<h2 id="minimax-h3-ref2va-+-fl2va-workflow">Minimax H3 ref2va + fl2va Workflow</h2><ul><li>Simple toggle between ref2va and fl2va</li><li>Uses stock Minimax H3 sampler settings with <a target="_blank" rel="ugc" href="https://github.com/xmarre/ComfyUI-Spectrum-MiniMax-H3">Spectrum for a ~30-40% speed boost</a><ul><li>I have yet to find a single other combination that doesn't have some kind of worse downside - The turbo LoRAs suck.</li></ul></li></ul><ul><li><a target="_blank" rel="ugc" href="https://github.com/NikoDemon80/ComfyUI-H3-Motion-Context">Motion Context </a>video extension using save and load latents<ul><li>How to use in workflow</li><li>Can lead to gamma shift after extending - may need to manually adjust brightness/contrast</li></ul></li><li><a target="_blank" rel="ugc" href="https://github.com/Carasibana/ComfyUI-H3-FaceRefine">FaceRefine</a> for fixing distant garbled faces<ul><li>required custom_nodes that aren't on the ComfyUI Manager included in archive</li></ul></li><li>Simple postproduction settings<ul><li>Interpolation using <a target="_blank" rel="ugc" href="https://github.com/ethanfel/ComfyUI-Tween">https://github.com/ethanfel/ComfyUI-Tween</a><ul><li>GIMM VFI</li><li>SPEED VFI (seems better than RIFE at about the same speed)</li></ul></li><li>Upscale<ul><li>Tensorrt frame by frame upscale</li><li>RTX VSR</li></ul></li><li>RTX Denoise/Deblur</li></ul></li><li>Postproduction looping tools for fl2va using the same first and last frame<ul><li>clip still end or starting frames + audio</li><li>Smoothen out the loop with rife generated frames using Seamless Loop</li></ul></li><li>Generation Preview</li><li>Batch or single video upscale using GIMM VFI+Tensorrt as toggle below the main workflow<ul><li>throw your videos into any folder inside ComfyUI/input/... and toggle the batch upscale to get everything running</li></ul></li></ul>No workflow will help, if your prompt doesn't follow the guidelines. I recommend looking through the following prompting guides if you have no idea about Minimax H3 prompt and then use other's or my prompts as help to get started.I added the full workflows, including prompt and resources I used in the example videos, to the workflow archive. <a target="_blank" rel="ugc" href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/docs/VIDEO_PROMPT_WRITING_GUIDE_base_en.md">https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/docs/VIDEO_PROMPT_WRITING_GUIDE_base_en.md</a><a target="_blank" rel="ugc" href="https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/docs/VIDEO_PROMPT_WRITING_GUIDE_ref_en.md">https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/docs/VIDEO_PROMPT_WRITING_GUIDE_ref_en.md</a>Resources<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/blob/main/diffusion_models/minimax_h3_fl2va_pruned_int8_convrot.safetensors">https://huggingface.co/Comfy-Org/MiniMax-H3/blob/main/diffusion_models/minimax_h3_fl2va_pruned_int8_convrot.safetensors</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/MiniMax-H3-experimental/blob/main/minimax_h3_video_vae_int8_convrot.safetensors">https://huggingface.co/Kijai/MiniMax-H3-experimental/blob/main/minimax_h3_video_vae_int8_convrot.safetensors</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/blob/main/vae/minimax_h3_audio_vae_fp32.safetensors">https://huggingface.co/Comfy-Org/MiniMax-H3/blob/main/vae/minimax_h3_audio_vae_fp32.safetensors</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/blob/main/text_encoders/qwen3vl_32b_minimax_h3_int8_convrot.safetensors">https://huggingface.co/Comfy-Org/MiniMax-H3/blob/main/text_encoders/qwen3vl_32b_minimax_h3_int8_convrot.safetensors</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/MiniMax-H3-experimental/blob/main/loras/minimax_h3_ref_lora_rank_256_bf16.safetensors">https://huggingface.co/Kijai/MiniMax-H3-experimental/blob/main/loras/minimax_h3_ref_lora_rank_256_bf16.safetensors</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/lightx2v/Minimax-h3-Turbo/blob/main/minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors">https://huggingface.co/lightx2v/Minimax-h3-Turbo/blob/main/minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors</a></li><li>for low VRAM/RAM users<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/MiniMax-H3-experimental/blob/main/minimax_h3_fl2va_pruned_w4a8_mixed.safetensors">https://huggingface.co/Kijai/MiniMax-H3-experimental/blob/main/minimax_h3_fl2va_pruned_w4a8_mixed.safetensors</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/MiniMax-H3-experimental/blob/main/minimax_h3_ref2va_pruned_w4a8_mixed.safetensors">https://huggingface.co/Kijai/MiniMax-H3-experimental/blob/main/minimax_h3_ref2va_pruned_w4a8_mixed.safetensors</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/blob/main/text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors">https://huggingface.co/Comfy-Org/MiniMax-H3/blob/main/text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors</a></li></ul></li></ul>Thanks to<ul><li><a target="_blank" rel="ugc" href="https://github.com/Carasibana/ComfyUI-H3-FaceRefine">https://github.com/Carasibana/ComfyUI-H3-FaceRefine</a></li><li><a target="_blank" rel="ugc" href="https://github.com/NikoDemon80/ComfyUI-H3-Motion-Context">https://github.com/NikoDemon80/ComfyUI-H3-Motion-Context</a></li><li><a target="_blank" rel="ugc" href="https://github.com/xmarre/ComfyUI-Spectrum-MiniMax-H3">https://github.com/xmarre/ComfyUI-Spectrum-MiniMax-H3</a></li></ul>

Minimax H3 ref2va + fl2va + video extension (Motion Context) + FaceRefine Workflow

I'll use this as my resource upload for my H3 videos - this is the easiest way to share it. I'll update the file every now and then with the resources of some of my videos on request or whenever I feel like it.

Files with SHA256: ebce1461a5ac7c93c900931a55e405c4eda5ddb5009dbcadb76223944a381c15