Preserve a character across camera-angle changes: proposed Qwen 2509 keyframes to Wan 2.2 video workflow

Preserve a character across angle changes: approve angle keyframes, then animate them Proposed combined workflow, not a reproduced result: use Qwen-Image-Edit-2509 to prepare still keyframes from the same approved character reference, review those stills, and animate each approved keyframe with the pinned Wan2.2 5B image-to-video graph. The individual interfaces below are documented. Their combination and identity retention across angles have not been tested here. 1. Prepare references you are entitled to use. Keep one approved character image as the anchor for each angle; optionally add a scene reference. Qwen's pinned 2509 card documents multi-image editing with best reported results at one to three images and reports improved person/pose consistency. That is the author's claim, not an angle-retention guarantee. A hidden face or unseen costume surface cannot be checked from a single front view. 2. Use the documented base route, with no angle LoRA or Lightning dependency: QwenImageEditPlusPipeline.from_pretrained("Qwen/Qwen-Image-Edit-2509", torch_dtype=torch.bfloat16), on CUDA. Its example passes image=[image1,image2], prompt, generator=torch.manual_seed(0), true_cfg_scale=4.0, negative_prompt=" " (one space), num_inference_steps=40, guidance_scale=1.0, num_images_per_prompt=1. It saves output.images[0]. These are source example values, not tested settings for this proposed shot. The card asks for current diffusers; pin the actual installed revision for comparison. No 12 GB claim is made for this editing stage. 3. Proposed angle prompt, untested: 'Using image 1 as the character identity reference and image 2 as the scene reference, show the same character from a camera 45 degrees to the left. Preserve the face, hair, costume, proportions and prop placement; keep the scene lighting consistent.' If using only the character reference, omit the image-2 clause. For the reverse shot, change only the requested view. The model may invent unseen detail or alter identity; this prompt is a way to request constraints, not evidence that they will hold. 4. Approve each still before animation. Compare face, hair, costume, proportions, handed props and scene layout with the anchor. Reject drifted stills instead of treating them as new identity references. This manual check is a proposed production control. Record failed attempts and the reason for rejection. 5. Feed each accepted still to LoadImage in the official ComfyUI video_wan2_2_5B_ti2v template at commit 3c2199b9362457b12b9c60c6cc303501526ebd62. Enable that bypassed node with Ctrl+B. Its three files are wan2.2_ti2v_5B_fp16.safetensors in models/diffusion_models, umt5_xxl_fp8_e4m3fn_scaled.safetensors in models/text_encoders, and wan2.2_vae.safetensors in models/vae. Saved defaults: 1280x704, 121 frames, batch 1, shift 8, 20 steps, CFG 5, uni_pc/simple, denoise 1, 24 fps. The seed randomizes; save the actual generated value. These defaults are not a measured memory or quality result. 6. Proposed motion prompt: '[approved character and scene]. The subject [one action]. Camera [one modest move]. Preserve the approved wardrobe and props.' Check start/middle/end frames and the cut between angles; a correct start still does not guarantee the later face remains stable. Save input/output hashes, both models' weight revisions, prompts, seeds, settings, runtime versions and rejected outputs. Alternative: the separate Wan2.1 Fun Camera v1.1 14B graph documents explicit start-image and camera conditioning. Its default Zoom Out is not a demonstrated orbit or angle-preservation test. The dx8152 Qwen2509 Multiple-angles LoRA card supplies rotation prompts but reports a consistency issue and requires a Lightning component without pinning its exact checkpoint; it is not needed in the base route above. Veda's R2VA preview documents reference-conditioned generation, but its recovered card does not specify a custom-reference manifest schema or prove identity retention. None is a universal replacement for keyframe review. Scope and rights: these pinned documents describe Qwen-Image-Edit-2509 and Wan2.2-TI2V-5B, not every current model. The Qwen card declares Apache-2.0; inspect applicable model/component terms and reference-image rights separately. No media, model weights, likeness rights or tested success rate is granted by this original synthesis. Shared-founder desk curation: source_inspected, not_run, unreviewed.

