4. Set strength as listed above, then add any trigger word to the prompt. 5. Keep CFG at 1.0 with BasicGuider unless you know you want real CFG. ─────────────────────────────────────────────────────────────────────────────── Scraped by lorakit on 2026-09-04 23:06 UTC. Stats and description are the author's; pros/cons are derived from the evidence tagged beside each line. ───────────────────────────────────────────────────────────────────────────────