Make a 16 megapixel picture from a prompt, or edit a picture in plain words. For an edit, you can give MiniMax H3 Image up to seven more pictures and tell it what to take from each one.<h3 id="how-to-use-it">How to use it</h3><ol><li>Drop the workflow into ComfyUI and press Run. It opens with a full prompt, so you get a picture right away.</li><li>For your own picture, write a full description. Or turn Auto prompt on and write a few words: a writer turns them into the long description the model wants.</li><li>To edit, turn Edit a picture on, load your picture and write the change, for example “Make it snow.” Auto prompt works here too: it looks at your pictures and writes out the change from a few words.</li><li>For a reference, connect an image loader to picture 2 on Write the prompt. Add more in order through picture 8. Name the picture in your request, for example “Put the jacket from picture 2 on the woman in picture 1.”</li><li>Size picks 4 MP or 16 MP. Fast runs 2 steps instead of 6. Upscale the result doubles a 4 MP picture with SeedVR2.</li></ol><h3 id="what-you-need">What you need</h3>Update ComfyUI and <a target="_blank" rel="ugc" href="https://github.com/ausboss/ComfyUI-AusBoss">AusBoss nodes</a> first. MiniMax H3 Image support was added to ComfyUI on 2026-11-10, after version 0.44.0, so you need a build newer than that. This version ran on AusBoss nodes 2.23.0. The workflow opens on High VRAM.<ul><li>High VRAM · <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3-Image/resolve/main/diffusion_models/minimax_h3_image_pruned_int8_convrot.safetensors">minimax_h3_image_pruned_int8_convrot.safetensors</a> → <code>models/diffusion_models</code> · 21.0 GB</li><li>Low VRAM · <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3-Image/resolve/main/diffusion_models/minimax_h3_image_pruned_w4a8.safetensors">minimax_h3_image_pruned_w4a8.safetensors</a> → <code>models/diffusion_models</code> · 12.5 GB</li><li>Both · <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3-Image/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>Both · <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3-Image/resolve/main/vae/minimax_h3_image_vae_fp16.safetensors">minimax_h3_image_vae_fp16.safetensors</a> → <code>models/vae</code> · 1.2 GB</li><li>Auto prompt · <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3-Image/resolve/main/text_encoders/qwen3.5_9b_w4a8_gptq.safetensors">qwen3.5_9b_w4a8_gptq.safetensors</a> → <code>models/text_encoders</code> · 7.3 GB</li><li>Fast · <a target="_blank" rel="ugc" href="https://huggingface.co/akhaliq/p-h3-image-pdmd-2step/resolve/main/minimax_h3_pdmd_2nfe_comfyui.safetensors">minimax_h3_pdmd_2nfe_comfyui.safetensors</a> → <code>models/loras</code> · 1.96 GB</li><li>2× upscale · <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/SeedVR2/resolve/main/diffusion_models/seedvr2_3b_int8_convrot.safetensors">seedvr2_3b_int8_convrot.safetensors</a> → <code>models/diffusion_models</code> · 3.46 GB</li><li>2× upscale · <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/SeedVR2/resolve/main/vae/seedvr2_ema_vae_fp16.safetensors">seedvr2_ema_vae_fp16.safetensors</a> → <code>models/vae</code> · 501 MB</li></ul><h3 id="tips">Tips</h3><ul><li>On an RTX 5090 a new 16 MP picture took about 22 seconds and a 16 MP edit about 35. At 4 MP an edit took about 12.</li><li>Put any words that should appear in the picture in quotes. Signs and posters spell them right. Small text far from the subject can still come out as nonsense.</li><li>Leave Auto prompt off when your prompt is already a full description. In our runs of the opening prompt, rewriting it tangled the hands.</li><li>On an edit, Auto prompt makes a bigger change from a few words, like “vampire” or “winter”. For a small, exact change, leave it off.</li><li>For an edit, say what should stay the same as well as what you want to change.</li><li>Fast frames a little tighter and small words can come out wrong. Leave it off for posters and covers.</li></ul>MiniMax-H3-Image is by MiniMax and uses the <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3-Image">MiniMax-H3-Image Community License</a>. Powered by MiniMax-H3-Image. The 2-step LoRA is <a target="_blank" rel="ugc" href="https://huggingface.co/akhaliq/p-h3-image-pdmd-2step">akhaliq's pDMD</a>. Optional upscaling uses <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/SeedVR2">SeedVR2</a> under Apache 2.0.v1.0 (2026-11-10) · First release.v1.1 (2026-11-11) · Auto prompt now works on edits and sees every picture you plug in.<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 Image Generate + Edit | 16 MP, 8 Pictures

Auto prompt now works with Edit a picture on. The writer looks at your picture and every extra picture you plugged in, and writes out the change from a few words. With Auto prompt off nothing changes: the same settings give the same picture as v1.0. Tested with ComfyUI's master branch (commit ede4e5f) and AusBoss nodes 2.23.0.

Files with SHA256: fa9a66a89bb09e19059c66664eb87c54214a6a7ce59fc98db2c19e5bb2cdef96