中身は全部、今の実データ（到達間近の候補5件＋Animaの有力LoRA 3件）で同じ。違うのは見た目だけ。PC幅で見比べてください。
共通の考え方（前のデザイン勉強から）：色は飾りじゃなく「ベースの識別」に使う／数字（DL）は大きく太く／メタ情報（公開・作者・DL）はカード末尾に固定。
DL 1,000〜3,000。線に届いたら上の新着へ移ります。
Generate videos with 100+ camera control and VFX LoRAs for free on the Remade Canvas . Wan2.1 14B I2V 480p v1.0: Trained on 50 seconds of video comprised of 10 short clips (each clip c
Source: https://huggingface.co/silveroxides/flux1-nf4-unet/tree/main from silveroxides ☕ Buy me a coffee: https://ko-fi.com/ralfingerai 🍺 Join my discord: https://discord.com/invite/pA
As a classic technique in film and television creation, zooming out can extend from a close-up of a character to a grand scene, cleverly revealing the relationship between the environment and the char
Anima系モデルを寄せ集めたフランケンシュタイン・マージ。SLG併用（スキップブロック14、scale 1〜1.5）と30ステップ・CFG 4.5〜7が推奨設定。
Generate videos with 100+ camera control and VFX LoRAs for free on the Remade Canvas . Wan2.1 14B I2V 480p v1.0: Trained on 50 seconds of video comprised of 10 short clips (each clip c
Animaを少ステップ化するターボLoRAで、CFG 1・8〜12ステップが前提。他のAnima系にも効き、安定性と解剖の一貫性が上がる一方、細部と画風の追従は素より少し落ちる。
光の強さをスライダーで操るAnima向けLoRA。ウェイトを正負に振って光源を明るくも暗くもでき、「blue hour」のような光の指定語と組み合わせると自然に効く。
Showcase images are base model (left) vs LoRA (right). This LoRA does two things: Allows generating at higher resolutions. 1536 works without any major issues, and even 2048 (4 MP) now works witho
DL 1,000〜3,000。線に届いたら上の新着へ移ります。
Generate videos with 100+ camera control and VFX LoRAs for free on the Remade Canvas . Wan2.1 14B I2V 480p v1.0: Trained on 50 seconds of video comprised of 10 short clips (each clip c
Source: https://huggingface.co/silveroxides/flux1-nf4-unet/tree/main from silveroxides ☕ Buy me a coffee: https://ko-fi.com/ralfingerai 🍺 Join my discord: https://discord.com/invite/pA
As a classic technique in film and television creation, zooming out can extend from a close-up of a character to a grand scene, cleverly revealing the relationship between the environment and the char
Anima系モデルを寄せ集めたフランケンシュタイン・マージ。SLG併用（スキップブロック14、scale 1〜1.5）と30ステップ・CFG 4.5〜7が推奨設定。
Generate videos with 100+ camera control and VFX LoRAs for free on the Remade Canvas . Wan2.1 14B I2V 480p v1.0: Trained on 50 seconds of video comprised of 10 short clips (each clip c
Animaを少ステップ化するターボLoRAで、CFG 1・8〜12ステップが前提。他のAnima系にも効き、安定性と解剖の一貫性が上がる一方、細部と画風の追従は素より少し落ちる。
光の強さをスライダーで操るAnima向けLoRA。ウェイトを正負に振って光源を明るくも暗くもでき、「blue hour」のような光の指定語と組み合わせると自然に効く。
Showcase images are base model (left) vs LoRA (right). This LoRA does two things: Allows generating at higher resolutions. 1536 works without any major issues, and even 2048 (4 MP) now works witho
DL 1,000〜3,000。線に届いたら上の新着へ移ります。
Generate videos with 100+ camera control and VFX LoRAs for free on the Remade Canvas . Wan2.1 14B I2V 480p v1.0: Trained on 50 seconds of video comprised of 10 short clips (each clip c
Source: https://huggingface.co/silveroxides/flux1-nf4-unet/tree/main from silveroxides ☕ Buy me a coffee: https://ko-fi.com/ralfingerai 🍺 Join my discord: https://discord.com/invite/pA
As a classic technique in film and television creation, zooming out can extend from a close-up of a character to a grand scene, cleverly revealing the relationship between the environment and the char
Anima系モデルを寄せ集めたフランケンシュタイン・マージ。SLG併用（スキップブロック14、scale 1〜1.5）と30ステップ・CFG 4.5〜7が推奨設定。
Generate videos with 100+ camera control and VFX LoRAs for free on the Remade Canvas . Wan2.1 14B I2V 480p v1.0: Trained on 50 seconds of video comprised of 10 short clips (each clip c
Animaを少ステップ化するターボLoRAで、CFG 1・8〜12ステップが前提。他のAnima系にも効き、安定性と解剖の一貫性が上がる一方、細部と画風の追従は素より少し落ちる。
光の強さをスライダーで操るAnima向けLoRA。ウェイトを正負に振って光源を明るくも暗くもでき、「blue hour」のような光の指定語と組み合わせると自然に効く。
Showcase images are base model (left) vs LoRA (right). This LoRA does two things: Allows generating at higher resolutions. 1536 works without any major issues, and even 2048 (4 MP) now works witho