P-H3-Image Generate + Edit | 8 Pictures + Auto Prompt

Edit a picture in plain words or make a new one from scratch. For an edit, you can give P-H3 up to seven more pictures and tell it what to take from each one.

P-H3 makes its best pictures at 8 MP. Smaller sizes can give blurry faces and artifacts. The Size pill sets edits and new pictures to 4 MP or 8 MP: pick 8 MP if your card can take it.

How to use it

1. Drop the workflow into ComfyUI. Load the picture you want to change and write your edit.

2. 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 “Give the person in picture 1 the jacket from picture 2.”

3. Press Run. Drag the comparison slider to check what changed. Auto prompt shows the expanded request in Show Text.

4. To generate from words, turn Edit a picture off and choose a shape in Latent Size. The workflow scales it to the Size you picked. Turn Upscale the result on if you want SeedVR2 to double the width and height.

What you need

Update ComfyUI and AusBoss nodes first. This version ran on ComfyUI 0.44.0 with AusBoss nodes 2.20.5. Pick one matching model and text encoder pair. The workflow opens on Low VRAM.

• Low VRAM · p-h3-image_w4a8.safetensors → models/diffusion_models · 13.4 GB

• Low VRAM · p-h3-image_text_encoder_w4a8.safetensors → models/text_encoders · 3.6 GB

• High VRAM · p-h3-image_int8_convrot.safetensors → models/diffusion_models · 21.2 GB

• High VRAM · p-h3-image_text_encoder_int8_convrot.safetensors → models/text_encoders · 5.1 GB

• Both · p-h3-image_vae_int8_convrot.safetensors → models/vae · 3.1 GB

• Low VRAM · Auto prompt · p-h3-image_prompt_upsampler_w4a8.safetensors → models/text_encoders · 6.7 GB

• High VRAM · Auto prompt · p-h3-image_prompt_upsampler_bf16.safetensors → models/text_encoders · 19.3 GB

• 2× upscale · seedvr2_3b_int8_convrot.safetensors → models/diffusion_models · 3.46 GB

• 2× upscale · seedvr2_ema_vae_fp16.safetensors → models/vae · 501 MB

Tips

• With Auto prompt off, say what should stay the same as well as what you want to change.

• Check faces, lighting and the background after a multi-picture edit. The model can change more than you asked for.

• Size: 4 MP | 8 MP sets the size of an edit and of a new picture. 4 MP is the default and uses less memory. 8 MP can improve faces and fine detail, with more memory and time. P-H3 makes its best new pictures at 8 MP.

• Higher resolution does not lock identity. Check the face against the original after an edit.

Powered by MiniMax H3. P-H3-Image is by Pruna AI and uses the MiniMax H3 Community License. Optional upscaling uses SeedVR2 under Apache 2.0.

v1.1 (2026-11-07) · Added the Size choice, 4 MP or 8 MP, for edits and new pictures. Low VRAM now uses the smaller prompt writer.

v1.0 (2026-11-06) · First release.

Report an issue · Discord · YouTube @ausbossdev · X @Zanzibased · GitHub