FLUX.2 Kontext Img2Img — Multi-Reference + Strength-Guidance Image Editing Workflow by TripTrap
Files:
flux-2-klein-9b-kv-fp8.safetensors
qwen_3_8b_fp8mixed.safetensors
Description
This workflow turns FLUX.2's native Kontext architecture into a fully-featured image-to-image
editing powerhouse. Built from the ground up over months of iteration, it gives you surgical
control over how reference images influence your generations — from subtle texture injection to
complete stylistic transformation.
Whether you're editing album art, refining character designs, or exploring glitch aesthetics,
this workflow lets you feed in up to 2 reference images and dial in exactly how much they
influence the output with a single strength slider.
### What makes this different
- FLUX.2 Native — This isn't a hack. It uses FLUX.2 klein 9B KV-FP8's built-in Kontext reference
system for clean, artifact-free image conditioning
- Strength Control — A denoise slider that actually works. 0.0 = no change, 1.0 = full
generation. No cryptic parameters.
- Multi-Reference — Chain up to 6 reference images through the Kontext system for composite influences
- Prompt Engineering — Built-in text concatenation for complex multi-source prompts
- VRAM Safe — Auto-scales images to 0.5MP before encoding, preventing accidental OOM crashes
- 4-Step Generation — Optimized for FLUX.2's distilled inference. Blazing fast.
### How it works
```
Reference Image → Scale → VAE Encode ──┐
├──→ ReferenceLatent Chain → Conditioning → Sampler
Reference Image → Scale → VAE Encode ──┘
↑
Prompt → Text Concat → CLIP Encode → Flux Guidance ──────────┘
```
The reference images are injected directly into FLUX.2's Kontext conditioning system — the same
mechanism the BFL API uses internally. No separate style models, no CLIP vision encoders, no
bloat.
### Requirements
Models (download and place in ComfyUI/models/):
┌────────────────────────────────────┬───────────────────┐
│ File │ Location │
├────────────────────────────────────┼───────────────────┤
│ flux-2-klein-9b-kv-fp8.safetensors │ diffusion_models/ │
├────────────────────────────────────┼───────────────────┤
│ qwen_3_8b_fp8mixed.safetensors │ text_encoders/ │
├────────────────────────────────────┼───────────────────┤
│ flux2-vae.safetensors │ vae/ │
└────────────────────────────────────┴───────────────────┘
Custom Nodes: (install via ComfyUI Manager)
- rgthree-comfy (Power Lora Loader)
- ComfyUI-Custom-Scripts (ShowText)
- ComfyUI_Comfyroll_CustomNodes (CR Aspect Ratio)
### How to use
1. Load the workflow JSON (drag into ComfyUI)
2. Load your base image in Ref 1
3. Optionally load a second reference in Ref 2
4. Write your prompt
5. Set denoise (0.65 is a good starting point)
6. Queue it
### Tips
- 0.5–0.65 denoise: Subtle edits, preserves composition
- 0.65–0.8 denoise: Balanced changes with strong reference influence
- 0.8–1.0 denoise: Heavy transformation, prompt dominates
- Use 4 steps for speed, or up to 8 for more refinement
- Keep images under 1MP for best performance
### License
This workflow is free to use under the FLUX Non-Commercial License.
Respect the model license terms.
────────────────────────────────────────────────────────────────────────────────
▶ YouTube — TripTrap Music
https://www.youtube.com/c/TripTrap1?sub_confirmation=1
▶ Spotify — TripTrap Artist
https://open.spotify.com/artist/7vPfTIL4FweqDqTjcw4Bvr
▶ Apple Music — TripTrap
https://music.apple.com/us/artist/triptrap/1760346233
────────────────────────────────────────────────────────────────────────────────
Built by TripTrap — glitch artist, experimental pop producer, and AI alchemist.
Every image this workflow generates carries a frequency. Make it yours.
Description
Fully unlocked 🔓 - NSFW
Model:
https://civitai.red/models/2382648/pornmaster-flux2-klein?modelVersionId=2763416
LORA's:
https://civitai.red/models/2324315/klein-4b9b-base-to-turbo-lora
https://civitai.red/models/2121900/flux2klein-9b-anything2real-lrzjason
https://civitai.red/models/1934100/anime2real?modelVersionId=2674717
Prompt example:
The photo was processed to a realistic style, creating a lifelike cosplay photo.
Maintain consistency in character, hairstyle, and clothing. And maintain consistency in facial expressions and posture.
Maintain consistency in the characters' hair color.
FAQ
Comments (7)
Hello, the manager did not find the nodes.😢
My help will only be as informative as the questions given...
AKA
That tells me absolutely nothing.
Hi, great workflow!
-how to add 2nd ref img or more?
-Category "celebrity man/woman" ...how does it work? if i prompt a celebs name a unknown person appears.
See the 5 groups under the first image reference group that are all bypassed?
Simply enabling a group... enables it to be referenced.
*a simple way is enabling "Show fast toggles in Group Headers" in rgthree-comfy settings
The 5 groups under those though are simply a way to generate differing image-guidance strengths.
The category thing is a set-it-forget-it thing. You don't need to type literally anything, just choose random or set it to one choice from that drop-down and run the workflow
(and that goes for every other selectable option in the "optional prompter" groups as well)-
it'll auto-add it to everything else. ... All those nodes are connected together purposely to be as hands-off and easy as possible. You can see the final combined prompt result...right next to your starting prompt in that black box.
Thx for reply,
yeah some category's work but the workflow does not look like yours in the attached .png, because /ComfyUI-ZImagePowerNodes import failed. tried to git clone but not working either, have to figue out why, anyone?
@dude402 Yeah, instead of using the newest version- use version 1.0.0
That's what I'm using, forgot to mention that.
(along with A LOT more other things about the workflow, I'm sure.)
*give my message a react if this worked so I know this is resolved 👍
got it sorted, Z-Image Power Nodes V1.0 did the trick. :-)
just a q on the "special" character's: is it correct that they look no way near like the real one?
i was hoping for something like"sensual_beautiful_angels" on Instagram! :-)