Experimented a bit before releasing but this model is the best out there right now easily for motion control. I will require a WAN character lora for the best possible likeness retention but can work without. Inputs are base reference image and video reference for movement The workflow attached as the free version is the official comfyui template , didn't test it as I kinda hate subgraphs Models should be the same, example was made with my workflow at medium resolution! My version with infinite length is already up for subs in the video workflows section Model: https://huggingface.co/Comfy-Org/SCAIL-2/tree/main/diffusion_models Sam3.1 in checkpoints: https://huggingface.co/Comfy-Org/sam3.1/blob/main/checkpoints/sam3.1_multiplex_fp16.safetensors Vae & Text encoders - wan_2.1_vae.safetensors: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors - umt5_xxl_fp8_e4m3fn_scaled.safetensors: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors - clip_vision_h.safetensors: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/clip_vision/clip_vision_h.safetensors Loras - lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors: https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/Lightx2v/lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors

Krea2 turbo: https://huggingface.co/Comfy-Org/Krea-2/resolve/main/diffusion_models/krea2_turbo_fp8_scaled.safetensors Text encoder: https://huggingface.co/Comfy-Org/Krea-2/resolve/main/text_encoders/qwen3vl_4b_fp8_scaled.safetensors vae: https://huggingface.co/Comfy-Org/Krea-2/resolve/main/vae/qwen_image_vae.safetensors You can also use the Wan2.1 vae for this model, can get sharper results Controlnet Is included in the sub version!! Wanna sub? Over here: https://www.skool.com/ai-tech-and-comfyui-workflows-2226/plans

Consistency is on point with this new model and it does NSFW as well - Training and sub workflow coming soon. Will also be releasing my Krea realism LoRA to subs / Course members, stay tuned! (Applied in these images)

Wondering if i can just use the same wan2.2 lora i have without any nsfw images in the dataset? Or Is there a better way to do nsfw? Not seeing anything in the sub section just sdxl

Has anyone tried using Gemini to generate images and then using those images to train a Flux LoRA? How do the results turn out?