<a target="_blank" rel="ugc" href="https://www.youtube.com/watch?v=n4yO0oqBWdM">▶ Video guide: how I made a meme edit with it, one cut at a time</a>: <a target="_blank" rel="ugc" href="https://www.youtube.com/watch?v=n4yO0oqBWdM">https://www.youtube.com/watch?v=n4yO0oqBWdM</a>Make a clip from your own pictures, or change a video: swap a person, change one thing, copy its moves, or keep it going. Up to four pictures and one video, each with a job you pick.<a target="_blank" rel="ugc" href="https://discord.gg/RwVxY9Fuaj">Discord</a> · <a target="_blank" rel="ugc" href="https://www.youtube.com/@ausbossdev">YouTube @ausbossdev</a><h3 id="how-to-use-it">How to use it</h3><ol><li>Load a picture in Picture 1 and pick its job on H3 Prompt Writer: person, place, outfit or thing.</li><li>Type what happens, one line for each thing. <code>@1</code> is Picture 1: <code>@1 walks to the window and looks out.</code></li><li>Pick the length on Seconds.</li><li>Pick High VRAM for 24 GB or more or Low VRAM for 8 to 24 GB, and press Run.</li></ol>Everything else is a switch. Pictures turns on Picture 2 to 4. Video and sound adds your clip, its sound, a voice or a song. Extras has Fast preview and Auto prompt. Finish the clip has FlashVSR for a sharper, 2x bigger clip.<h3 id="what-it-can-do">What it can do</h3><ul><li>Your own place: Picture 2 as place. <code>@1 sits at the counter in @2</code></li><li>Two people: Picture 2 as person. <code>@1 and @2 sit side by side on a night bus</code></li><li>A new outfit: Picture 2 as outfit. <code>@1 walks down a runway wearing @2</code></li><li>Copy a dance: Video on, as copy its moves. <code>@1 dances on a rooftop at sunset</code></li><li>Put someone in a video: Video on, as swap the person. Name who goes, then add an <code>@1 looks like</code> line.</li><li>Change one thing in a video: Video on, as change something. <code>He wears @1 in place of his cap</code></li><li>A longer story: Video on, as keep going. Type what comes next.</li></ul>For only a person swap, the <a target="_blank" rel="ugc" href="https://civarchive.com/models/3040833">Person Swap workflow</a> is the smaller page.<h3 id="what-you-need">What you need</h3>Update ComfyUI (0.38.0 or newer; 0.45 or newer on 8 GB; Auto prompt needs 0.42.0 or newer) and <a target="_blank" rel="ugc" href="https://github.com/ausboss/ComfyUI-AusBoss">AusBoss nodes</a> (2.25.2 or newer) first.<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/diffusion_models/minimax_h3_ref2va_pruned_int8_convrot.safetensors">minimax_h3_ref2va_pruned_int8_convrot.safetensors</a> → <code>models/diffusion_models</code> · 21.0 GB</li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors">qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors</a> → <code>models/text_encoders</code> · 15.7 GB</li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_video_vae_fp16.safetensors">minimax_h3_video_vae_fp16.safetensors</a> → <code>models/vae</code> · 5.2 GB</li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_audio_vae_fp32.safetensors">minimax_h3_audio_vae_fp32.safetensors</a> → <code>models/vae</code> · 0.6 GB</li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/loras/pika_h3_flex_ref2va_v1_bf16.safetensors">pika_h3_flex_ref2va_v1_bf16.safetensors</a> → <code>models/loras</code> · 2.0 GB</li><li>Low VRAM · <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/diffusion_models/minimax_h3_ref2va_pruned_w6a8.safetensors">minimax_h3_ref2va_pruned_w6a8.safetensors</a> → <code>models/diffusion_models</code> · 16.0 GB, in place of the first file</li><li>Low VRAM · <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_video_vae_int8_convrot.safetensors">minimax_h3_video_vae_int8_convrot.safetensors</a> → <code>models/vae</code> · 2.8 GB, in place of the video