Pornmaster_wan 2.2_14b_I2V_ double penetration

詳細

モデル説明

通義萬相AI生成影片—使用指南-中文

訓練使用的字幕下載。

Download the subtitles used in the training.

--

Pro-SDXL-V7-inpainting

--

最新加速器可讓生成的影片更穩定。

Using the latest accelerator can make the generated video more stable.

Wan_2_2_I2V_A14B_HIGH_lightx2v_4step_lora_v1030_rank_64_bf16

wan2.2_i2v_A14b_high_noise_lora_rank64_lightx2v_4step_1022

wan2.2_i2v_A14b_low_noise_lora_rank64_lightx2v_4step_1022

--

可加快動作速度:PainterI2V

It can speed up the action: PainterI2V

--

低噪聲與高噪聲LoRa必須同時使用。

範例影片使用WAN 2.2官方標準工作流生成。

我的影片使用「wan2.2_i2v_14b_fp8_scaled」生成。

主要適用於面部特寫照片,也可使用已進行雙插姿勢的全身照片。

LoRa權重使用0.95~1。

--

注意事項:(若生成的性器官容易出錯,僅需更換為最新版加速器即可。)

雙插姿勢過於複雜,此LoRa成功率約為30%。

背景不能是人物躺在枕頭上的畫面,否則會出現錯誤,可先透過圖片編輯替換背景。

由於影片中包含三人,性器官有時無法完美呈現。可提取影片中某一幀,再使用SDXL的局部重繪模型重新繪製性器官後繼續生成影片;或使用首尾幀方式生成影片。

使用首尾幀方式生成影片時,可搭配其他性愛LoRa,以增強陰莖插入陰道的動態感。

使用低細節照片會自然生成低細節的性器官,失敗率更高。

建議影片解析度為768以上,否則三人性器官在畫面中過小會導致失敗。

需簡要描述性愛場景與背景,例如:他們在草地上性交,背景為森林。

--

Low-noise and high-noise LoRa must be used together.

The example video was generated using the official WAN 2.2 standard workflow.

My video was generated using "wan2.2_i2v_14b_fp8_scaled".

Primarily used for close-up facial photos, but full-body photos of double penetration positions can also be used.

Lora uses a weight of 0.95~1.

--

Notes:

If the generated sex organs are prone to errors, simply switch to the latest version of the accelerator.

Double penetration positions are quite complex; the success rate of this LoRa method is approximately 30%.

The background cannot be a photo of someone lying on a pillow, as this will cause errors. You can replace the background first using image editing.

Because there are three people in the video, the sexual organs are sometimes not perfect. You can extract a frame from the video, and then redraw the sexual organs using the local redraw model of sdxl before generating the video. Alternatively, you can generate the video using the first and last frames.

When generating videos using the first and last frames, it can be combined with other sex loras to enhance the dynamic feel of penile insertion into the vagina.

Using low-detail photos will naturally generate low-detail sexual organs, increasing the likelihood of failure.

A video resolution of 768 or higher is recommended; otherwise, the sexual organs of the three people will be too small in the frame, leading to failure.

Please provide a brief description of the location and background of the sexual activity, for example: they had sex on a grassy field with a forest in the background.

When a vertical video fails, you can try generating a horizontal or square one.

--

RunningHub 提供多種實用工作流,例如文字轉圖像或圖像轉影片,請點擊連結:

https://www.runninghub.ai/workflows/?inviteCode=rh-v1304

透過上述連結註冊可領取1000 RH幣,約可免費生成20部影片;每日登入再贈100幣,免費使用!

首次註冊用戶若未收到1000 RH幣,請點擊右上角頭像 > 邀請碼 > 輸入邀請碼:rh-v1304

--

RunningHub offers many useful workflows, such as text-to-image or image-to-video conversion. Click the link below:

https://www.runninghub.ai/workflows/?inviteCode=rh-v1304

Register through the link above to receive 1000 RH tokens, which can be used to generate approximately 20 videos for free. Log in daily to receive an additional 100 tokens. Play for free!

If you are a first-time registered user and have not received 1000RH coins, please click on the avatar in the upper right corner > Invitation Code > Enter the invitation code: rh-v1304

--

觸發詞(Trigger words)

從左側進行性行為(Having sex from the left side):

一名女性,鏡頭迅速拉遠展現她的陰道,她的乳房與臀部隨動作晃動,她坐著並向後倚靠一名男性,該男性正從下方將陰莖插入她的肛門,另一名男性在左側將陰莖插入她的陰道,雙方陰囊持續晃動,她的雙腿張開,乳房明顯分開,下方男性的臀部清晰可見,

--

從右側進行性行為(Having sex from the right side):

一名女性,鏡頭迅速拉遠展現她的陰道,她的乳房與臀部隨動作晃動,她坐著並向後倚靠一名男性,該男性正從下方將陰莖插入她的肛門,另一名男性在右側將陰莖插入她的陰道,雙方陰囊持續晃動,她的雙腿張開,乳房明顯分開,下方男性的臀部清晰可見,

--

我的其他檢查點與LoRa。

My other checkpoints and Lora.

--

如果你喜歡我的LoRa,請用「buzz」鼓勵我。

If you like my lora, you can encourage me with "buzz".

--

客製化LoRa:我的Telegram ID:@iamddtla0620

我的微信ID:iamddtla

我的Line ID:iamddtla

時間寶貴,請直接說明需求,例如:訂製LoRa。

Customized lora: My Telegram ID: @iamddtla0620

My WeChat ID: iamddtla

My Line ID: iamddtla

Time is precious, please state your intention directly, for example: customized LORA.

このモデルで生成された画像

画像が見つかりません。