{
  "citations": [
    {
      "url": "https://huggingface.co/Qwen/Qwen-Image-Edit-2509/raw/d3968ef930e841f4c73640fb8afa3b306a78167e/README.md",
      "note": "qwen2509-base.txt; UTF-8 bytes [1298,2693); excerpt SHA256 89487fecae96bf83a7ea09d9d77ec24918c6387e4059d1a6015f6793b18d789e"
    },
    {
      "url": "https://huggingface.co/Qwen/Qwen-Image-Edit-2509/raw/d3968ef930e841f4c73640fb8afa3b306a78167e/README.md",
      "note": "qwen2509-base.txt; UTF-8 bytes [2693,3884); excerpt SHA256 e262af4d8a59e7888ffb916a01f6e57395fcbcd0df30da8b4fdf12d1e2970ed0"
    },
    {
      "url": "https://huggingface.co/Qwen/Qwen-Image-Edit-2509/raw/d3968ef930e841f4c73640fb8afa3b306a78167e/README.md",
      "note": "qwen2509-base.txt; UTF-8 bytes [9293,9358); excerpt SHA256 b604b00b67e1684bb80f3ecfcf335af6dbb5bb83464eb44d9c2e94c57826f20e"
    },
    {
      "url": "https://huggingface.co/dx8152/Qwen-Edit-2509-Multiple-angles/raw/c342b0e746c3a3275af1a4a0c6ae78e0e4802531/README.md",
      "note": "qwen2509-angles.txt; UTF-8 bytes [699,890); excerpt SHA256 3bcc7d9d846216449ff642fa6218b5beeafe1fbf31474b7d566521b8ea49217e"
    },
    {
      "url": "https://huggingface.co/dx8152/Qwen-Edit-2509-Multiple-angles/raw/c342b0e746c3a3275af1a4a0c6ae78e0e4802531/README.md",
      "note": "qwen2509-angles.txt; UTF-8 bytes [975,1200); excerpt SHA256 f104c03a4bba4402803d9a4ea6ffedfcb44e3695da4dc3750e9321b72b17b26b"
    },
    {
      "url": "https://huggingface.co/dx8152/Qwen-Edit-2509-Multiple-angles/raw/c342b0e746c3a3275af1a4a0c6ae78e0e4802531/README.md",
      "note": "qwen2509-angles.txt; UTF-8 bytes [2031,2209); excerpt SHA256 2d9cce2f6fcf13eddcb5a9d68fff6c5da1383275cd5a2df14cfba68fea5bca7a"
    },
    {
      "url": "https://huggingface.co/Veda-Sparse/Minimax-H3-R2VA-Veda-Preview/raw/1598b407905b7c0af85aa0c13acdfa6f01ff2982/README.md",
      "note": "veda-r2va.txt; UTF-8 bytes [12346,13536); excerpt SHA256 2c0af912775cdc1e30d0c4582ecc56e1f1d480d00dabb1b14fdefa9c54a63040"
    },
    {
      "url": "https://huggingface.co/Veda-Sparse/Minimax-H3-R2VA-Veda-Preview/raw/1598b407905b7c0af85aa0c13acdfa6f01ff2982/README.md",
      "note": "veda-r2va.txt; UTF-8 bytes [13536,13634); excerpt SHA256 8187b99981cc906f326840313ebb3709d464562955386f99a17ea1b38d2a3634"
    },
    {
      "url": "https://raw.githubusercontent.com/Comfy-Org/workflow_templates/3c2199b9362457b12b9c60c6cc303501526ebd62/templates/video_wan2_2_5B_ti2v.json",
      "note": "wan22-template.txt; complete original workflow JSON; detailed node checks in VIDEO-REVIEW.json; excerpt SHA256 23c93b88adecbdf5bcf4c5438117070fe757f30aca373dd6a2eb488d2c6a585a"
    },
    {
      "url": "https://raw.githubusercontent.com/Comfy-Org/workflow_templates/3c2199b9362457b12b9c60c6cc303501526ebd62/templates/video_wan2.1_fun_camera_v1.1_14B.json",
      "note": "wan21-camera-template.txt; complete original workflow JSON; detailed node checks in VIDEO-REVIEW.json; excerpt SHA256 5b2c8d5e4a58994325c43bac8f721b897c8b2af1416af36bb7131908ce545aae"
    }
  ]
}