VAE</li><li>Auto prompt · <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/text_encoders/qwen3vl_8b_int8_convrot.safetensors">qwen3vl_8b_int8_convrot.safetensors</a> → <code>models/text_encoders</code> · 9.35 GB</li><li>FlashVSR · <a target="_blank" rel="ugc" href="https://huggingface.co/ausboss/FlashVSR-v1.1-ComfyUI/resolve/main/flashvsr_v1.1_fp16.safetensors">flashvsr_v1.1_fp16.safetensors</a> → <code>models/diffusion_models</code> · 3.5 GB</li></ul>A 1.6 second swap at 864 x 480 took about half a minute on a 32 GB card with the models loaded. Low VRAM uses the two smaller files and makes a smaller clip.On 8 GB: pick Low VRAM, keep clips to 10 seconds or less, and have about 32 GB of system RAM. We tested by holding back all but 8 GB of a 5090 with RAM capped at 32 GB (ComfyUI 0.45.2): with four pictures a 5 s clip took 39 s, 8 s 72 s and 10 s 87 s, and 12 s ran out of memory; three pictures and a 10 s video took 150 s; an 8 s clip with FlashVSR on took 150 s.<h3 id="tips">Tips</h3><ul><li>Start with Fast preview on and a fixed seed. A draft that looks right can still miss at full size, so check the full size run before you call it done.</li><li>For a swap, the <code>@1 looks like</code> line does most of the work. Without it, the swap can start late or not happen at all.</li><li>A new person, a new place and a new thing all in one go is too much for a few plain lines. In our test the old person came back halfway. Do one change per run, or paste a full H3 prompt.</li><li>A full H3 prompt of your own: paste all six parts, from <code>subject_definitions:</code> to <code>non_diegetic_music:</code>, and it goes to H3 as it is. Your pictures are <code>&lt;Picture 1&gt;</code> to <code>&lt;Picture 4&gt;</code> in the order they are on, and your video is <code>&lt;Video 1&gt;</code>. With a video, set its job to swap the person so the clip keeps the video's length.</li><li>Making a long clip in pieces? Load the last frame of the piece before as a picture, and say in your prompt that the clip continues from it.</li><li>FlashVSR makes the clip 2x larger and sharper (480 x 768 becomes 960 x 1536). It runs with High or Low VRAM.</li><li>Auto prompt needs ComfyUI 0.42.0 or newer. On older versions it wrote a garbage sound line or crashed ComfyUI in our tests.</li><li>Keep the clip's sound also moves the new person's mouth to that sound. With music in the clip, they sing along.</li><li>Leave Pika at strength 1 and add no Turbo or Lightning LoRA. Pika is already the six-step speed-up.</li></ul>Powered by MiniMax H3 under the <a target="_blank" rel="ugc" href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE">MiniMax H3 Community License</a>. The Pika H3 Flex LoRA is by Pika; the ComfyUI files are Comfy-Org's. The optional finish uses <a target="_blank" rel="ugc" href="https://huggingface.co/ausboss/FlashVSR-v1.1-ComfyUI">FlashVSR v1.1</a> by Junhao Zhuang and the OpenImagingLab team, under Apache 2.0.v1.0 (2026-11-13): first release.<a target="_blank" rel="ugc" href="https://github.com/ausboss/ComfyUI-AusBoss/issues">Report an issue</a> · <a target="_blank" rel="ugc" href="https://discord.gg/RwVxY9Fuaj">Discord</a> · <a target="_blank" rel="ugc" href="https://www.youtube.com/@ausbossdev">YouTube @ausbossdev</a> · <a target="_blank" rel="ugc" href="https://x.com/Zanzibased">X @Zanzibased</a> · <a target="_blank" rel="ugc" href="https://github.com/ausboss">GitHub</a>

MiniMax H3 Pika Remix | High + Low VRAM, 8 GB+

First release. Runs on 8 to 32 GB cards: Low VRAM covers 8 to 24 GB, and FlashVSR finishes the clip. Needs AusBoss nodes 2.25.2 or newer and ComfyUI 0.38.0 or newer (0.45 or newer on 8 GB; Auto prompt needs 0.42.0 or newer).

Files with SHA256: 140790bf1f4eaff63cd75eb1bec990d86842de049600a6e3b63e37353159d965